WO2025199409A1 - System and method for laboratory diagnosis and treatment targeting in idiopathic psychosis via psychosis biotypes - Google Patents

Abstract

A method and system for diagnosing an idiopathic psychosis patient and improving treatment targeting for that patient. Cognitive performance is measured on the patient. Pro- and anti-saccade signals are measured on the patient. Motor inhibition is measured on the patient. EEG signals are measured on the patient. Principal components analysis is applied to the measured signals and scales to determine the most significant features. The patient is evaluating on at least 11 dimensions of neuro-cognitive performance. A trained numerical taxonomy approach is used to classify the patient as belonging to a B-SNP psychosis Biotype and the patient's condition is categorized based on the classified Biotype. The B-SNIP psychosis Biotype is used to implement targeted treatment for an individual patient. The diagnostic algorithm is continuously re-trained using new cases and new laboratory tests to improve precision of B-SNIP psychosis Biotypes diagnosis and the accuracy of selecting treatments for individual patients.

Description

SYSTEM AND METHOD FOR LABORATORY DIAGNOSIS AND TREATMENT TARGETING IN IDIOPATHIC PSYCHOSIS VIA PSYCHOSIS BIOTYPES CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the benefit of and priority to U.S. Provisional Application No. 63/568,822 filed March 22, 2024, which is incorporated herein by reference in its entirety

STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH

This invention was made with government support under R01 MH124813, R01 MH127179, R01 MH127158, R01 MH124802, R01 MH077945, R01 MH096957, R01 MH078113, R01 MH096942, R01 MH096900, R01 MH094172, R21 MH126398, MH124804, MH127162, and MH103368 awarded by the National Institutes of Health. The government has certain rights in the invention.

FIELD OF THE INVENTION

The invention is generally in the field of diagnosis and/or treatment of serious psychiatric conditions, particularly diagnosis and/or treatment of psychosis (e.g., idiopathic psychosis) using bio-factors without regard to an indication of a Diagnostic and Statistical Manual (DSM) diagnosis.

BACKGROUND OF THE INVENTION

Many serious psychiatric conditions lack objectively measurable physical criteria for diagnosis. They are diagnosed only using clinical features which depend on reports by the patient and informants and the belief in those reports by the evaluating clinical staff. The lack of objective extra-clinical and measurable criteria hinders diagnostic validity, understanding of disease mechanisms, and therefore the appropriate treatment of many persons with serious psychiatric conditions.

Accordingly, a need arises for techniques that can accurately and objectively diagnose certain types of serious psychiatric conditions such as psychosis. Laboratory-based diagnosis can be more valid for appropriate treatment selection for individual psychosis patients.

SUMMARY OF THE INVENTION

This disclosure and diagnostic and/or treatment concepts described herein resulted from (i) an observation by the inventors that conventional Diagnostic and Statistical Manual (DSM) psychosis diagnoses defined only by clinical features, as decided by committee consensus, do not capture actionable differences in brain structure and function; and (ii) a diagnostic device collaboratively derived by the inventors that combined the use of multiple biomarkers agnostic to DSM psychosis diagnoses and optionally unsupervised machine learning to derive biological subtypes of psychosis (called “psychosis Biotypes”) that are replicable and cross-validate between independent samples; and (iii) that such “Bipolar-Schizophrenia Network for Intermediate Phenotypes (B-SNIP) psychosis Biotypes” reveal differences on biological measures not used to construct the Biotypes (external validation); and (iv) those differences on biological measures provide specific psychosis Biotype diagnoses of idiopathic psychosis patients with treatment targets that follow directly from those diagnoses; and (v) those treatment targets are not derivable from any other currently available approach to idiopathic psychosis diagnosis.

The techniques described herein comprise a method for laboratory-based diagnosis of a patient into a B-SNIP psychosis Biotype. Cognitive performance (problem solving abilities, decision-making, and complex behavioral responses, including stop-signal task performance and pro- and anti-saccades) is measured from a patient. Speed of responding in simple and complex behavioral tasks are measured from a patient. Ongoing electroencephalography (EEG) signals from the brain are measured from a patient. Brain responses to specific types of stimuli (event-related potentials or ERPs) are measured from a patient. The individual laboratory measures are scored and integrated for the seven different laboratory testing procedures (general cognition, anti-saccades, pro-saccades, stop signal, resting EEG, two auditory ERP tasks). Prior to the algorithm’s application to an individual patient, or when re-tuning the algorithm after addition of a sufficient number of new cases, principal component analysis (PCA) is applied to the measured and quantified values within a measurement domain to determine the most significant features contributing to overall laboratory test outcomes. The outcomes of these analysis steps of neurobiological laboratory data, rather than clinical features, are used to form psychosis Biotypes. In one aspect, based on a large dataset, multiple quantitative approaches show the number of laboratory derived psychosis subgroups is three. In other aspects, the subgroups may vary in number. Preferably, numerical taxonomy using k-means clustering, an unsupervised machine learning algorithm, constructs a diagnostic system of three B-SNIP psychosis Biotypes based on these laboratory measures. In additional aspects, the solution replicates in a separate sample and cross-validates between two independent samples. Multiple other types of information (e.g., brain MRI measures) not included in the creation of B-SNIP psychosis Biotypes provide additional diagnostic value and indicate a superior construct validity (i.e., how well the diagnoses measure what they were intended to measure) and external validity (i.e., whether the diagnoses can be generalized to other contexts) for Biotype diagnoses compared to the prevailing DSM diagnostic method. Construct and external validity are shown using multiple approaches in this application and in the embodiments.

These outcomes illustrate that B-SNIP psychosis Biotypes yield specific neurobiological diagnoses of idiopathic psychosis, and those diagnoses yield specific treatment targets (e.g., brain physiology targets that may indicate response to a drug called clozapine) applicable to individual patients. B-SNIP psychosis Biotypes and accompanying unique treatment targets are an implementable outcome of the work described herein. B-SNIP psychosis Biotypes change the standard of care for persons with idiopathic psychosis in a way not derivable from any other available approach.

BRIEF DESCRIPTION OF THE DRAWINGS

The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.

So that the way the above recited steps and implementations of the present invention can be understood in detail, a more particular description of the innovative work, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this innovative work, and the disclosure may admit to other equally effective embodiments. The algorithm is re-trainable and/or is continually re-trained with new cases and new laboratory measures based on accumulated experience of the inventors and relevant new information.

FIG. 1 illustrates the biomarker measure groups that differentiate and define B-SNIP psychosis Biotypes and their relationship to DSM diagnoses. These content groups alone are new and implementable outcomes of the disclosure for diagnosis and treatment selection.

FIG. 2 illustrates the number of Biotype cases with different DSM diagnoses and the number of DSM diagnoses with different Biotypes. This shows that (i) Biotypes do not recapitulate DSM diagnoses, (ii) DSM diagnoses, part of the current standard of care, do not offer neurobiological treatment targets, and (iii) B-SNIP psychosis Biotypes provide neurobiological treatment targets.

FIG. 3 illustrates the consistency of cognition and behavioral outcomes across two separate samples. This consistency supports practical application and implementation of these laboratory tests. FIG. 4 illustrates the consistency of ERP measurements across two separate samples. This consistency supports practical application and implementation of these laboratory tests.

FIG. 5 illustrates the gap statistic outcome for determining the number of Biotypes, with the arrow showing that the outcome stabilizes at three.

FIG. 6 illustrates the consistency of the Biotypes outcome as a function of sample sizes, which shows the number of participants needed to get a stable biomarker diagnostic system. This illustrates the power of this device to apply to individual cases, which has never been demonstrated for any psychosis diagnostic method. A consistent outcome is attainable only using the B-SNIP biomarker panel and large numbers of psychosis persons in the computations. This shows part of the requirements for the successful development of a clinically valid and implementable neurobiological diagnostic procedure for idiopathic psychosis.

FIG. 7 illustrates the bio-factors by Biotype groups in relation to healthy performance for both psychosis participants and their clinically healthy relatives. This pattern of bio-factors by Biotype provides one implementable approach for selecting targeted treatments specific to individual patients.

FIG. 8 illustrates DSM versus Biotype group differences in effect size units and the integrated separation of DSM versus Biotype groups using multiple measures. Biotype categories show larger effect sizes than DSM categories. This shows that only B-SNIP psychosis Biotypes yield distinctive pathophysiological signatures with unique treatment targets.

FIG. 9 illustrates the canonical discriminant function outcomes and the primary differentiators of each Biotype group, and that B-SNIP psychosis Biotypes yield distinctive and implementable treatment targets.

FIG. 10 illustrates external validation (construct validity) of the electrophysiological characteristics of B-SNIP psychosis Biotypes.

FIG. 11 illustrates the external validation (construct validity) structural anatomical (hippocampal complex) characteristics of B-SNIP psychosis Biotypes.

FIG. 12 illustrates the diagnostic value of an MRI-based machine learning classifier specifically for B-SNIP psychosis Biotype-1 (BT1). This MRI-based algorithm yields a unique and implementable test to verify the diagnosis of B-SNIP psychosis Biotype-1 (BT1) in a manner never previously demonstrated for any psychosis diagnostic system.

FIG. 13 illustrates the external validation of sensory training treatment implications for B- SNIP psychosis Biotypes. Level of performance on a tone matching test (y-axis) is shown as a function of eight training days (x-axis) for three different task difficulty levels. BT1 are the only group that improved over training days, consistent with our treatment targeting expectation. BT2 got worse over time and BT3, with the best overall performance, did not improve with training. This sensory training method yields another unique and implementable test to verify the diagnosis of B-SNIP psychosis Biotypes in a manner never previously demonstrated for any psychosis diagnostic system. This sensory training method also illustrates that B-SNIP psychosis Biotypes provide an implementable treatment target for BT1 that is not derivable from any other existing approach to diagnosis of persons with an idiopathic psychosis. This outcome also illustrates that B- SNIP psychosis Biotypes improve standard-of-care for individual idiopathic psychosis patients.

FIG. 14 illustrates the external validation (construct validity) of clozapine treatment implications for B-SNIP psychosis Biotypes. Level of performance in relation to healthy persons is shown for psychosis Biotypes (y-axis) across biomarker targets (x-axis) as a function of on or off clozapine. The bar charts illustrate that B-SNIP psychosis Biotypes provide implementable clozapine treatment targets for BT1 (IEA) or BT3 (SNR or signal-to-noise and BACS or general cognition) that are not derivable from any other existing approach to diagnosis of persons with an idiopathic psychosis. They also show that not using B-SNIP psychosis Biotypes yields suboptimal care for individual idiopathic patients.

FIG. 15 illustrates the paired stimuli task signals used for Biotypes creation.

FIG. 16 illustrates the standard stimuli signals from the oddball task used for Biotypes creation.

FIG. 17 illustrates the frontal cortex target stimuli signals from the oddball task used for Biotypes creation.

FIG. 18 illustrates the parietal cortex target stimuli signals from the oddball task used for Biotypes creation.

FIG. 19 illustrates the PC A solution for the paired stimuli task.

FIG. 20 illustrates the first PCA components for the standard stimuli, frontal response to target stimuli, and parietal response to target stimuli during the oddball task.

FIG. 21 illustrates the second PCA components for the standard stimuli, frontal response to target stimuli, and parietal response to target stimuli during the oddball task.

FIG. 22 illustrates the third PCA components for the standard stimuli, frontal response to target stimuli, and parietal response to target stimuli during the oddball task.

FIG. 23 illustrates an exemplary computing device.

FIG. 24 illustrates the steps involved in implementing aspects of the systems and/or methods disclosed herein. Details of the flow chart are described in the text.

Other features of the present embodiments will be apparent from the Detailed Description that follows. DETAILED DESCRIPTION OF THE INVENTION

In some aspects, the current disclosure provides improved methods for diagnosis and/or treatment of one or more serious psychiatric conditions.

In some aspects, the current disclosure provides improved methods for diagnosis and/or treatment of psychosis.

In some aspects, the current disclosure provides improved methods for diagnosis and/or treatment of psychosis, by utilizing bio-factors.

In some aspects, the current disclosure provides improved methods for diagnosis and/or treatment of psychosis, by utilizing bio-factors and other diagnostic tests (e.g. structural MRI) that are selected agnostically with regard to a subject’s past Diagnostic and Statistical Manual (DSM) diagnosis.

I. Definitions

“Bio-factor” refers to a neurobiological variable with numerical values associated with cognitive and/or neurological responses of a subject. The neurobiological variable can be identified from a larger context of neurobiological variables through a dimension-reduction analysis, such as principal component analysis.

“Neurobiological,” as relates to diagnosis, refers to diagnosis that uses cognitive and/or neurological responses of a subject.

“Operably linked” refers to the connection of at least two components in an MRI or other neurobiological measurement system via technology including, but not limited to, integrated circuits, electrical cables, ethernet, internet, intranet, Bluetooth, near field communication, WiFi, or a combination thereof.

The term “real-time” refers to data transmission to a user interface of a computer- implemented method, system, tool, or device within 1, 2, 3, 4, 5, 10, 15, 20, or no more than 30 minutes after the computer-implemented method, system/tool/device receives input data. The transmitted data can be a neurobiological diagnosis based, in part, on processing input data.

II. Systems and methods for diagnosing psychosis

In the following detailed description of the preferred embodiments, reference is made to the accompanying drawings, which form a part hereof, and within which are shown by way of illustration specific embodiments by which the disclosure may be practiced. It is to be understood that other embodiments may be utilized, and structural changes may be made without departing from the scope of the disclosure. Electrical, mechanical, logical, and structural changes may be made to the embodiments without departing from the spirit and scope of the present teachings. The following detailed description is therefore not to be taken in a limiting sense, and the scope of the present disclosure is defined by the appended claims and their equivalents.

The present disclosure relates to systems and methods for diagnosing serious psychiatric conditions, and the implementation of that diagnosis for selection of treatments for individual patients. In some aspects, the psychiatric condition is a schizophrenia spectrum and psychotic disorder, non-limiting examples of which include idiopathic psychosis, primary psychosis, secondary psychosis, paranoid psychosis, schizotypal psychosis, schizophreniform disorder, brief psychotic disorder, delusional disorder, major depressive disorder, childhood-onset schizophrenia, post-traumatic stress disorder (PTSD), acute stress disorder, functional neurological (conversion) disorder. In some aspects, the present disclosure relates to systems and methods for diagnosing serious psychiatric conditions, and the implementation of that diagnosis for selection of treatments for individual patients with psychosis. In some aspects, the psychosis is an idiopathic psychosis. The main differentials of a subject that qualifies for an idiopathic psychosis include schizophrenia, schizoaffective disorder, or bipolar disorder.

In psychosis, knowledge of unique physiology and pathology will improve diagnosis and promote targeting the most effective treatments to the needs of individual patients. For DSM psychosis diagnoses, schizophrenia, schizoaffective disorder, and bipolar disorder with psychosis, the most prominent of the idiopathic psychoses, there is substantial neurobiological heterogeneity within and overlap between those subgroups. Treatments, therefore, cannot be targeted to address a patient’s specific physiological deviations. The Bipolar-Schizophrenia Network for Intermediate Phenotypes (B-SNIP) disclosed herein improves on this state-of-affairs and provides an approach for enhancing the standard of care. The technology disclosed herein uses neurobiological features characteristic of B-SNIP psychosis Biotypes that yield specific treatment targets for patients with an idiopathic psychosis.

To achieve these goals, B-SNIP used three modifications to the traditional and typical approach within psychosis clinical and neuroscience research. First, collect large “trans-diagnostic” samples across diagnoses (schizophrenia, schizoaffective disorder, bipolar disorder) to capture clinical and neurobiological heterogeneity. Large samples are also necessary to support the statistical methods, but they are not a sufficient condition for developing a successful diagnostic device. Second, quantify biological and clinical features at multiple levels of analysis with an emphasis on capturing cognitive and physiological features of psychosis because those levels of analysis have the best-established relationships to psychosis deviations. Cognitive measures alone are insufficient for developing the device. Physiological measures alone are also insufficient for developing the device. The joint use of both cognitive and physiological features improves the likelihood of successful development of the diagnostic algorithm and derivation of B-SNIP psychosis Biotypes. Third, integrate over biomarkers that index a single construct (e.g., cognition, behavioral inhibition, auditory sensory registration) in scenarios where no single measure adequately captures any underlying brain function.

Even using large samples, multiple and multi-level biomarkers, and considering biomarkers both individually and as integrated statistical constructs (what B-SNIP calls bio-factors), B-SNIP found no apparent mapping of neurobiological features to DSM schizophrenia, schizoaffective disorder, or bipolar disorder with psychosis, or distinctions between those diagnoses that could be clinically useful, as shown in FIG. 1. As a result, the disclosed systems modified the typical approach to psychosis stratification by creating neurobiologically similar subgroups within the larger trans-diagnostic psychosis sample independent of DSM diagnosis (FIG. 1). FIG 2 shows that B-SNIP psychosis Biotypes and DSM diagnoses are uniquely different approaches to psychosis diagnosis.

This new multistage approach (i) shows replication of all steps in the biomarker and biofactor quantification process (see FIG. 3 and FIG. 4), (ii) replicates what is referred to herein as B- SNIP psychosis Biotypes across two samples, (iii) cross-validates B-SNIP psychosis Biotypes between two samples, and (iv) constructs validated Biotypes’ defining physiological features and illustrates their treatment implications. Based on data from thousands of individuals (this example utilized 3507 people), this application illustrates unique procedures and the probable clinical implementations of stratifying idiopathic psychosis cases into B-SNIP psychosis Biotypes that will enhance standard-of-care.

A full B-SNIP-type laboratory evaluation is impractical for many clinical settings. Previous psychosis Biotypes algorithms combined information from multiple laboratory tests (e.g., multiple EEG paradigms estimated a single defining feature of Biotypes such as ERP magnitude). To develop an efficient diagnostic procedure, each assessment must be separately implementable, quantifiable, and uniquely useful. The innovative work described herein accomplishes that goal for diagnosing B-SNIP psychosis Biotypes, which also clearly identifies specific and implementable treatment targets not previously derivable.

B-SNIP used to screen biomarkers for differential diagnostic usefulness by requiring statistical differences between DSM psychosis and healthy groups because there was no other generally accepted approach. That strategy missed informative and clinically useful biomarkers. In the innovative work described herein, B-SNIP removed that requirement, so the biomarker selection process is agnostic to clinical diagnoses of psychosis or any specific psychosis syndrome. Thus, B- SNIP expanded the range and disclosure of clinically useful physiological assessments. A drawback of numerical taxonomy is that it yields solutions regardless of whether subgroups are present and whether the outcomes are consistent. B-SNIP estimated the number of subgroups using the gap statistic and 23 other estimators of cluster number. In addition, for the best estimate number of clusters, B-SNIP evaluated the consistency of assigning a subject to their modal group as a function of sample size used to derive the clustering solution. These analyses illustrate the robustness of this disclosure. Only B-SNIP amassed the number of cases required and discovered that multiple laboratory tests assessing different aspects of psychosis neurobiology can be used to construct a consistent biomarker-based diagnostic system. These analyses illustrate the power and uniqueness of the B-SNIP approach.

Most psychosis cases in biomarker studies are medicated. Additionally, most have been chronically ill and chronically medicated. These factors create uncertainty about whether biomarker differences between groups are related to trait illness, medications, or other effects of living with and adapting to a chronic condition. One way to address such concerns is to investigate correlations between biomarker values and medication status. Among the psychosis patients only, those included in the replication studies (see below in methods for participant numbers), of 44 biomarkers by 18 medications associations (792 total), only one (0.1%) showed 3-4%, five (0.6%) showed 2- 3%, and 27 (3.4%) showed 1-2% of uniquely shared variance. All other associations (95.9%) accounted for less than 1 % of uniquely shared variance. What this means is that biomarker score variances that differentiate psychosis groups are not accounted for by the medications the psychosis patients are taking.

Another way to address such concerns is to point out that all psychosis Biotypes have patients on all medications, yet the biomarker patterns across psychosis Biotypes are remarkably different. This also illustrates that neurobiologically imprecise DSM diagnoses cause nontargeted application of unselected treatments for persons with idiopathic psychosis. This means that clinicians using DSM diagnosis are unable to effectively target a drug treatment to the underlying neurobiological deviations of an individual patient. B-SNIP psychosis Biotypes offers a unique and implementable solution to this problem.

A final way to address medication concerns is to study the clinically non-psychotic biological relatives of individuals with a psychosis Biotype. Medication and chronic condition effects have less explanatory power if the non-psychotic first-degree relatives show the same patterns of biomarker deviations as their ill relatives. In this application, we show the scores across bio-factors in our large sample of untreated first-degree relatives (FIG. 7).

It is contemplated that the systems and/or methods disclosed herein can be applied to other serious psychiatric conditions in general, and not only (idiopathic) psychosis. Method of Analysis

In the current B-SNIP database, there are 1907 psychosis cases, 705 nonpsychotic first- degree biological relatives of those cases, and 895 healthy persons recruited from the community. This is an increase of 902 participants over any previous B-SNIP reports on Biotypes. All laboratory measures for all participants, both old and new, were re-assessed and re-quantified using updated and innovative analytical procedures as described herein.

Cases were drawn from academic and community mental health centers, small towns with large universities, large cities, inner cities, rural regions, affluent and less affluent areas. B-SNIP recruited a research sample, not an epidemiological sample; nonetheless, the large study numbers and broad geographical recruitment foster generalizability of the outcomes across the range of early onset through midcourse to chronic idiopathic psychosis. Thus, this innovative work has broad applicability to multiple types of persons with an idiopathic psychosis. Tables 1-3 below illustrate the findings of such a study as broken down by Biotype, DSM diagnosis, and biological relatives. Table 1 shows the characteristics of the healthy people and patients by Biotype. These are the characteristics of the groups after they were created using unsupervised machine learning based on their neurobiological features. GAF is “global assessment of functioning” and captures general level of societal and personal functioning with higher scores being better. SES is socio-economic status base on the Hollingshead two-factor scale, with lower scores meaning higher SES. Table 2 shows the same information by DSM psychosis diagnosis. Table 3 shows the same information for the biological relatives by the Biotype of the patient to who those relatives are related, and relatives who are included in below analyses.

Table 1 Demographic characteristics by Biotype

Table 2 Demographic characteristics by DSM Diagnosis Table 3 Demographic characteristics of the biological relatives

Clinical evaluations

Clinically stable outpatients were administered the Structured Clinical Interview for DSM diagnosis (DSM-IV-TR). Psychosis cases were limited to schizophrenia (n=783), schizoaffective disorder (n=582), and bipolar I disorder with psychosis (n=542) because these are the idiopathic psychosis diagnoses with the highest prevalence in most settings. Cases were rated on the Birchwood Social Functioning, Montgomery-Asberg Depression Rating, Positive and Negative Syndrome, and Young Mania Rating scales. Healthy persons were free of lifetime psychosis syndromes, recurrent mood syndromes, and a history of psychosis or bipolar disorders in their first- degree relatives.

The extensive clinical information on every individual was reviewed in a best-estimate diagnostic meeting with at least two experienced research clinicians to establish the consensus diagnosis. Cross-site diagnostic conference calls were carried out monthly, chaired by two senior primary investigators, and attended by the 2-4 trained clinical assessors at each site. From study start, there were face-to-face and virtual training sessions for all raters, with a requirement for reliability above 0.85. Table 4 Clinical characteristics — mean (SD) - by Biotype

Table 5 Clinical characteristics — mean (SD) - by DSM diagnosis

As described above, we demonstrated that medication effects do not significantly account for group differences and group formulations based on biomarker features.

Table 6 Medications by Biotype

Table 7 Medications by DSM diagnosis

Biomarker Panel

Participants completed comprehensive laboratory evaluations within a few weeks of their clinical assessments. The individual laboratory paradigms provide extensive data collection and preparatory analysis details. The information in this application creatively and uniquely extends any information derivable from the individual use of any of those previously described laboratory measures.

The laboratory measures span behavioral, cognitive, and physiological domains. The disclosed technology obtains information from all these domains, and integrates that information in a new fashion. The behavior and cognition paradigms are (i) the Brief Assessment of Cognition in

Schizophrenia (BACS) to test general cognitive performance, (ii) pro- and (iii) anti-saccades (saccades) to assess speed of visual orienting, goal maintenance, and inhibitory control under perceptual conflict, and (iv) a stop signal task (SST) to assess adequacy of adapting speeded motor responses to situations requiring inhibitory control.

There are also three assessments of brain physiology as measured with dense-array electroencephalography (EEG). Event-related brain potentials (ERP) were measured with (v) auditory paired stimuli and (vi) auditory oddball paradigms to assess preparation for and recovery from sensory activations, neural responses to stimulus salience and relevance, context updating in working memory, and nonspecific (or intrinsic) brain activity during performance (i.e., brain activity not time-locked to stimulus processing). The 9-10 second inter-pair interval of the paired stimuli paradigm was also included as a direct measure of (vii) intrinsic EEG activity, or IEA (i.e., background brain activity not associated with ongoing stimulus processing requirements), one of B- SNIP’s unique and most informative and differentiating biomarkers. IEA measured from the living, awake brain has never been implemented for Biotypes, or any other neurobiological diagnosis.

Data Reduction and Creation of Bio-Factors

Within each laboratory measurement domain (BACS, saccades, SST, paired stimuli ERP, oddball ERP, IEA/EEG), principal component analysis (PCA; Covariance Matrix, Promax Rotation, Kaiser Normalization, Kappa=3) reduced multiple variables within that domain to an efficient and smaller variable set. This was done for two main reasons. First, for estimating the true value on any construct, multiple independent measures are better than any single variable. For example, neural response to stimulus salience is better estimated by many ERP measures than by a single voltage from a single sensor at one time point. Second, reducing the redundancy of measurements increases the accuracy of numerical taxonomy.

All psychosis and healthy participants were included in PCAs using standardized variables. Age and sex-adjusted biomarker data were used if such effects were statistically significant. This approach produced variables integrated over multiple biomarker measurements, which were the units of analysis for numerical taxonomy. B-SNIP calls these PCA variates “bio-factors” since they integrate multiple facets of neuro-cognition and physiological responses and labelled them based on their most characteristic biomarker associations. These procedures proved to be stable and replicated with high accuracy in two independent samples, each of which contained >700 psychosis and >200 healthy participants (see FIG. 3 and FIG. 4). Nonpsychotic first-degree relatives’ biofactor scores were created by applying the PCA coefficients obtained from psychosis and healthy persons.

BACS. The BACS subtests, covering verbal abilities, processing speed, reasoning, problem solving, and working memory, were scored according to standard procedures. PCA of the BACS subtests identified one component (bio-factor). Saccades. Participants completed three pro-saccade (gap, synchronous, and overlap) and one overlap anti-saccade condition. Trials were scored for (i) direction (to evaluate correct or error response) and (ii) onset latency. Pro-saccade latencies, anti-saccade latencies, and proportion of correct anti-saccades were included in the PCA, which identified two bio-factors called “latency” and “anti-saccade.”

Stop Signal task. A baseline task of go-only trials (these trials have no inhibition requirement but serve as a baseline for understanding performance when inhibition may be required) with a visual stimulus presented pseudo-randomly to the left or right of central fixation, assessed baseline reaction time. For stop-signal trials, a go cue appeared to the left or right. On 40% of trials, a stop signal was presented at central fixation. Participants were instructed to respond quickly and accurately to the go cue unless they encountered the stop signal. Strategic slowing (difference between response latencies on baseline go trials and go trials during stop signal performance) and proportion of stop signal errors were included in the PCA, which identified one SST bio-factor.

Auditory ERP tasks. For the paired-stimuli task, participants passively listened through headphones to at least 120 broadband auditory click pairs with 500 msec inter-click interval occurring every 9.5 sec on average (9-10 sec inter-pair interval). For the oddball task, participants listened through headphones to 567 standard (1000 Hz) and 100 target (1500 Hz) tones presented in pseudorandom order (1300 msec inter-trial interval) and pressed a button when a target was detected (to maintain vigilance).

Data from trials free of artifacts (± 75 mV) were averaged to create 64-sensor ERPs. In addition to analyzing the grand-averaged ERP in the time domain, a frequency-wise PCA of evoked power empirically defined low, beta, and gamma frequency bands. The combination of temporal and frequency information over all sensors and time points maximizes the use of spatial, temporal, and oscillatory information. A spatial PCA on the grand-averaged ERP and each frequency band yielded four waveforms (“virtual sensors”). These virtual sensors were analyzed instead of separate sensors, efficiently summarizing the spatial distributions, minimizing the number of statistical comparisons, and maximizing the signal/noise ratio of the EEG/ERP data. For the paired-stimuli task, the PCA identified three paired-stimuli bio-factors. For the oddball task, the PCA identified three oddball bio-factors.

Intrinsic EEG Activity (IEA). Data derived from the 9-10 sec inter-pair interval of the paired-stimuli task. No stimuli were presented during this period. EEG data were pre-processed following methods described above. Data were transformed into the frequency domain, with frequency bands empirically determined using PC A, resulting in four primary bands: delta/theta, alpha, beta, and gamma. The PCA identified one IEA bio-factor.

Data Analyses

Clustering. The 11 bio-factors were used to construct psychosis Biotypes via k-means clustering. Only psychosis cases were used at this stage since the goal was to determine how to meaningfully parse bio-factor variance within psychosis. This step is used for the identification of B-SNIP psychosis Biotypes. The number of clusters given the data were determined by the gap statistic and the 23 estimators in the NBclust package in R.

Clustering membership consistency. Bootstrapped samples of psychosis cases were selected at sizes of 500 to 1800 cases, in 100 case increments, with 1000 pseudo-replicates for each sample size. Each of the clustering solutions were then compared to the total sample solution using unadjusted and adjusted rand indices for the least and most conservative estimates of cluster membership consistency.

Group differences. The 11 bio-factors were compared between-groups using analysis of variance, with Tukey’s method for post-hoc evaluations (HSD or Tukey-Kramer where appropriate). For statistical significance in omnibus tests, the Holm-Bonferroni procedure was used to maintain the family-wise alpha at .05. For first-degree relatives’ comparisons, degrees of freedom were adjusted based on the number of unique families included in the analysis since some families in the study had multiple members.

Results for Bio-Factors

Bio-factors by Psychosis and Healthy Groups

The means, standard deviations, and effect sizes for the total psychosis versus healthy groups are presented in Table 8. Of the 11 bio-factors, those in the cognition set (BACS, antisaccade, SST) were the best differentiating (F’s > 90.7, p’s < .001, Glass A’s of -1.04, -1.03, and - .45). The ERP response magnitude bio-factors also significantly differentiated groups (F’s > 33.6, p’s < .001 ), but with considerably less separation (Glass A’s of -0.35 and -0.25); the same was true of the intrinsic activity bio-factors (F’s > 12.3, p’s < .001, Glass A’s of 0.19, 0.26, and 0.16). The bio-factors in the stimulus salience set were more modestly differentiating, with the latency biofactor failing to separate psychosis and healthy groups (F < 1, p > .770, Glass A = -.01). The other two stimulus salience bio-factors, P300 complex and paired-stimuli S2, showed significant effects (F’s of 6.2 and 13.8, p’s of .013 and c.001) of small group differentiations (Glass A’s of 0.09 and - 0.16). Table 8 Standard Score Mean (SD) of Standardized Bio-factors

Number of Clusters

These analyses addressed the best estimate of the number of clusters across the 11 biofactors. The gap statistic outcome is illustrated in FIG. 5, and results from the 23 cluster number estimators of the NBclust package are presented in Table 9. Both the gap statistic and NBclust majority rule indicate the most parsimonious solution is three clusters given the bio-factor data. Therefore, k-means was obtained requesting a three-cluster solution; the algorithm achieved cluster stability within 43 iterations. The k-means outcome resulted in observations per cluster (psychosis Biotypes) as described in Table 1 (BT1 n = 630, BT2 n = 631, BT3 n = 646).

Table 9 NBclust Outcomes (indicating 3 clusters best accounts for bio-factor data)

Consistency of Cluster Membership Assignment

FIG. 6 shows the consistency of k-means membership for an individual patient using a subsampling approach (1000 iterations at each subsample size from 500 to 1800 probands). The illustration of application of this algorithm to individual cases is new in psychiatry. The figure shows two consistency estimates. The first rand index (upper line) shows consistency with the full model solution without adjusting for chance assignment. This outcome shows remarkable consistency of > 95% agreement for samples of greater than 1500 observations, excellent agreement of > 90% for sample sizes of greater than 900, and still good agreement > 82% for sample sizes of at least 500. The second rand index (lower line) shows consistency adjusting for the probability of a case being assigned by chance to one of the three groups. This most conservative metric shows remarkable agreement of > 95% for samples of greater than 1600, excellent agreement of > 90% for samples of greater than 1500, and good agreement of > 80% for samples of greater than 1000. This outcome illustrates that a combination of B-SNIP laboratory tests, data collection, quantification, and statistical analysis procedures, combined with sufficiently large samples sizes, are necessary to obtain a stable and clinically implementable biomarker-based diagnostic algorithm for idiopathic psychosis that is applicable to individual patients.

Bio-Factors by B-SNIP Psychosis Biotypes

FIG. 7 shows bio-factors plotted by group membership for the psychosis patients and for the clinically healthy relatives of those patients. All bio-factors differentiate psychosis Biotypes (Holm- Bonferroni adjusted significance, F’s = 20.21 to 703.81, p’s < .001). This is not surprising because numerical taxonomy used these bio-factors to create maximally homogeneous and distinct groups. When adding the healthy group to the models, all comparisons remained significant and of similarly large magnitude (Holm-Bonferroni adjusted significance, F’s = 14.96 to 442.78, p’s < .001). The bio-factor patterns for psychosis groups in comparison to healthy performance are robust because of the new and innovative analytical approaches and methods that are described above. BT1 patients have low cognition and low neural response magnitudes, BT2 patients have low cognition, poor inhibition, and accentuated intrinsic brain activity, and BT3 patients are reasonably normal across most bio-factors but still show cognitive performance lower than expected based on the same scores for their relatives and are mildly deviant on measures of stimulus salience. FIG. 8 illustrates how Biotypes are distributed in multi-dimensional space, and that space is defined by implementable treatment targets, but DSM diagnoses have a modest and largely overlapping uni-dimensional distribution.

The Biotypes are distinguished within idiopathic psychosis by unique patterns across the 1 1 bio-factors. They are also distinguished from healthy persons on these same variables. To ease visualization of unique group bio-factor patterns, canonical discriminant analysis (CDA) was used with the criterion being group membership (BT1, BT2, BT3, healthy (HC)) and the predictors being the 11 bio-factors. This is a simplification of group differentiations in the 11 -variable space of the bio-factors. The CDA yielded three significant variates (chi-squares > 110.7, p’s <.001 ; canonical correlations of 0.69, 0.64, and 0.26, p’s <.001; see FIG. 9 and Table 10).

Table 10 CDA results

In FIG. 9, CDA Variate 1, called “neural dysregulation,” has the most significant associations with anti-saccades (r = .60), BACS (r = .56), and ongoing EEG high frequency activities (oddball r = .48, paired-stimuli r = .47). Lower scores indicate a triumvirate of worse cognitive performance and behavioral inhibition combined with accentuated background brain activity during stimulus processing. Neural dysregulation best distinguishes BT2 from the other groups, with post-hoc tests showing a pattern of BT2 < BT1 < (BT3 = HC). This new pattern, identified by the inventors, illustrates distinctive neurobiological deviations within B-SNIP psychosis Biotype-2 (BT2). CDA Variate 2, called “neural vigor,” best separates BT1 from the other groups and is associated with a reduced ERP responses (paired-stimuli r = .69, oddball r = .72) and reduced intrinsic EEG activity (IEA r = .70). Lower scores indicate generally reduced neural activity. Post-hoc comparisons show a pattern of BT1 < (HC = BT2) < (BT2 = BT3). This new pattern, identified by the inventors, illustrates that B-SNIP captured a separate and distinctive pattern of neurobiological deviations within a different subgroup (BT1) of idiopathic psychosis. CDA Variate 3, called “stimulus salience,” best separated BT3 from the other groups, and is associated with frontal P3 complex responses (r = .61), response to the second stimulus of the paired-stimuli paradigm (r = -.57), and prosaccade latencies (r = -.34). Lower scores indicate generally greater sensitivity to stimulus salience. Post-hoc comparisons show a pattern of BT3 < (BT2 = BT1) < HC. This new pattern, identified by the inventors, illustrates a different distinctive pattern within idiopathic psychosis. When assessing biomarker features using DSM diagnosis, it is often assumed that differentiations in neural dysregulation, neural vigor, and stimulus salience characterize the same patients. B-SNIP’s new psychosis Biotyping scheme illustrates that this assumption is false; different clusters of patients have different neurobiological deviations and unique treatment targets. Without B-SNIP psychosis Biotypes, these unique treatment targets are not implementable.

Construct Validation of B-SNIP Psychosis Biotypes

First-degree relatives by psychosis Biotype proband type. FIG. 7 shows bio-factors plotted for the first-degree relatives by the proband to whom they are related. Table 3 shows the demographic characteristics of the first-degree relatives by Biotype of their proband. The BACS, anti-saccade, paired stimuli and oddball ERPs, and IEA bio-factors differentiated the relative groups (Holm-Bonferroni adjusted significance, F’s > 4.1, p’s <007). These are also the most important bio-factors for diagnosing B-SNIP psychosis Biotypes in persons with an idiopathic psychosis. The relatives’ patterns of deviation on those bio-factors are like the patterns among their probands. This outcome illustrates that B-SNIP’s biomarker panel, implemented by the inventors, identifies unique constitutional deviations as treatment targets for individual patients.

The BACS [(BT1 = BT2) < HC < BT3) and anti-saccade bio-factors [(BT1=BT2) < (HC = BT3) showed similar patterns of deviations. BT3 relatives had the best general cognitive performance, even in comparison to healthy persons. This illustrates that BT3 is a unique and not previously diagnosable group within idiopathic psychosis. They will require unique treatments that can only be identified and properly implemented via B-SNIP psychosis Biotype diagnosis.

The patterns for the ERP amplitude measures recapitulate the probands’ patterns with BT1 relatives having lower ERP amplitudes than the other three groups combined. Likewise, the IEA bio-factor shows a pattern like the ERP amplitude measures, with BT1 relatives being lower than the other three groups. These outcomes also illustrate that specific neurobiological deviations are present among the clinically healthy relatives of psychosis cases, suggesting specific constitutional predispositions combined with nonfamilial features that distinguish psychosis Biotypes. This knowledge is important for implementing searches for etiological understanding and for treatment targeting. This information is only possible via implementing this innovative work. Validation of psychosis Biotype-defining electrophysiology. Important differentiating features of BT1 and BT2 are low neural response to salient stimuli (low neural vigor of BT1) and excessive intrinsic and background brain activity (neural dysregulation of BT2). Neurophysiological theories of psychosis propose nonspecific (or intrinsic) activity is an important translational biomarker, but intrinsic activity fails to consistently differentiate conventional clinical psychosis diagnoses, so when stratifying by DSM diagnoses intrinsic activity is not a clinically implementable target. Both BT1 and BT2 deviations result in poor signal-to-noise (BT1 because of a small numerator and BT2 because of a large denominator). In a subset of participants, B-SNIP added an auditory steady-state paradigm to directly probe these features using a laboratory task that is not part of Biotypes’ creation.

In steady-state paradigms, stimuli are modulated at known frequencies (e.g., 40-Hz, an event every 25-ms) for an extended time (e.g., 1500-ms). Neurons tuned to those oscillations resonate at the stimulation frequency. There is a known input (40-Hz signal) and an expected output (40-Hz oscillations in the EEG). This one paradigm allows for evaluation of neural dysregulation and neural vigor simultaneously. If the neurophysiological model that supports specific diagnosis and treatment targeting is correct, there should be a double dissociation of BT1 and BT2 defining physiological characteristics.

The upper part of FIG. 10 shows the ERPs to stimuli onset in the steady state paradigm by group. Only BT1 have reduced N100 ERP magnitude, part of BTl ’s unique defining feature of low neural vigor. BT2 have normal magnitude N 100 ERP, but accentuated P200 ERP, which coincides with the beginning of the auditory steady state response (seen as “divots” in the ERP). Following the P200, the lower part of FIG. 10 shows power at the driving frequencies during ongoing steadystate stimulation. BT2 are the only group that is accentuated on this characteristic of exaggerated neural responding, one of the defining features of neural dysregulation. These physiology differences yield specific etiological and treatment targets that are not available with any other psychosis classification system.

Structural brain imaging validation of psychosis Biotypes. Biotypes are defined by cognition and electrophysiology, but they capture unique deviations across levels of analysis, including brain morphometry. It is suspected there is an association between the hippocampal complex and a subset of psychosis cases. How to capture that subset of psychosis cases has been uncertain. B-SNIP psychosis Biotypes resolve that uncertainty. B-SNIP assessed hippocampal and amygdala volume and shape deformities in 475 psychosis cases and 315 healthy subjects. Volume and shape outcomes were highly similar; FIG. 11 shows the outcomes for shape (DSM at top of FIG. 11, and Biotypes at bottom of FIG. 11). To summarize the results: (i) DSM groups did not significantly differ on hippocampal and amygdala volume or shape; (ii) BT2, BT3, and healthy groups are indistinguishable on hippocampal volume and shape; (hi) BT1 significantly differ from BT2, BT3, and healthy groups (average effect size = .42). These outcomes illustrate three important points: (i) modest deviations are distributed across DSM groups; (ii) sorting idiopathic psychosis patients by B-SNIP Biotypes reveals that hippocampal complex deviations are largely restricted to BT1; (hi) defining cases by neurobiological homology supports organization of neuropathology, and therefore treatment targeting, at multiple levels of analysis.

Structural brain imaging diagnosis of psychosis Biotypes. A critical question is if biological measures commonly used in clinical practice, like structural MRI, can facilitate the accurate diagnosis of persons with an idiopathic psychosis. If so, diagnostic precision, treatment targeting, and standard-of-care will improve. Prior research tried using structural MRI measures to discriminate psychosis groups, mainly schizophrenia or bipolar disorder, from healthy persons. The typical outcome is that gray matter features discriminate schizophrenia versus healthy persons modestly accurately. The ability to distinguish bipolar disorder from healthy persons is less certain. Pathology versus healthy groups discrimination is important, but a more pressing interest for treatment targeting is distinguishing between different subtypes of psychosis. Few studies have attempted to discriminate between schizophrenia and bipolar disorder, but those that have had at best modest success.

There is growing interest in using machine learning to disentangle the heterogeneity of serious psychiatric conditions. In this innovative work, B-SNIP illustrates that a supervised machine learning approach applied to voxel-by-voxel brain gray matter densities successfully classifies B- SNIP psychosis Biotype- 1 (BT1). T1 -weighted structural MR images were acquired from 3T MRI. The analysis pipeline incorporated the D ARTEL high-dimensional nonlinear inter-subject registration tool. Gray matter densities were extracted from the segmented and modulated gray matter images using a gray matter mask. A total of 371 ,243 gray matter density features were used in the machine learning analyses.

Machine learning analyses extracted patterns of gray matter densities that reliably differentiate B-SNIP psychosis Biotype-1 (BT1) from other groups. The inventors used a repeated train-then-test split approach with 1000 iterations. For each iteration, a randomly selected subset of the data trained the classification model, and the held-out data tested the model. All models were based on L2-normed logistic regression (penalty=l) using the liblinear package as implemented in the Princeton MVPA toolbox.

Three binary classification models were trained to discriminate one of the three Biotypes versus healthy persons. The trained models were applied to every case in the held-out test groups. Classifier accuracy was computed using a balanced accuracy metric, the unweighted average of each group’s classification accuracy, or the average of the sensitivity and specific of the classifier. A model’s classification accuracy was considered statistically significant if the 99.17% confidence interval for overall classifier accuracy across the 1,000 repeated train-test iterations did not encompass the chance value of 50%. We used 99.17% as a conservative approach to control for multiple comparisons in the overall classification accuracies.

A model for each Biotype was also tested on the other two Biotypes, allowing assessment of the specificity of each model. The idea behind this approach is that if a given model classifies the designated Biotype above chance but fails to do so for the other two Biotypes, then the model is likely identifying gray matter features specific to a particular Biotype. If a model classifies the other Biotypes at rates exceeded chance, then the model is identifying non-specific gray matter features for psychosis generally. The above methods were also employed to examine classification of the three DSM psychosis diagnoses.

The results for the three Biotypes classification models are shown in FIG. 12. For BT1, overall classification accuracy was significantly above chance. Classification accuracies were also significantly above chance for healthy persons. Importantly, the model did not classify either BT2 or BT3 cases as belonging to the BT1 group at rates above chance. This pattern illustrates specificity of this gray matter density diagnostic algorithm to BT1.

Alternatively, classification accuracy of the BT2 model was driven by gray matter density features common to both BT1 and BT2, not features specific to BT2. Lastly, overall classification accuracy for the BT3 versus healthy model was significantly above chance. However, neither the separate classification accuracies for BT3 nor for healthy persons exceeded chance. Moreover, the BT3 model did not show specificity as BT1 cases were misclassified as belonging to the BT3 group at rates greater than chance. BT2 cases, however, were not misclassified as BT3 above chance. These outcomes illustrate that classification performance of the BT3 model was driven by gray matter density features common to all Biotypes and healthy persons.

This gray matter density-based algorithm has specificity for diagnosing BT1. DSM diagnoses of schizophrenia and bipolar disorder were not classified above chance using the same data and approach. This is a new application of a machine learning algorithm that both validates and facilitates diagnosis of B-SNIP psychosis Biotypes. It also shows that MRI differential diagnostic value is not observed for DSM, the most common approach to diagnosis of idiopathic psychosis. Notably, the classifier algorithm was trained on whole-brain gray matter density features that were not used to derive Biotypes. Ergo, this gray matter density machine learning algorithm provides an independent diagnostic test for B-SNIP psychosis Biotype- 1 (BT1). This test can be implemented to improve B-SNIP psychosis Biotypes diagnostic accuracy, and to enhance implementation of Biotype-specific treatments.

Sensory training validation of psychosis Biotypes. The physiological differences between B-SNIP psychosis Biotypes offer specific treatment targets not provided by any other currently available approach for diagnosing idiopathic psychosis patients. The only way to determine improved efficacy for treatment selection is to directly compare available approaches.

BT1 and BT2 patients have poor signal-to- noise, the former due to deficient neural responses to salient stimuli and the latter due to accentuated intrinsic or background brain activity. Signal-to-noise measures the difference between a person’ s strength of neural response to a specific stimulus (like an auditory or visual event in the environment) and that person’s background level of ongoing neural activity in their brain. The bigger this difference, the better able a person is to accurately process the stimulus of interest. Both BT1 and BT2 patients have low signal-to-noise and need a treatment to correct this deviation. The means to achieve that end, however, differ by BT group. One approach involves sensory training to specifically enhance ERP magnitudes in BT1 because they need stronger neural response to the stimulus to improve their signal-to-noise. Such approaches have been tried with schizophrenia cases, who are a mix of different B-SNIP psychosis Biotypes. Those studies have shown at best only modest success.

So far, 7 BTls, 10 BT2s, and 8 BT3s have participated in three weeks of sensory training targeting the underlying problem of BT1. FIG. 13 shows the training outcomes for these patients. The x-axis shows eight training days (4 training sessions per day). Behaviorally on signal discrimination, BTls improve on all conditions, BT2 have the worst overall performance, and across all conditions they deteriorate over time, and BT3 have the best performance overall, but show no significant improvement over training. These outcomes illustrate that B-SNIP psychosis Biotypes yield implementable and meaningful treatment targets that are not derivable from any other available approach to idiopathic psychosis diagnosis.

The B-SNIP inventors show that only BT1 benefit from a sensory training treatment aimed at enhancing ERP magnitudes because they are the only group with that specific deviation. BT2 have neural dysregulation in association with stimulus processing, so participation in the same paradigm that improves BT1 worsens BT2 because processing the stimuli degrades BT2 signal-to- noise ratios even further. This is an iatrogenic effect on BT2 of a commonly employed sensory training procedure, but this effect is only identifiable by implementing B-SNIP psychosis Biotypes. This same differential treatment efficacy is not evident when using DSM psychosis diagnoses.

Selecting patients for clozapine treatment using psychosis Biotypes. Clozapine is the most effective antipsychotic drug, but it is underused because of the possibility of troubling side effects and sometimes complex administration. If there was a means to identify responsive cases in advance, clozapine could be used more decisively. Clozapine’s unique antipsychotic action remains unexplained; however, unlike other antipsychotics, clozapine increases alpha and theta electroencephalography power in a resting state and modifies signal-to-noise ratios in some patients. How those effects relate to psychosis treatment is unclear using DSM diagnosis but is clarified by implementing B-SNIP psychosis Biotypes.

B-SNIP has cases off and on clozapine across psychosis Biotypes. The patterns of relationships between clozapine status and relevant B-SNIP bio-factors and biomarkers are displayed in FIG. 14. The largest number of patients are not taking clozapine (n= 1763, roughly evenly spread across the three Biotypes). A smaller number of patients are taking clozapine (n=140, roughly evenly spread across the three Biotypes).

There are five main conclusions from the bar charts in FIG. 14: (i) Being on clozapine is associated with increased intrinsic EEG activity (IEA) regardless of psychosis group. Nevertheless, being on clozapine is associated with a closer to normal level of IEA among BT1 patients but more deviant IEA among BT2 and BT3 patients. If adjusting level of IEA is related to treatment success, BT 1 patients are the ones who should be targeted, (ii) ERP magnitudes are significantly larger only among BT3 patients on clozapine versus not on clozapine, (iii) Level of induced EEG activity, which is brain activity during stimulus processing that is not part of the ERP response, is modestly lower among all patients on clozapine versus not on clozapine. Level of induced EEG activity is closer to normal among BT3 patients on clozapine versus not on clozapine, (iv) Level of signal-to- noise (ERP magnitude versus induced EEG activity) is modestly larger in every psychosis group on clozapine, but only significantly larger among BT3 patients on clozapine versus not on clozapine. If adjusting signal-to-noise is related to treatment success, BT3 patients are the ones who should be targeted. BT3 is also the only group in the same range as healthy persons on the signal-to-noise laboratory measure, (v) Both BT1 and BT2 patients on clozapine have worse general cognitive performance when on clozapine versus not on clozapine. This could be because clinicians treat the most cognitively compromised patients with clozapine. In comparison, however, this simple interpretation is not consistent with the fact that BT3 patients on clozapine have better general cognitive performance (in the healthy range) than those not taking clozapine. Ergo, B-SNIP psychosis Biotypes yield specific treatment targets for clozapine, the most effective antipsychotic medication. There is no such predictive ability provided by any other approach to psychosis diagnosis.

Finally, signal-to-noise is a new and informative biomarker for differentiating BT3 from the other Biotypes. Only the current inventors have devised and implemented this signal-to-noise metric in idiopathic psychosis while showing both its differential diagnostic utility and possible importance for determining clozapine treatment efficacy. Like gray matter density for diagnosis of BT1, signal-to-noise can be used to improve B-SNIP psychosis Biotypes diagnostic accuracy, and to enhance implementation of Biotype- specific treatments.

Additional Treatments

In some aspects, the method disclosed herein may also help determine other suitable treatment options, other than clozapine, based on the diagnosed subtype. Non-limiting examples include any one or more of antipsychotic medications (typical and atypical), mood stabilizers, anxiolytics (e.g., benzodiazepines), antidepressants (e.g., SSRIs), cognitive behavioral therapy for psychosis (cbtp), supportive therapy, insight-oriented therapy, family therapy, social skills training, vocational rehabilitation, case management, hospitalization, electroconvulsive therapy (ect), sleep hygiene, exercise, dietary adjustments, mindfulness, relaxation techniques, or any combinations thereof. Examples of antipsychotic medications include haloperidol, chlorpromazine, fluphenazine, perphenazine, thioridazine, trifluoperazine, loxapine, pimozide, risperidone, olanzapine, quetiapine, aripiprazole, clozapine, ziprasidone, paliperidone, lurasidone, asenapine, brexpiprazole, cariprazine. Non-limiting examples of mood stabilizers include lithium, valproate (Divalproex), carbamazepine, lamotrigine, oxcarbazepine, gabapentin, topiramate.

Computer Hardware Components

The present systems and methods may include implementation on a system or systems that provide multi-processor, multi-tasking, multi-process, and/or multi-thread computing, as well as implementation on systems that provide only single processor, single thread computing. Multiprocessor computing involves performing computing using more than one processor. Multi-tasking computing involves performing computing using more than one operating system task. A task is an operating system concept that refers to the combination of a program being executed, and bookkeeping information used by the operating system. Whenever a program is executed, the operating system creates a new task for it. The task is like an envelope for the program in that it identifies the program with a task number and attaches other bookkeeping information to it. Many operating systems, including Linux, UNIX®, OS/2®, and Windows®, can run many tasks at the same time and are called multitasking operating systems. Multi-tasking is the ability of an operating system to execute more than one executable at the same time. Each executable is running in its own address space, meaning that the executables have no way to share any of their memory. This has advantages, because it is impossible for any program to damage the execution of any of the other programs running on the system. However, the programs have no way to exchange any information except through the operating system (or by reading files stored on the file system). Multi-process computing is like multi-tasking computing, as the terms task and process are often used interchangeably, although some operating systems make a distinction between the two.

The present technology may be a system, a method, and/or a computer program product at any possible technical detail level of integration. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention. The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. In some aspects, the computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device to perform any of the operations discussed herein regarding FIGs. 1-24.

Preferably, in all instances described in this technology, the computer-readable storage medium or computer-readable medium is a non-transitory computer-readable storage medium or a non-transitory computer-readable medium, respectively.

FIG. 23 illustrates a computing device 3700 as it relates to the present disclosure. The computing device 3700 may, for example, perform calculations, execute routines and algorithms, process data, communicate with other devices via a network, and display results. In some aspects, the computing device 3700 may, for example, perform calculations, execute routines and algorithms, process data, communicate with other devices via a network, and display results of any of the operations discussed herein regarding FIGs. 1-24. For example, a computing device 3700 may comprise a processor or CPU 3704, a network adapter 3706 for communication with a network 3708. The network 3708 may connect the computing device 3700 to external data sources such as patient data 3750 or to other computers (not shown in the figure). The computing device may comprise an input/output device 3702. Such an input/output component 3702 may be an input device, an output device, or both and the computing device 3700 may have several such components. Example input devices 3702 include a keyboard, a mouse, a microphone, a touchpad, a joystick, and the like. Example output devices 3702 include a display, a speaker, a haptic feedback device, and the like. The computing device 3700 may further comprise memory 3710 or a computer readable storage medium 3710. In the computer memory 3710 may reside instructions for carrying out the methods and techniques described elsewhere in this disclosure. The computer memory 3710 may also comprise an operating system 3730 for control of the various parts and components of the computing device 3700. The memory 3710 may also store data, for example training data 3712 and testing data 3714. The memory 3710 may also comprise algorithms such as machine learning algorithms 3716, dimension reduction algorithms 3718, decision tree algorithms 3720, clustering algorithms (e.g., k-means), 3722, classifier algorithms 3724, or other algorithms 3726. In some aspects, the memory 3710 may also comprise algorithms such as machine learning algorithms 3716, dimension reduction algorithms 3718, decision tree algorithms 3720, clustering algorithms (e.g., k-means), 3722, classifier algorithms 3724, or other algorithms 3726 to perform any of the operations discussed herein regarding FIGS. 1-24.

Other types of clustering algorithms that can be implemented in the disclosed methods and/or systems include hierarchical clustering; density -based spatial clustering of applications with noise (DBSCAN); ordering points to identify the clustering structure (OPTICS); mean shift; spectral clustering; agglomerative clustering; balanced iterative reducing and clustering using hierarchies (BIRCH); and affinity propagation.

The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a readonly memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.

Computer readable program instructions for carrying out operations of the present innovative work may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, statesetting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user’s computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, to perform aspects of the present disclosure.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions. These computer readable program instructions may be provided to a processor of a special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks, which includes a non-generic and non- conventional arrangement of components for performing a non-generic and non-conventional series of operations, resulting in the improved systems disclosed herein.

These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks. For examples, the disclosed technology can form part of a vendible product, such as downloadable software, which can be purchased as a cloud service and/or as a standalone application.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in FIG. 23 illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks may occur out of the order noted in FIG. 23. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or that carry out combinations of special purpose hardware and computer instructions.

Although specific embodiments of the present disclosure have been described, it will be understood by those of skill in the art that there are other embodiments that are equivalent to the described embodiments. Accordingly, it is to be understood that the innovative work is not to be limited by the specific illustrated embodiments, but only by the scope of the appended claims.

Non-limiting Flow Chart for Implementation of the Innovative Work

FIG. 24 shows a non-limiting method involved in implementing the innovative work as described above. First, it can be determined whether a patient is suitable for a B-SNIP psychosis Biotype evaluation (step 1000; inside gray box). A patient is first referred for laboratory evaluation (step 1002). The patient’s medical and demographic information is collected and reviewed (step 1004), as is done in evaluations conducted prior to any medical diagnosis. From here, the patient can be verified to be suitable for further evaluation criteria. The are many ways a patient is deemed unsuitable for a B-SNIP psychosis Biotype diagnosis (step 1006), including age (less than 18 years of age or greater than 65 years of age), having suffered serious head injury, being a chronic or active user of psychoactive substances that compromise the accuracy of laboratory tests of brain structure and function, or having other conditions that better account for the clinical picture, for instance a neurological disorder such as temporal lobe epilepsy, known genetic deviation (e.g., 22ql 1 deletion syndrome) or autoimmune condition (e.g., anti-NMDA receptor autoimmune encephalopathy). Such rule-outs are verified prior to definitive exclusion from B-SNIP psychosis Biotype laboratory evaluation (step 1008).

When a referred patient successfully passes the above screening, the patient is then evaluated for psychosis (step 1010 in FIG. 24), which is defined as perceptions, thoughts, or actions that do not comport with socially shared experience. Psychosis can be verified using a standard evaluation that identifies the presence of delusions and hallucinations (collectively called reality distortions), thoughts in which speech is difficult or impossible to comprehend (e.g., thought disorder), or unusual behaviors that do not fit the situation (e.g., so-called negative symptoms or catatonia). The patient must meet the clinical psychosis standard to be evaluated for a psychosis Biotype; otherwise, they are excluded from B-SNIP psychosis Biotype evaluation. If the patient meets the psychosis definition, additional clinical evaluations can be conducted if requested (step 1012). Alternatively, a patient can be directly referred for laboratory biomarker collection (step 1100) as described above.

If a laboratory biomarker cannot be obtained from the patient according to standard procedures, the biomarker can be unusable (step 1102), and an additional attempt is made to collect the biomarker (step 1104; return to step 1100). If the examiner deems the biomarker cannot be obtained, then further attempts to collect that biomarker are abandoned (step 1106). Following collection of all obtainable biomarkers, each biomarker is prepared and screened for quality and acceptability (step 1108). If data quality for a biomarker is poor (step 1110), then the biomarker is re-collected (step 1112; return to step 1100), re-prepared and re-screened. If the data evaluator deems a patient’s biomarker collection is unlikely to meet quality and acceptability standards, then further attempts to collect that biomarker are abandoned (step 1106). Following completion of biomarker collection and quality checks, the available biomarker panel is submitted to a separate examiner for final approval (step 1114).

Data of good quality are then processed according to techniques developed for each individual biomarker (step 1200). Those processing techniques include creating scores or grand averages for every subcomponent of a biomarker measure, using the approaches outlined above. These techniques prepare every biomarker measure for application of PCA weights (step 1202), with there being a weight associated with every biomarker. The output of this step is the bio-factor scores. Bio-factor scores are the input to the tuned Biotype algorithm (step 1204). In some instances, the B-SNIP psychosis Biotypes algorithm was constructed using the laboratory measures, bio-factors, and individuals as described above. The three psychosis Biotypes (BT1, BT2, and BT3) are defined by locations in the 11-variable space of the bio-factor scores (as displayed in FIG. 7). There is a centroid for each psychosis Biotype that is defined by the joint locations of the 11 bio-factor scores within a Biotype. To determine an individual patient’s location in this 11 -variable space, that individual’s bio-factors scores are compared to the three Biotype centroids ( e.g., in relation to BT1 centroid-defining bio-factor scores, in relation to BT2 centroiddefining bio-factor scores, in relation to BT3 centroid-defining bio-factor scores). This constitutes application of the tuned Biotypes algorithm (step 1204 of FIG. 24).

The outputs of the tuned Biotypes algorithm are the sums of the squared Euclidean distances between that patient’s bio-factor scores and the centroid locations of each Biotype’s bio-factor scores (as displayed in FIG. 7). An individual patient’s psychosis B-SNIP Biotype diagnosis is the smallest of those summed Euclidean distances (step 1206 in FIG. 24). In this way, it is possible to obtain a B-SNIP psychosis Biotype even in the absence of complete biomarker data.

The Biotypes algorithm can be modified with the addition of a sufficiently large number of new patients or the addition of new biomarker measures (e.g., like the structural MRI algorithm for BT1 as described above and the signal-to-noise ratio measure as described above). In this aspect, processed data with new subjects or new biomarkers from step 1200 in FIG. 24 feeds a new PC A decomposition (step 1208). New components and biomarker weights are derived at this step, with the application of these new components and weights yielding updated bio-factor definitions (step 1210), which then modify the computations of step 1202. The updated bio-factors are then used to recompute (re- tune) the Biotype algorithm using the steps described above (step 1212). The retuned algorithm modifies the Biotypes computations of step 1204 in FIG. 24. The phrases “retune,” “re-tuning,” “re-tuned,” or other equivalent phrases, e.g., “fine-tune,” “fine-tuning,” “finetuned” in the context of computer algorithms refer to the process of training a pre-trained algorithm on a specific data set to improve its performance for a particular task.

Following the generation of a B-SNIP psychosis Biotype diagnosis (step 1206), the patient can be prescribed a specific treatment or treatments that are appropriate for that diagnosis to rectify specific issues (step 1214). Examples of such treatments are provided above. Some of those treatments may be applied by the inventors (e.g., the sensory training intervention for BT1), but most frequently they can be implemented by the referring clinician.

The disclosed systems and methods of use can be further understood through the following enumerated paragraphs or embodiments. 1. A computer- implemented method (CIM) for neurobiological diagnosis of a subject, optionally followed by an individual devising a treatment regiment, the method involving: using one or more computer-implemented algorithms (i) configured to process a first set of bio-factor data from the subject and (ii) configured to classify the subject as having a subtype of psychosis, wherein the one or more computer-implemented algorithms have been trained on a second set of bio-factor data to recognize one or more subtypes of psychosis, wherein the second set of bio-factor data includes bio-factor data agnostic to clinical diagnosis of psychosis of the subject, another subject, or a combination thereof, and/or selecting the second set of bio-factor data does not require statistical differences between Diagnostic and Statistical Manual (DSM) psychosis groups and healthy groups, and wherein the one or more computer-implemented algorithms are operably linked to one or more processors.

2. The CIM of paragraph 1 , wherein selecting the second set of bio-factor data does not require statistical differences between Diagnostic and Statistical Manual (DSM) psychosis groups and healthy groups.

3. The CIM of any of the preceding paragraphs, wherein the psychosis is idiopathic.

4. The CIM of any of the preceding paragraphs, wherein the first set of bio-factor data includes the subject’s cognitive performance data, behavioral performance data, brain signal data, or a combination thereof.

5. The CIM of any of the preceding paragraphs, wherein the first set of bio-factor data includes the subject’s Brief Assessment of Cognition in Schizophrenia (BACS) data, anti-saccade data, paired stimuli data (e.g. , auditory paired stimuli data), oddball event-related brain potentials (ERP) data, intrinsic electroencephalography activity (IEA) data, or a combination thereof.

6. The CIM of any of the preceding paragraphs, wherein the first set of bio-factor data includes the subject’s intrinsic electroencephalography activity (IEA) data, optionally obtained from a living, awake brain.

7. The CIM of any of the preceding paragraphs, wherein classifying the subject as having a subtype of psychosis involves: using a classification algorithm e.g., decision tree, logistic regression, random forest, support vector machines, k-nearest neighbors, naive Bayes, etc.).

8. The CIM of any of the preceding paragraphs, wherein the subtype of psychosis includes a neural dysregulation Biotype (BT2), a neural vigor Biotype (BT1), and a stimulus salience Biotype (BT3). 9. The CIM of any of the preceding paragraphs, further involving: causing a recommendation of one or more treatment regiments based on the subtype of psychosis to be presented at a user interface that preferably includes a digital screen (e.g., a screen of a computing device such as a screen of a smartphone, a laptop, a desktop computer, a watch, a tablet, etc.), an electro-mechanical acoustic system e.g., electronic speakers), or a combination thereof.

10. The CIM of any of the preceding paragraphs, further involving: re-tuning the one or more computer-implemented algorithms on a third set of data, preferably wherein the third set of data includes a third set of bio-factor data.

11. The CIM of any of the preceding paragraphs, further involving: performing a principal component analysis to identify the second set of bio-factor data and/or the third set of bio-factor data prior to training, re-tuning, or a combination thereof.

12. The CIM of any of the preceding paragraphs, wherein the CIM provides neurological diagnosis in real-time.

13. A non-transitory computer-readable medium (CRM) with one or more computerexecutable instructions stored thereon executed by one or more processors, wherein the one or more computer-executable instructions contain one or more computer-implemented algorithms (i) configured to process a first set of bio-factor data from the subject and (ii) configured to classify the subject as having a subtype of psychosis, wherein the algorithm has been trained on a second set of bio-factor data to recognize one or more subtypes of psychosis, wherein the second set of bio-factor data includes bio- factor data agnostic to clinical diagnosis of psychosis of the subject, and wherein the one or more computer-executable instructions are operably linked to the one or more processors.

14. The non-transitory CRM of paragraph 13, wherein the one or more computer- implemented algorithms are capable of being re-tuned using a third set of bio-factor data.

15. The non-transitory CRM of any of the preceding paragraphs, wherein the one or more algorithms contain machine learning algorithms, dimension reduction algorithms, clustering algorithms, classifier algorithms, or a combination thereof.

16. The non-transitory CRM of any of the preceding paragraphs, wherein the one or more computer-implemented algorithms are operably linked to a user interface (e.g., graphical user interface) and configured to transmit neurobiological diagnosis to a user interface for output at the user interface. 17. The non-transitory CRM of paragraph 16, wherein the user interface includes a digital screen (e.g., a screen of a computing device such as a screen of a smartphone, a laptop, a desktop computer, a watch, a tablet, etc.), an electro-mechanical acoustic system e.g., electronic speakers), or a combination thereof.

18. The non-transitory CRM of paragraph 16 or 17, wherein the user interface includes a digital screen selected from a screen of smartphone, laptop, desktop computer, watch, or tablet.

19. The non-transitory CRM of paragraph 16 or 17, wherein the user interface includes an electro-mechanical acoustic system selected from one or more electronic speakers.

20. A method of treating a patient diagnosed with psychosis using the CIM of any one of paragraphs 1 to 12, wherein the treatment involves any one or more of antipsychotic medications (typical and atypical), mood stabilizers, anxiolytics, antidepressants, cognitive behavioral therapy for psychosis, supportive therapy, insight-oriented therapy, family therapy, social skills training, vocational rehabilitation, case management, hospitalization, electroconvulsive therapy (ECT), sleep hygiene, exercise, dietary adjustments, mindfulness, relaxation techniques, or any combinations thereof.

21. The method of paragraph 20, wherein the antipsychotic medication is selected from haloperidol, chlorpromazine, fluphenazine, perphenazine, thioridazine, trifluoperazine, loxapine, pimozide, risperidone, olanzapine, quetiapine, aripiprazole, clozapine, ziprasidone, paliperidone, lurasidone, asenapine, brexpiprazole, cariprazine, or a combination thereof.

24. A method of treating a patient diagnosed with psychosis using a device containing the non-transitory CRM of any one of paragraphs 13 to 19, wherein the treatment comprises any one or more of antipsychotic medications (typical and atypical), mood stabilizers, anxiolytics, antidepressants, cognitive behavioral therapy for psychosis, supportive therapy, insight-oriented therapy, family therapy, social skills training, vocational rehabilitation, case management, hospitalization, electroconvulsive therapy (ECT), sleep hygiene, exercise, dietary adjustments, mindfulness, relaxation techniques, or any combinations thereof.

25. The method of claim 24, wherein the antipsychotic medication is selected from haloperidol, chlorpromazine, fluphenazine, perphenazine, thioridazine, trifluoperazine, loxapine, pimozide, risperidone, olanzapine, quetiapine, aripiprazole, clozapine, ziprasidone, paliperidone, lurasidone, asenapine, brexpiprazole, cariprazine, or a combination thereof.

Those skilled in the art will recognize or be able to ascertain using no more than routine experimentation many equivalents to the specific embodiments of the invention described herein. Such equivalents are intended to be encompassed by the following claims.

Claims

We claim:

1. A computer-implemented method (CIM) for neurobiological diagnosis of a subject, optionally followed by an individual devising a treatment regiment, the method comprising: using one or more computer-implemented algorithms (i) configured to process a first set of bio-factor data from the subject and (ii) configured to classify the subject as having a subtype of psychosis, wherein the one or more computer-implemented algorithms have been trained on a second set of bio-factor data to recognize one or more subtypes of psychosis, wherein the second set of bio-factor data comprises bio- factor data agnostic to clinical diagnosis of psychosis of the subject, and/or selecting the second set of bio-factor data does not require statistical differences between Diagnostic and Statistical Manual (DSM) psychosis groups and healthy groups, and wherein the one or more computer-implemented algorithms are operably linked to one or more processors.

2. The CIM of claim 1 , wherein selecting the second set of bio-factor data does not require statistical differences between Diagnostic and Statistical Manual (DSM) psychosis groups and healthy groups.

3. The CIM of claim 1 or 2, wherein the psychosis is idiopathic.

4. The CIM of any one of claims 1 to 3, wherein the first set of bio-factor data comprises the subject’s cognitive performance data, behavioral performance data, brain signal data, or a combination thereof.

5. The CIM of any one of claims 1 to 4, wherein the first set of bio-factor data comprises the subject’s Brief Assessment of Cognition in Schizophrenia (BACS) data, anti-saccade data, paired stimuli data (e.g., auditory paired stimuli data), oddball event-related brain potentials (ERP) data, intrinsic electroencephalography activity (IEA) data, or a combination thereof.

6. The CIM of any one of claims 1 to 5, wherein the first set of bio-factor data comprises the subject’s intrinsic electroencephalography activity (IEA) data, optionally obtained from a living, awake brain.

7. The CIM of any one of claims 1 to 6, wherein classifying the subject as having a subtype of psychosis comprises: using one or more classification algorithms (e.g., a decision tree, a logistic regression, a random forest, support vector machine, a k-nearest neighbors algorithm, naive Bayes, etc.).

8. The CIM of any one of claims 1 to 7, wherein the subtype of psychosis comprises a neural dysregulation Biotype (BT2), a neural vigor Biotype (BT1), and a stimulus salience Biotype (BT3).

9. The CIM of any one of claims 1 to 8, further comprising: causing a recommendation of one or more treatment regiments based on the subtype of psychosis to be presented at a user interface comprising a display of a computing device, an electromechanical acoustic system, or a combination thereof.

10. The CIM of any one of claims 1 to 9, further comprising: re-tuning the one or more computer-implemented algorithms on a third set of data, wherein the third set of data comprises a third set of bio-factor data.

11. The CIM of claim 10, further comprising: performing a principal component analysis to identify the second set of bio-factor data and/or the third set of bio-factor data prior to training, re-tuning, or a combination thereof.

12. The CIM of any one of claims 1 to 11, wherein the CIM provides neurological diagnosis in real-time.

13. A non-transitory computer-readable medium (CRM) with one or more computer-executable instructions stored thereon executed by one or more processors, wherein the one or more computerexecutable instructions comprise one or more computer-implemented algorithms (i) configured to process a first set of bio-factor data from the subject and (ii) configured to classify the subject as having a subtype of psychosis, wherein the algorithm has been trained on a second set of bio-factor data to recognize one or more subtypes of psychosis, wherein the second set of bio-factor data comprises bio-factor data agnostic to clinical diagnosis of psychosis of the subject, and wherein the one or more computer-executable instructions are operably linked to the one or more processors.

14. The non-transitory CRM of claim 13, wherein the one or more computer-implemented algorithms are capable of being re-tuned using a third set of bio-factor data.

15. The non-transitory CRM of claim 13 or 14, wherein the one or more algorithms comprise machine learning algorithms, dimension reduction algorithms, clustering algorithms, classifier algorithms, or a combination thereof.

16. The non-transitory CRM of any one of claims 13 to 15, wherein the one or more computer- implemented algorithms are operably linked to a user interface and configured to transmit neurobiological diagnosis to the user interface for output at the user interface.

17. The non-transitory CRM of claim 16, wherein the user interface comprises a digital screen, an electro-mechanical acoustic system.

18. The non-transitory CRM of claim 17, wherein the user interface comprises a digital screen selected from a screen of smartphone, laptop, desktop computer, watch, or tablet.

19. The non- transitory CRM of claim 17, wherein the user interface comprises an electromechanical acoustic system selected from one or more electronic speakers.

20. A method of treating a patient diagnosed with psychosis using the C1M of any one of claims 1-12, wherein the treatment comprises any one or more of antipsychotic medications (typical and atypical), mood stabilizers, anxiolytics, antidepressants, cognitive behavioral therapy for psychosis, supportive therapy, insight-oriented therapy, family therapy, social skills training, vocational rehabilitation, case management, hospitalization, electroconvulsive therapy (ECT), sleep hygiene, exercise, dietary adjustments, mindfulness, relaxation techniques, or any combinations thereof.

21. The method of claim 20, wherein the antipsychotic medication is selected from haloperidol, chlorpromazine, fluphenazine, perphenazine, thioridazine, trifluoperazine, loxapine, pimozide, risperidone, olanzapine, quetiapine, aripiprazole, clozapine, ziprasidone, paliperidone, lurasidone, asenapine, brexpiprazole, cariprazine, or a combination thereof.

24. A method of treating a patient diagnosed with psychosis using a device comprising the non- transitory CRM of any one of claims 13 to 19, wherein the treatment comprises any one or more of antipsychotic medications (typical and atypical), mood stabilizers, anxiolytics, antidepressants, cognitive behavioral therapy for psychosis, supportive therapy, insight-oriented therapy, family therapy, social skills training, vocational rehabilitation, case management, hospitalization, electroconvulsive therapy (ECT), sleep hygiene, exercise, dietary adjustments, mindfulness, relaxation techniques, or any combinations thereof.

25. The method of claim 24, wherein the antipsychotic medication is selected from haloperidol, chlorpromazine, fluphenazine, perphenazine, thioridazine, trifluoperazine, loxapine, pimozide, risperidone, olanzapine, quetiapine, aripiprazole, clozapine, ziprasidone, paliperidone, lurasidone, asenapine, brexpiprazole, cariprazine, or a combination thereof.