CN116597995A - System for screening and managing high risk group of cerebral apoplexy in hospital based on artificial intelligence - Google Patents
System for screening and managing high risk group of cerebral apoplexy in hospital based on artificial intelligence Download PDFInfo
- Publication number
- CN116597995A CN116597995A CN202310546740.4A CN202310546740A CN116597995A CN 116597995 A CN116597995 A CN 116597995A CN 202310546740 A CN202310546740 A CN 202310546740A CN 116597995 A CN116597995 A CN 116597995A
- Authority
- CN
- China
- Prior art keywords
- risk group
- screening
- risk
- cerebral apoplexy
- hospital
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 208000006011 Stroke Diseases 0.000 title claims abstract description 83
- 230000002490 cerebral effect Effects 0.000 title claims abstract description 66
- 206010008190 Cerebrovascular accident Diseases 0.000 title claims abstract description 64
- 238000012216 screening Methods 0.000 title claims abstract description 58
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000012502 risk assessment Methods 0.000 claims abstract description 17
- 238000003745 diagnosis Methods 0.000 claims description 34
- 230000003993 interaction Effects 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 7
- 238000003032 molecular docking Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000010570 post-docking Methods 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 6
- 238000003058 natural language processing Methods 0.000 description 6
- 201000010099 disease Diseases 0.000 description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 5
- 208000032109 Transient ischaemic attack Diseases 0.000 description 4
- 230000000391 smoking effect Effects 0.000 description 4
- 201000010875 transient cerebral ischemia Diseases 0.000 description 4
- 206010003658 Atrial Fibrillation Diseases 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000002604 ultrasonography Methods 0.000 description 3
- 208000032928 Dyslipidaemia Diseases 0.000 description 2
- 206010020772 Hypertension Diseases 0.000 description 2
- 208000017170 Lipid metabolism disease Diseases 0.000 description 2
- 208000008589 Obesity Diseases 0.000 description 2
- 206010008118 cerebral infarction Diseases 0.000 description 2
- 208000026106 cerebrovascular disease Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 206010012601 diabetes mellitus Diseases 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 235000020824 obesity Nutrition 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 201000006474 Brain Ischemia Diseases 0.000 description 1
- 206010008120 Cerebral ischaemia Diseases 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 102000017011 Glycated Hemoglobin A Human genes 0.000 description 1
- 108010014663 Glycated Hemoglobin A Proteins 0.000 description 1
- FFFHZYDWPBMWHY-VKHMYHEASA-N L-homocysteine Chemical compound OC(=O)[C@@H](N)CCS FFFHZYDWPBMWHY-VKHMYHEASA-N 0.000 description 1
- 206010053649 Vascular rupture Diseases 0.000 description 1
- 206010057469 Vascular stenosis Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 206010003119 arrhythmia Diseases 0.000 description 1
- 230000006793 arrhythmia Effects 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 208000035474 group of disease Diseases 0.000 description 1
- 230000007971 neurological deficit Effects 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000005586 smoking cessation Effects 0.000 description 1
- 230000009861 stroke prevention Effects 0.000 description 1
- 208000037816 tissue injury Diseases 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Pathology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application discloses an artificial intelligence-based screening and management system for high risk group of cerebral apoplexy in hospital, comprising the following steps: the system comprises a data access module, a high-risk group screening module and a high-risk group management module; the data access module is respectively connected with the high-risk group screening module, the high-risk group management module and the EMR system, and is used for receiving and processing EMR original data to obtain a relevant characteristic set of the high-risk group; the high-risk group screening module is used for carrying out cerebral apoplexy high-risk assessment based on the related feature set to obtain an assessment result; the high-risk group management module is used for sending an intervention management prompt to a doctor based on the evaluation result and generating post-intervention notes based on the evaluation result and the intervention process of the doctor. The application can relieve the pressure of high-risk cerebral apoplexy screening of basic medical institutions, and improve the prevention and management in and after the hospital of high-risk cerebral apoplexy people while relieving the burden of medical staff to a certain extent.
Description
Technical Field
The application belongs to the technical field of artificial intelligence assisted medical decision making, and particularly relates to an artificial intelligence-based screening and management system for high-risk group of cerebral apoplexy in a hospital.
Background
Cerebral apoplexy is an acute cerebrovascular disease, is a group of diseases which are caused by cerebral tissue injury due to cerebral vascular rupture or cerebral ischemia caused by vascular blockage, and has the characteristics of high morbidity, high disability rate, high mortality rate and high recurrence rate. Prevention is considered to be the best measure for effectively reducing the mortality of the disease, as there is a constant lack of effective treatment. Early evaluation of patients can effectively prevent cerebral apoplexy by screening out high risk groups, so that the prevention consciousness of the patients is improved, and accurate intervention of key target groups is further realized.
Although Chinese stroke prevention has become a national focus and significant effort in screening, the high rate of stroke death remains a significant public health challenge for the quality and efficiency of large-scale stroke risk screening. Because of the limitations of limited medical resources and the like in the basic level, the in-hospital cerebral apoplexy risk screening of the superior hospital is still the key point of the screening work, but the in-hospital high-risk cerebral apoplexy screening work mainly depends on medical staff to carry out risk layering according to an evaluation table recommended by a guideline, although part of hospitals embed the evaluation table into a Hospital Information System (HIS), the problem that the manual checking of the evaluation table causes the burden of doctors to be increased, the dynamic risk screening is difficult, the screening capability of the risk evaluation table is limited, the screening index is simple, HIS business data information is isolated, the neurological consultation of high-risk groups is not in time, the post-hospital management and handover of patients are difficult and the like still exists. With the development of information technology and artificial intelligence, patent number CN111430029B discloses a multi-dimensional cerebral apoplexy prevention screening method based on artificial intelligence, which brings doctor inquiry, blood biochemical indexes and daily monitoring indexes into a screening system, solves the problems of simple screening indexes and excessive burden of doctors to a certain extent, but carries out the inspection and examination required by cerebral apoplexy screening, dynamically tracks the risk state, and carries out diagnosis and treatment procedures such as neurology consultation, community management handover after cerebral apoplexy prevention and education of high-risk early-warning patients, and the like, and still needs to rely on the excessive professional literacy of medical staff. However, in the implementation process of cerebral apoplexy dynamic high-risk screening of inpatients, the phenomenon of weak awareness of screening in part of departments still exists, and due to the fact that medical staff is required to put into a great deal of effort, omission and delay of necessary screening projects of patients with potential high-risk groups and high-risk risks cannot be avoided, and untimely consultation of neurology specialists of high-risk patients is avoided, and the loss of post-hospital management handover process (including post-hospital self-management and post-hospital community management) is avoided. Aiming at the problems, the technical scheme is that the high-risk cerebral apoplexy screening and managing system capable of realizing high-efficiency dynamic in-hospital cerebral apoplexy risk screening is needed in the field, standardizing the diagnosis and treatment processes of medical staff in quality control hospitals for managing different cerebral apoplexy risk groups, and facilitating self-management and community management of patients after docking.
Disclosure of Invention
The application aims to solve the defects of the prior art, and provides an artificial intelligence-based screening and management system for high risk groups of cerebral apoplexy in a hospital, which realizes efficient dynamic cerebral apoplexy risk assessment aiming at inpatients and timely quality control reminding of medical staff on relevant diagnosis and treatment links of screening and management of the high risk groups of cerebral apoplexy.
In order to achieve the above object, the present application provides the following solutions:
an artificial intelligence-based screening and management system for high risk group of cerebral apoplexy in hospital, comprising: the system comprises a data access module, a high-risk group screening module and a high-risk group management module;
the data access module is respectively connected with the high-risk group screening module, the high-risk group management module and the EMR system, and is used for receiving and processing EMR original data to obtain a relevant characteristic set of the high-risk group;
the high-risk group screening module is used for carrying out cerebral apoplexy high-risk assessment based on the related feature set to obtain an assessment result;
the high-risk group management module is used for sending an intervention management prompt to a doctor based on the evaluation result and generating post-intervention notes based on the evaluation result and the intervention process of the doctor.
Preferably, the data access module includes: the device comprises a data input unit, a data processing unit and a data return unit;
the data input unit is used for inputting EMR original data;
the data processing unit is used for carrying out post-structuring processing on the EMR original data to obtain processed data;
the data processing unit is further configured to extract the set of relevant features based on the processed data;
the data return unit is used for returning the evaluation result, the intervention process and the post-intervention notes to an EMR system.
Preferably, the post-structuring treatment method comprises the following steps:
the pure text in the EMR original data is segmented to obtain a generation labeling entity;
semantic annotation is carried out on the generation annotation entity, and an annotated entity is obtained;
and constructing a cerebral apoplexy semantic tree based on the marked entity, and completing the post-structuring processing to obtain the relevant feature set.
Preferably, the relevant feature set includes a keyword library of ten decision points of a stroke score scale.
Preferably, the high risk group screening module includes: the dynamic intelligent risk assessment unit and the man-machine interaction unit;
the dynamic intelligent risk assessment unit is used for dynamically judging the high risk of cerebral apoplexy based on the related feature set to obtain the assessment result;
the man-machine interaction unit is used for providing the evaluation result for a doctor for verification;
and the doctor can further utilize the man-machine interaction unit to continuously modify the evaluation result so as to complete double verification of the evaluation result.
Preferably, the dynamic determination process includes:
scoring the high-risk items in the related feature set by using an XGBoost algorithm;
when the score value is larger than the preset score value, the high risk of cerebral apoplexy is judged, and when the score value is smaller than the preset score value, the low risk of cerebral apoplexy is judged;
and dynamically evaluating the patient judged to be at high risk of cerebral apoplexy to obtain the evaluation result.
Preferably, the high risk group management module includes: the hospital management unit and the docking post-hospital management unit;
the hospital management unit is used for analyzing the evaluation result and the doctor diagnosis and treatment process, sending an intervention management prompt to a doctor based on the analysis result and reminding the doctor of carrying out diagnosis and treatment intervention;
the post-docking management unit is used for generating post-intervention notes based on the evaluation result and the intervention process of the doctor.
Preferably, the intervention management reminder includes: the key diagnosis and treatment flow reminding and the missing diagnosis and treatment flow reminding.
Compared with the prior art, the application has the beneficial effects that:
(1) According to the application, through accessing EMR system data, depending on post-structured data processing capability, based on machine learning and combining a medical knowledge base, the screening project indexes required by high risk groups are perfected through man-machine interaction, the cerebral apoplexy high risk groups in inpatients are effectively identified, the burden of medical workers is reduced, and the screening efficiency and quality are improved;
(2) Through analyzing the risk assessment result of cerebral apoplexy, intelligently recommending required diagnosis and treatment measures, automatically checking with the diagnosis and treatment path of doctors, carrying out 'leak detection and deficiency repair' and timely reminding, particularly high-risk early warning patients, further enhancing the intra-hospital management of high-risk groups of cerebral apoplexy and reducing the occurrence of cerebral apoplexy events in the hospital;
(3) By guiding out the risk scoring result of cerebral apoplexy in hospital, the diagnosis and treatment intervention process and the post-hospital management notice, the self-management awareness of patients after hospital is improved, the management of the high-risk group of cerebral apoplexy in the primary hospital after hospital docking is facilitated, the pressure of high-risk screening of cerebral apoplexy in the primary medical institution is relieved, the burden of medical staff is reduced to a certain extent, and meanwhile, the prevention and management of the high-risk group of cerebral apoplexy in and after hospital are improved.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the embodiments are briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a system structure according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description.
In this embodiment, as shown in fig. 1, an artificial intelligence-based screening and management system for high risk group of cerebral apoplexy in hospital includes: the system comprises a data access module, a high-risk group screening module and a high-risk group management module.
The data access module is respectively connected with the high-risk group screening module, the high-risk group management module and the EMR system, and is used for receiving and processing EMR original data to obtain a relevant characteristic set of the high-risk group. The data access module comprises: the device comprises a data input unit, a data processing unit and a data return unit.
The data input unit is used for inputting EMR original data. The EMR adopts electronic equipment such as a computer to store, manage, transmit and online digitize medical records, including personal information of patients in the whole hospital, vital signs, disease course records, examination and examination results, medical orders, operation records, nursing records and the like. Further, the EMR raw data includes medical data of different structural types: structured data and unstructured data; the structured data (such as vital signs, medical orders, diagnosis and the like) are composed of well-defined data types, are easy to search, and have the characteristics of quick early warning, quick prompt and high intelligent degree after being accessed into a cerebral apoplexy screening and management module; unstructured data, such as examination report results, course records, operation records, etc., require further post-structuring of such data.
The data processing unit is used for carrying out post-structuring processing on the EMR original data to obtain processed data; the data processing unit also extracts a set of related features based on the processed data. The data processing unit is used for carrying out post-structuring processing on EMR original data by utilizing Natural Language Processing (NLP) and Named Entity Recognition (NER) to obtain processed data, and carrying out high-risk cerebral apoplexy medical feature extraction by combining a medical knowledge base to obtain a related feature set.
Further, post-structuring is a process of performing deep learning-based medical language processing on the unstructured data by using NLP; the relevant feature set includes basic information in EMR raw data, basic vital signs, orders, diagnostic course records, care records, exam report results, and the like. The post-structuring processing method comprises the following steps: the method comprises the steps of segmenting a plain text in EMR original data to obtain a generation labeling entity; semantic annotation is carried out on the generation annotation entity, and an entity after annotation is obtained; and constructing a cerebral apoplexy semantic tree based on the marked entity, and performing post-construction treatment to obtain a relevant feature set. The relevant feature set comprises a keyword library of ten judgment points of a stroke scoring scale.
In this embodiment, the post-structuring method specifically includes the following steps: s1, segmenting the plain text of the electronic medical record, and adopting a general simplified Chinese shielding word list to obtain a marked entity; s2, automatically labeling the entity; s3, modeling and generating a cerebral apoplexy semantic tree, and realizing post-text structuring processing; s4, post-structuring extraction rules, namely matching the post-structuring extraction rules by using a rule engine, finally outputting the formatted data in json format, and determining the rules by the final requirement. The relevant feature set for screening out the high risk group of cerebral apoplexy is a keyword library combining a medical knowledge base and results based on machine learning, wherein the relevant feature set comprises ten judgment points of a cerebral apoplexy scoring scale.
The embodiment needs to further explain the keyword library related to the decision point: ten decision points include hypertension, diabetes, dyslipidemia, few physical activities, smoking, atrial fibrillation, obesity, family history of stroke, history of past stroke, past Transient Ischemic Attacks (TIA); the keyword library includes standard terms, data item names, legal keywords, negative keywords, and suspicious keywords. Further, the decision points for hypertension, diabetes and dyslipidemia include diagnosis in hospitals of two or more levels, disease history and medication history, and the negative history is determined by means of specific examination check values (if any); the physical exercise judgment points comprise physical exercise standards and medium physical labor standard judgment; the smoking history judging points comprise smoking, smoking cessation and passive smoking conditions; atrial fibrillation decision points include symptoms, signs, electrocardiographic examination results, atrial fibrillation history, and whether there is an autonomic arrhythmia sensation; the obesity determination point is BMI index (BMI=weight (kg)/height) 2 (m 2 ) The method comprises the steps of carrying out a first treatment on the surface of the The past stroke family history judging points comprise whether the direct relatives are ill or not and specific conditions; the brain of the pastThe history of stroke, past TIA should be judged by neurologists; the past stroke history judging points comprise the clear diagnosis, neurological deficit symptoms in the onset of the disease in the second-stage hospitals and above, and the detailed past history, treatment and return conditions of the symptomatic lacunar cerebral infarction; the past TIA decision points include secondary and above hospital diagnosis and administration of regular treatment, detailed past medical history, treatment and prognosis.
The data feedback unit is used for transmitting the evaluation result, the intervention process and the notice matters after the intervention back to the EMR system. In this embodiment, the data transmission unit may select the risk assessment result of the cerebral apoplexy of the patient and transmit back to the EMR system, further based on medical knowledge, the auxiliary diagnosis and treatment advice of the patient with different risk grades is intelligently analyzed and recommended, and the final risk assessment result, the diagnosis and treatment process in the hospital, the post-hospital management notice and other contents may be imported into the discharge record and submitted to the patient, which is helpful for enhancing the understanding and importance of the patient to the self situation, helping the basic medical staff to know the patient condition more quickly and definitely, and facilitating the implementation of post-hospital management of the cerebral apoplexy high-risk patient.
The high-risk group screening module is used for carrying out cerebral apoplexy high-risk assessment based on the relevant feature set to obtain an assessment result. The high risk crowd screening module includes: a dynamic intelligent risk assessment unit and a man-machine interaction unit.
The dynamic intelligent risk assessment unit is used for dynamically judging the high risk of cerebral apoplexy based on the relevant feature set to obtain an assessment result. The dynamic determination flow comprises the following steps: scoring the high-risk items in the related feature set by using an XGBoost algorithm; when the score value is larger than the preset score value, the high risk of cerebral apoplexy is judged, and when the score value is smaller than the preset score value, the low risk of cerebral apoplexy is judged; and dynamically evaluating the patients judged to be at high risk of cerebral apoplexy to obtain an evaluation result.
In this embodiment, the dynamic intelligent risk assessment unit combines with the medical knowledge base, and completes the dynamic judgment of the stroke high risk screening based on the high risk group related feature set extracted by the stroke NLP model. The specific steps of the dynamic judgment are as follows: s1, inputting a relevant feature set of high-risk cerebral apoplexy in EMR original data extracted by NLP and NER; s2, judging a stroke high risk scoring item of the relevant feature set by adopting an XGBoost algorithm, wherein the preset score of the judgment is set to be 3 points; s3, outputting a result value, wherein the result value consists of a yes value and a no value, if the result value is more than or equal to a judgment critical value of 3 minutes, the output is yes, if the result value is the high risk of cerebral apoplexy, otherwise, the output is no, and if the result value is not the low risk of cerebral apoplexy; s4, dynamically evaluating whether the output result is that the inpatients are not. Further, dynamic evaluation means that if illness state changes occur during patient hospitalization, through identifying the change of the accessed post-structured EMR data, the grading result is intelligently upgraded and reminding and warning are carried out, namely, the patients are firstly graded as low risk crowd and then graded as high risk, and screening and warning can be carried out through a dynamic intelligent evaluation system.
The man-machine interaction unit is used for providing an evaluation result for a doctor for verification; the doctor can also utilize the man-machine interaction unit to continuously modify the evaluation result, so as to complete double verification of the evaluation result. The man-machine interaction unit can remind the intelligent risk assessment result when a doctor records the course of a disease, the reminding appears in a popup window mode, the red color is high risk, the warning needs to be highly valued, the low risk is displayed as green, and the popup window is closed after the doctor checks the assessment result. The doctor can also modify the result judgment of the judgment point according to the actual condition of the patient to perform double verification; the medical personnel operation interface reminds the medical personnel in a popup window mode if the medical personnel operation interface is not identified, so that the screening omission of high risk groups in the hospital is reduced.
The high-risk group management module is used for sending an intervention management prompt to the doctor based on the evaluation result and generating post-intervention notes based on the evaluation result and the intervention process of the doctor. The high risk crowd management module includes: an in-hospital management unit and a post-hospital docking management unit.
The hospital management unit is used for analyzing the evaluation result and the doctor diagnosis and treatment process, sending an intervention management prompt to the doctor based on the analysis result and reminding the doctor of carrying out diagnosis and treatment intervention. The intervention management reminder includes: the key diagnosis and treatment flow reminding and the missing diagnosis and treatment flow reminding.
In this embodiment, the intervention process is based on machine learning to analyze the patient condition and the diagnosis and treatment path of the doctor, and the necessary intervention measures are reminded to the diagnosis and treatment process of the medical staff, and the specific steps are as follows: s1, carrying out key diagnosis and treatment process reminding on a high-risk early-warning patient; s2, inputting processed data after NLP and NER recognition processing; s3, judging a necessary diagnosis and treatment process by adopting an XGBoost algorithm; s4, outputting a result value, wherein the result value is yes or no, and represents the existing necessary diagnosis and treatment flow or the lack of the necessary diagnosis and treatment flow; s5, reminding the hospitalized patient with the output result of NO again by carrying out missing diagnosis and treatment paths. The processed data of NLE and NER identification processing comprises course records, examination and inspection results, orders and the like, and is input to the next step of judgment.
The necessary diagnosis and treatment flow needs to be described, the content is based on a medical knowledge base, and the medical knowledge base comprises the steps of carrying out blood fat four items, fasting blood glucose, glycosylated hemoglobin, homocysteine, carotid color ultrasound/vertebral color ultrasound/TCD and electrocardiogram on a patient with high risk early warning with good TCD/carotid or vertebral color ultrasound results, continuously monitoring and controlling risk factors, and timely applying for neurology specialist consultation on the patient with the detection result showing vascular stenosis or unstable plaque and treating the patient with high risk of cerebral apoplexy. Furthermore, the hospital management unit also has a man-machine interaction function, and necessary diagnosis and treatment links such as review of necessary examination and inspection, consultation of neurology specialists and the like are reminded in a popup window mode.
The post-hospital interfacing management unit is used for generating post-intervention notes based on the evaluation result and the intervention process of the doctor. In this embodiment, the post-hospital administration unit may send back the risk assessment result and the intervention diagnosis and treatment process of the cerebral apoplexy in the hospital to the EMR system, intelligently generate post-hospital administration notes, write in and export the medical history, help the patient to understand and attach themselves to the post-hospital administration advice by exporting the post-hospital administration advice, and help the post-hospital administration management of the basic medical institution after the hospital administration to help the basic medical staff to recognize and administer the identified cerebral apoplexy high risk patient in the hospital more quickly.
The above embodiments are merely illustrative of the preferred embodiments of the present application, and the scope of the present application is not limited thereto, but various modifications and improvements made by those skilled in the art to which the present application pertains are made without departing from the spirit of the present application, and all modifications and improvements fall within the scope of the present application as defined in the appended claims.
Claims (8)
1. An artificial intelligence-based screening and management system for high risk group of cerebral apoplexy in hospital, which is characterized by comprising: the system comprises a data access module, a high-risk group screening module and a high-risk group management module;
the data access module is respectively connected with the high-risk group screening module, the high-risk group management module and the EMR system, and is used for receiving and processing EMR original data to obtain a relevant characteristic set of the high-risk group;
the high-risk group screening module is used for carrying out cerebral apoplexy high-risk assessment based on the related feature set to obtain an assessment result;
the high-risk group management module is used for sending an intervention management prompt to a doctor based on the evaluation result and generating post-intervention notes based on the evaluation result and the intervention process of the doctor.
2. The system for screening and managing high risk group of stroke in hospital based on artificial intelligence of claim 1, wherein the data access module comprises: the device comprises a data input unit, a data processing unit and a data return unit;
the data input unit is used for inputting EMR original data;
the data processing unit is used for carrying out post-structuring processing on the EMR original data to obtain processed data;
the data processing unit is further configured to extract the set of relevant features based on the processed data;
the data return unit is used for returning the evaluation result, the intervention process and the post-intervention notes to an EMR system.
3. The system for screening and managing high risk group of stroke in hospital based on artificial intelligence as claimed in claim 2, wherein the method for post-structuring processing comprises:
the pure text in the EMR original data is segmented to obtain a generation labeling entity;
semantic annotation is carried out on the generation annotation entity, and an annotated entity is obtained;
and constructing a cerebral apoplexy semantic tree based on the marked entity, and completing the post-structuring processing to obtain the relevant feature set.
4. The system for screening and managing high risk group of stroke in hospital based on artificial intelligence according to claim 2, wherein the related feature set comprises a keyword library of ten decision points of a stroke scoring scale.
5. The system for screening and managing high risk group of cerebral apoplexy in hospital based on artificial intelligence according to claim 2, wherein the high risk group screening module comprises: the dynamic intelligent risk assessment unit and the man-machine interaction unit;
the dynamic intelligent risk assessment unit is used for dynamically judging the high risk of cerebral apoplexy based on the related feature set to obtain the assessment result;
the man-machine interaction unit is used for providing the evaluation result for a doctor for verification;
and the doctor can further utilize the man-machine interaction unit to continuously modify the evaluation result so as to complete double verification of the evaluation result.
6. The system for screening and managing high risk group of stroke in hospital based on artificial intelligence of claim 5, wherein the process of dynamic determination comprises:
scoring the high-risk items in the related feature set by using an XGBoost algorithm;
when the score value is larger than the preset score value, the high risk of cerebral apoplexy is judged, and when the score value is smaller than the preset score value, the low risk of cerebral apoplexy is judged;
and dynamically evaluating the patient judged to be at high risk of cerebral apoplexy to obtain the evaluation result.
7. The system for screening and managing high risk group of stroke in hospital based on artificial intelligence of claim 5, wherein the high risk group management module comprises: the hospital management unit and the docking post-hospital management unit;
the hospital management unit is used for analyzing the evaluation result and the doctor diagnosis and treatment process, sending an intervention management prompt to a doctor based on the analysis result and reminding the doctor of carrying out diagnosis and treatment intervention;
the post-docking management unit is used for generating post-intervention notes based on the evaluation result and the intervention process of the doctor.
8. The system for screening and managing high risk group of stroke in hospital based on artificial intelligence of claim 7, wherein the intervention management prompt comprises: the key diagnosis and treatment flow reminding and the missing diagnosis and treatment flow reminding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310546740.4A CN116597995A (en) | 2023-05-15 | 2023-05-15 | System for screening and managing high risk group of cerebral apoplexy in hospital based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310546740.4A CN116597995A (en) | 2023-05-15 | 2023-05-15 | System for screening and managing high risk group of cerebral apoplexy in hospital based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116597995A true CN116597995A (en) | 2023-08-15 |
Family
ID=87589162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310546740.4A Pending CN116597995A (en) | 2023-05-15 | 2023-05-15 | System for screening and managing high risk group of cerebral apoplexy in hospital based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116597995A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118315069A (en) * | 2024-06-05 | 2024-07-09 | 吉林大学 | Early warning system and method for cerebral apoplexy high risk group of inpatients |
-
2023
- 2023-05-15 CN CN202310546740.4A patent/CN116597995A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118315069A (en) * | 2024-06-05 | 2024-07-09 | 吉林大学 | Early warning system and method for cerebral apoplexy high risk group of inpatients |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Edgcomb et al. | Machine learning, natural language processing, and the electronic health record: innovations in mental health services research | |
| US9153142B2 (en) | User interface for an evidence-based, hypothesis-generating decision support system | |
| Roque et al. | A comparison of several key information visualization systems for secondary use of electronic health record content | |
| CN112466459B (en) | Active prediction, early warning and full-period intelligent management system for venous thromboembolism | |
| Bowles | Patient problems and nurse interventions during acute care and discharge planning | |
| CN116597995A (en) | System for screening and managing high risk group of cerebral apoplexy in hospital based on artificial intelligence | |
| CN112382388A (en) | Early warning method for adverse pressure sore event | |
| CN116860739A (en) | Severe medical big data processing system and method | |
| Goldstein et al. | Evaluation of an automated knowledge-based textual summarization system for longitudinal clinical data, in the intensive care domain | |
| US20180121545A1 (en) | Methods and system for improving the relevance, usefulness, and efficiency of search engine technology | |
| Ashu et al. | A novel approach of telemedicine for managing fetal condition based on machine learning technology from IoT-based wearable medical device | |
| Faisal et al. | A machine learning approach for analyzing and predicting suicidal thoughts and behaviors | |
| Gray-Miceli et al. | Orthostatic hypotension in older nursing home residents who fall: are they dizzy? | |
| Emakhu et al. | A hybrid machine learning and natural language processing model for early detection of acute coronary syndrome | |
| Sharma et al. | Health Recommendation System by using deep learning and fuzzy technique | |
| Aggarwal et al. | HEDEA: a Python tool for extracting and analysing semi-structured information from medical records | |
| CN115312186B (en) | Auxiliary screening system for diabetic retinopathy | |
| Wulff et al. | Learning healthcare systems in pediatrics: cross-institutional and data-driven decision-support for intensive care environments (CADDIE) | |
| US8756234B1 (en) | Information theory entropy reduction program | |
| CN111966838B (en) | Adverse event and medication relevance judging method and system | |
| Patel et al. | Advancements in Artificial Intelligence for Precision Diagnosis and Treatment of Myocardial Infarction: A Comprehensive Review of Clinical Trials and Randomized Controlled Trials | |
| Zubillaga et al. | Hospital readmission prediction via keyword extraction and sentiment analysis on clinical notes | |
| CN114283942A (en) | System and method for generating individual care scheme based on comprehensive old people assessment condition | |
| Bundi et al. | The role of IoT, blockchain, artificial intelligence and machine learning in maternal health | |
| Ryce et al. | Contemporary use of prophylactic inferior vena cava filters in patients with severe traumatic injuries and high thromboembolic event risk |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |