KR20230060392A - Apparatus and method for predicting mental illness using multimodal artificial neural network - Google Patents

Abstract

The present invention relates to a mental illness prediction device using a multimodal artificial neural network. For this purpose, the device includes: a memory module storing a program code of a mental illness prediction artificial neural network, which is an artificial intelligence system learned to predict the specific mental illness of new mental patients who have not been diagnosed with a specific mental illness through counseling data and activity data of existing mental patients who have been diagnosed with the specific mental illness; and a processing module processing the program code of a mental illness prediction artificial neural network module.

Description

Apparatus and method for predicting mental illness using multimodal artificial neural network}

The present invention relates to an apparatus and method for predicting mental illness using a multimodal artificial neural network.

Depression is one of the most important topics in psychiatry, with 17% of the population experiencing it. Currently, the main method for diagnosing depression in psychiatry is to use a self-diagnosis questionnaire. However, in this case, there is a problem in that objectivity is low because the patient has no choice but to depend on the subjective response felt by the patient. It is extremely difficult to objectify the symptoms of depression. Patients' objectivity is further reduced as they pursue 'desirable sociality' that is conscious of the external gaze.

Even in the case of mental disorders other than depression, the current methodology had limitations. For example, people who have experienced a disaster, such as a natural disaster or a traffic accident, experience various physical and mental difficulties for many years after the disaster. Some of them recover function and return to daily life relatively early after the accident, while others complain of constant mental stress and difficulties in daily life. In order to discriminate people who progress to PTSD (Post-Traumatic Stress Disorder) at an early stage after disasters and traumas, various measurement tools (e.g., EEG, etc.) are used to select high-risk groups for PTSD. Methods have been proposed (US9792823B2). However, since this method requires the use of physical measurement tools, there are limitations in applying it to all people who have experienced large-scale disaster situations, and there are limitations in selecting high-risk groups among those who have experienced disasters.

US Patent Publication US 2014-0046696 A1, Systems and Methods for Pharmacogenomic Decision Support in Psychiatry, AssureRx Health, Inc. US registered patent US 6317731 B1, Method for predicting the therapeutic outcome of a treatment, ADVANCED BIOLOGICAL LABORATORIES S.A. US registered patent US 9792823 B2, Multi-view learning in detection of psychological states, Raytheon BBN Technologies Corp.

Oh, J., Yun, K., Hwang, J. H., & Chae, J. H. (2017). classification of suicide attempts through a Machine learning algorithm Based on Multiple systemic Psychiatric scales., Frontiers in psychiatry,8, 192. Nuriel S. Mor, Kathryn L. Dardeck, (2018). Quantitative Forecasting of Risk for PTSD Using Ecological Factors: A Deep Learning Application, Journal of Social, Behavioral, and Health Sciences 2018, Volume 12, Issue 1, Pages 61-73. IR Galatzer-Levy, S Ma, A Statnikov, R Yehuda and A Y Shalev, (2017). Utilization of machine learning for prediction of post-traumatic stress: a re-examination of cortisol in the prediction and pathways to non-remitting PTSD, Transl Psychiatry (2017) 7, e1070. Barak-Corren Y, Castro VM, Javitt S, Hoffnagle AG, Dai Y, Perlis RH, et al. Predicting suicidal behavior from longitudinal electronic health records. Am J Psychiatry (2017) 174:154-62. Kessler RC, Warner CH, Ivany C, Petukhova MV, Rose S, Bromet EJ, et al. Predicting suicides after psychiatric hospitalization in US Army soldiers: the army study to assess risk and resilience in servicemembers (Army STARRS). JAMA Psychiatry (2015) 72:49-57.

Accordingly, an object of the present invention is to classify a patient's mental illness by using various scales commonly used in psychiatry, counseling data consisting of a patient's video/voice/text, and patient's activity data output from a wearable device as input data. It is to provide a mental disease prediction device and method using a modal artificial neural network.

Hereinafter, specific means for achieving the object of the present invention will be described.

An object of the present invention is to predict the specific mental illness of a new mental illness who is not diagnosed for the specific mental illness through counseling data and activity data of an existing mental illness who is a mental illness diagnosed for the specific mental illness. a memory module for storing program codes of an artificial neural network module for predicting mental illness, which is an artificial neural network trained to perform; and a processing module for processing the program code of the artificial neural network module for predicting mental illness; wherein the program code of the artificial neural network module for predicting mental illness is used to input the counseling data and the activity data of the new mentally ill person. input step; and an inference step of inferring and outputting mental disorder prediction data, which is data for prediction of the specific mental disorder of the new mental disorder patient, wherein the specific mental disorder includes depression of the mental disorder patient. Characterized in that, it can be achieved by providing a mental disease prediction device using a multimodal artificial neural network.

In addition, the specific mental disease includes a plurality of mental diseases including depression of the mentally ill person and a PTSD prognosis of the mentally ill person, and the mental disease prediction artificial neural network module includes a plurality of mental diseases learned for each of the plurality of mental diseases. An artificial neural network may be included, and in the inference step, the mental disorder prediction data for each of the plurality of mental disorders of the new mental disorder patient may be inferred and output.

Another object of the present invention is to determine the specific mental illness of the new mental illness who has not been diagnosed for the specific mental illness through counseling data and activity data of the existing mental illness, who is a mental illness diagnosed for the specific mental illness. and a mental disorder prediction artificial neural network module, which is an artificial neural network trained to perform prediction, wherein the mental disorder prediction artificial neural network module inputs the counseling data and the activity data of the new mental disorder patient, and inputs the mental disorder predictive artificial neural network module. A mental disorder prediction device using a multimodal artificial neural network, characterized in that inferring and outputting mental disorder prediction data, which is data for prediction of the specific mental disorder, and wherein the specific mental disorder includes depression of the mentally ill person. can be achieved by providing

Another object of the present invention is to determine the specific mental illness of the new mental illness who has not been diagnosed for the specific mental illness through counseling data and activity data of the existing mental illness, who is a mental illness diagnosed for the specific mental illness. an input step of inputting the counseling data and the activity data of the new mentally ill person to a mental disorder prediction artificial neural network module, which is an artificial neural network trained to perform prediction; and an inference step in which the mental disorder prediction artificial neural network module infers and outputs mental disorder prediction data, which is data for prediction of the specific mental disorder of the new mental disorder patient, wherein the specific mental disorder is depression of the mental disorder patient. It can be achieved by providing a machine learning method for predicting mental illness using a multimodal artificial neural network, characterized in that it comprises a.

As described above, the present invention has the following effects.

First, according to one embodiment of the present invention, by classifying mental disorders such as depression in real time, an effect capable of appropriately coping with a mental crisis situation is generated.

Second, according to one embodiment of the present invention, for patients who have visited a psychiatric outpatient clinic, etc., an effect that can discriminate mental disorders such as PTSD, depression, and suicide risk with relatively few resources occurs.

The following drawings attached to this specification illustrate preferred embodiments of the present invention, and together with the detailed description of the invention serve to further understand the technical idea of the present invention, the present invention is limited only to those described in the drawings. and should not be interpreted.
1 is a mental disorder prediction device using a multimodal artificial neural network that classifies a patient's mental disorder using a patient's video/voice/text data and the patient's activity data output from a wearable device according to an embodiment of the present invention ( A schematic diagram showing 1),
2 is a schematic diagram showing the configuration of a mental disorder prediction device 1 using a multimodal artificial neural network according to an embodiment of the present invention;
3 is a schematic diagram showing a learning session of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention;
4 is a schematic diagram showing the structure of a multilayer neural network model (deep learning or deep neural network model);
5 is a schematic diagram showing a calculation process at a node of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention;
6 is a schematic diagram showing a drop-out method of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention;
7 is a graph showing a ReLU activation function;
8 is a schematic diagram showing neural network transfer learning of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention;
9 is a schematic diagram showing reinforcement learning of the artificial neural network module 12 for predicting mental illness according to another embodiment of the present invention;
10 is a flowchart illustrating a method for predicting mental illness using a multimodal artificial neural network according to an embodiment of the present invention.

Hereinafter, an embodiment in which a person skilled in the art can easily practice the present invention will be described in detail with reference to the accompanying drawings. However, in the detailed description of the operating principle of the preferred embodiment of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted.

In addition, the same reference numerals are used for parts having similar functions and actions throughout the drawings. Throughout the specification, when a specific part is said to be connected to another part, this includes not only the case where it is directly connected but also the case where it is indirectly connected with another element interposed therebetween. In addition, including a specific component does not exclude other components unless otherwise stated, but means that other components may be further included.

Mental disease prediction device using multimodal artificial neural network

1 is a mental disorder using a multimodal artificial neural network that classifies a patient's mental disorder using consultation data composed of patient's video/voice/text and patient's activity data output from a wearable device according to an embodiment of the present invention. It is a schematic diagram showing the prediction device 1. As shown in FIG. 1, the mental disorder prediction apparatus 1 using the multimodal artificial neural network of the training session includes counseling data (100, patient's Psychiatric counseling session data composed of video/voice/text), activity data (200, sensor data including activity/sleep/stress data input from a wearable device given to the patient), and a questionnaire item 300 are input to provide multimodal artificial intelligence. A mental disorder predictive device (1) using a neural network is learned, and a mental disorder predictive device (1) using a multimodal artificial neural network in an inference session includes a patient who has not been diagnosed with a specific mental disorder, a patient with a new mental illness. Counseling data (100), activity data (200) are entered to predict depression (Depressive disorder) data (400), PTSD (posttraumatic stress disorder) prognosis prediction data (500), suicide attempt probability prediction data, anxiety disorder (Anxiety disorder) Mental disorder prediction data such as prediction data is output. Hereinafter, for convenience of explanation, the contents of the present invention will be described based on depression prediction data 400 and PTSD prognosis prediction data 500 among mental disease prediction data, and the scope of the present invention may not be limited thereto.

An apparatus for predicting mental illness using a multimodal artificial neural network according to an embodiment of the present invention (1) is a processing module of a computing device such as a specific web server, a virtual server such as a cloud server, a smartphone, a tablet PC, and a desktop PC. It can be configured to be processed by and stored in a memory module of each device.

Counseling data 100 refers to data about a counseling session for a mentally ill patient input in the form of video, audio, or text through a digital device. Counseling data 100 may be input from a smartphone, tablet, or PC of a mentally ill person or from a smartphone, tablet, or PC of a doctor in charge.

The activity data 200 refers to activity data about sleep, breathing, stress, etc. output by sensor data of a wearable device provided to a mentally ill patient. The activity data 200 may be input from a smart phone, tablet, PC, etc. connected to the wearable device of the mentally ill person, or input from the smart phone, tablet, PC, etc. of the doctor in charge.

Questionnaire 300 refers to questionnaires on psychiatric diagnosis, such as a depression questionnaire on depression, a suicide attempt questionnaire on suicide attempts, and a PTSD questionnaire on PTSD (posttraumatic stress disorder). . Suicide attempt questionnaires according to an embodiment of the present invention are "(1) Have you ever attempted suicide during your lifetime?, (2) Have you ever attempted suicide within the last year?, (3) Have you attempted suicide within the past month? Have you tried it?", and each questionnaire can be learned as an output value of the mental disorder prediction apparatus 1 using a multimodal artificial neural network. The questionnaire items 300 may be input from a smartphone, tablet, or PC of a mentally ill person or from a smartphone, tablet, or PC of a doctor in charge.

Depression prediction data 400 refers to the probability of depression of a corresponding mentally ill person predicted in an inference session according to a questionnaire item 300 on a depression questionnaire in a learning session.

The PTSD prognosis prediction data 500 means the possibility of PTSD prognosis of the mentally ill person predicted in the reasoning session according to the question items 300 of the PTSD questionnaire in the learning session.

The mental disorder prediction device 1 using a multimodal artificial neural network according to an embodiment of the present invention can be configured in the form of supervised learning, linear / logistic regression analysis (Regression), support vector machine (Support Vector Machine) It can be configured with various machine learning algorithms such as , multi-layer perceptron, Naive-Bayesian Classification, Random Forest Classification, and Neural Network. For convenience of description, the following describes an apparatus for predicting mental illness using a multimodal artificial neural network according to an embodiment of the present invention as an example configured with an artificial neural network.

FIG. 2 is a schematic diagram showing the configuration of an apparatus 1 for predicting mental illness using a multimodal artificial neural network according to an embodiment of the present invention. As shown in FIG. 2, the apparatus 1 for predicting mental illness using a multimodal artificial neural network according to an embodiment of the present invention includes a counseling data encoder 10, an activity data encoder 11, and a mental disorder predictive artificial neural network. module 12.

The counseling data encoder 10 learns based on the counseling data 100, activity data 200, and questionnaire items 300 of the existing mentally ill patient, and converts the counseling encoding vector based on the counseling data 100 of the new mentally ill patient. It refers to a module in which artificial neural network algorithms for reasoning are stored and processed.

The activity data encoder 11 learns based on the counseling data 100, activity data 200, and questionnaire items 300 of the existing mentally ill person, and converts the activity encoding vector based on the activity data 200 of the new mentally ill person. It refers to a module in which artificial neural network algorithms for reasoning are stored and processed.

The mental disorder prediction artificial neural network module 12 takes as input data a combination vector obtained by combining a counseling encoding vector and an activity encoding vector, and uses mental disorder prediction data such as depression prediction data and PTSD prognosis prediction data as output data. means module.

The neural network model of the counseling data encoder 10, activity data encoder 11, and mental disorder prediction artificial neural network module 12 is a supervised learning algorithm derived from the structure of neurons in biology. The basic operating principle of a neural network model is to predict an optimal output value for an input value by interconnecting several neurons. From a statistical point of view, a neural network model can be viewed as a projective tracking regression that takes a non-linear function over a linear combination of input variables. Hereinafter, for convenience of description, the mental disorder prediction artificial neural network module 12 will be mainly described.

3 is a schematic diagram showing a learning session of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention. As shown in FIG. 3, each attribute constituting the counseling encoding vector and activity encoding vector of the existing mentally ill patient is input to each node of the input layer of the counseling data encoder 10, such as x1, x2, and x3. And, after computing hidden layers such as h1, h2, and h3 based on weights such as w1, depression prediction data 400 predicted based on a cost function such as softmax or ReLU is an output layer with y1 ) Depression prediction data 400 is output. Back propagation can be performed to update the weight of the hidden layer in the direction of reducing the error (error, -Sigma(y _i log pi ₎ ) of the output depression prediction data 400 and the actual depression questionnaire 300.

Regarding the specific structure of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention, FIG. 4 is a schematic diagram showing the structure of a multi-layer neural network model (deep learning or deep neural network model). As shown in FIG. 4, the multilayer neural network model of the counseling data encoder 10 according to an embodiment of the present invention is composed of an input layer, a hidden layer, and an output layer. The input layer is composed of nodes corresponding to each input variable, and the number of nodes is equal to the number of input variables. The hidden layer serves to process the linear combination of variable values transmitted from the input layer with a non-linear function such as the sigmoid function and pass it to the output layer or other hidden layer (recently, by applying the chain rule in Back propagation, the error is Since the vanishing gradient problem occurs in , ReLU is generally used instead of the sigmoid function). The output layer is a node corresponding to an output variable, and output nodes are generated as many as the number of classes in the classification model.

5 is a schematic diagram showing a calculation process in a node of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention. As shown in FIG. 5 , calculation actually occurs at each node, and this calculation process is mathematically designed to simulate a process occurring in neurons constituting a human neural network. A node responds when it receives a stimulus of a certain size or more, and the size of the response is approximately proportional to the value obtained by multiplying the input value and the node's coefficient (or weights), excluding the bias value. In general, a node receives multiple inputs and has as many coefficients as the number of inputs. Therefore, by adjusting this coefficient, different weights can be given to different inputs. Finally, the multiplied values are all added up, and the sum goes into the input of the activation function. The result of the activation function corresponds to the output of the node, and this output value is ultimately used for classification or regression analysis. Each layer of the neural network model is composed of at least one node, and activation/deactivation of each node is determined according to an input value. The input data becomes the input of the first layer (input layer), and then the output of each layer becomes the input of the next layer. All the coefficients keep changing slightly during the learning process, which in turn reflects which inputs each node considers important. And 'training' of the neural network model is the process of updating these coefficients.

The most problematic problem in multilayer neural network models, that is, deep learning, is overfitting. Overfitting occurs when the complexity of the model is high compared to the amount of data given. Unfortunately, the complexity of the model increases exponentially as the neural network gets deeper. Therefore, although everyone knows that a deep network that can learn almost infinite phenotypes is good, overfitting occurs so severely that neural network research was stopped by Professor Marvin Minsky's 1969 Perceptrons theory. However, around 2007~2008, new initialization methods to prevent overfitting, such as RBM (Restricted Boltzmann Machine) and CNN (Convolutional Neural Network), were proposed, and deep learning research was actively conducted again.

In particular, RBM is used as a component of DBN (Deep Belief Network), and overfitting by effectively pre-training each layer of the feedforward neural network to be trained through an unsupervised RBM (restricted Boltzmann machine) We set an initialize point at a level that can prevent this, and proceed with learning in the form of using supervised back propagation again.

However, unsupervised pretraining such as RBM and DBN, which was proposed in two papers, the Greedy layer-wise training of deep networks by Professor Bengio's research team published in NIPS 2006 and A fast learning algorithm for deep belief nets by Professor Hinton's research team published in NIPS 2007 methods are not used in current practice. This is because it is now known that random initialization performs much better than initializing the weights in this way when there is enough data. As part of random initialization, the concept of drop-out was introduced, and most of them use the drop-out method recently.

6 is a schematic diagram showing a drop-out method of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention. As shown in FIG. 6, the drop-out method of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention uses about 50% of neurons in the hidden layer instead of all neurons in each learning do. It is known that there is an effect of ensemble of several small neural networks in one deep learning, and the ensemble greatly reduces overfitting. In addition, neurons with similar weights are reduced, so neurons making redundant judgments are reduced, which has the advantage of being able to use neurons efficiently.

In addition, recently, an activation function called ReLU (Rectified Linear Unit) has been used to solve problems such as slow learning time and overfitting. 7 is a graph showing a ReLU activation function. As shown in FIG. 7, the existing sigmoid function has a problem that errors disappear whenever gradient descent is performed in several layers. As you go through several layers and reach the limit, the gradient of the sigmoid function becomes smaller, causing a problem that the weights are not updated. However, when using the ReLU function as an activation function, when the gradient is learned as 0 or 1, the error is propagated to 100%, which solves this problem. Since the ReLU function is not limited to [0,1] like sigmoid and its range is unlimited, it can be seen that it has more reliable expressive power. In addition, there are many unnecessary values among the output values of each node. In this case, when using the sigmoid function, it is necessary to calculate all values, but the ReLU function can reduce a large part of the amount of calculation, resulting in an effect of improving the computing speed. Regularization can be improved by the ReLU function.

In the learning session of the mental disorder prediction artificial neural network module 12 according to an embodiment of the present invention, suicide attempt data is disproportionate (learning) compared to general mental disorders such as depression (Depressive disorder) or anxiety disorder (learning). Among the data, there is a problem that there is an imbalance between the data with suicide attempts and the data without suicide attempts) and the amount is small. In order to solve this problem, the mental disorder prediction artificial neural network module 12 according to an embodiment of the present invention is a general mental disorder in which the artificial neural network can easily learn due to a large amount of data, such as depression (Depressive disorder). It can be configured as a method of transferring the pre-learned artificial nerve of the artificial neural network module for.

Regarding neural network transfer, FIG. 8 is a schematic diagram showing neural network transfer learning of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention. As shown in FIG. 8, some layers of the mental disorder prediction artificial neural network module 12 predicting depression are some layers of the mental disorder prediction artificial neural network module 12 predicting other mental disorders. It is generated by neural network transition, and the remaining layers of the mental disorder prediction artificial neural network module 12 are generated as initialization layers in which the initial weight w and the initial bias b, which are parameters, are randomly initialized. Then, based on the counseling data (100) and activity data (200) of the mentally ill patient including the questionnaire items (300) for a specific mental disorder, the generated mental disorder prediction artificial neural network module (12) is relearned to predict mental illness. Parameters of the artificial neural network module 12 may be calibrated in detail. At this time, the input data of the mental disorder prediction artificial neural network module 12 for predicting depression is the counseling data 100 and activity data 200 of the mentally ill patient including the questionnaire 300 about depression, and the output data is depression prediction. data, and the input data of the mental disorder prediction artificial neural network module (12) for prediction of other mental disorders are counseling data (100) and activity data (200) of a mentally ill patient including a questionnaire item (300) for a specific mental disorder And the output data is depression prediction data (400).

In particular, neural network transition according to an embodiment of the present invention may be performed to configure only the output layer or the second half layer after a specific layer as an initialization layer. According to this, even if the amount of disaster experience data for each specific mental disorder, such as the possibility of suicide attempt and PTSD, is very insufficient to train the artificial neural network, the artificial neural network can predict the pattern of mental illness of disaster experiencers for general mental disorders such as depression in advance. By taking this into account, the effect of being able to smoothly predict mental illness is generated. In addition, without inserting dummy data into the mental disorder prediction artificial neural network module 12 or performing data processing such as data cloning, the possibility of suicide attempt can be predicted smoothly.

In addition, re-learning of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention is performed on hidden layers other than the input layer and initialization layer of the artificial neural network module 12 for predicting mental illness generated by neural network transition. For this, it can be fixed so that the parameters are not changed by relearning. In certain frameworks you can use trainableParameter=0 or freeze=1. According to this, the effect of learning only the output layer or the latter layer by storing the active value of the fixed layer is generated.

In addition, the re-learning of the artificial neural network module 12 for predicting mental illness according to an embodiment of the present invention is configured such that the hyperparameters of the artificial neural network module 12 for predicting mental illness are adjusted by the upper layer artificial neural network and re-learned. can According to an embodiment of the present invention, the hyperparameters of the mental disorder prediction artificial neural network module 12 adjusted by the upper layer artificial neural network are Parameter Scale, Gradient, Learning rate (learning rate), Learning rate decay (learning rate decomposition), Regularization strength (normalization strength) and the like.

The learning rate adjusted during re-learning according to an embodiment of the present invention may be applied to parameter update during re-learning as shown in Equation 1 below.

In Equation 1 above, W is the initial weight, b is the initial bias, η is the learning rate, L is the loss, and ∂L/∂W and ∂L/∂b are the gradients of the weight and bias, respectively. do.

After all, the upper-layer artificial neural network means a higher-layer artificial neural network that performs automatic tuning for each mental disorder by adjusting and outputting hyperparameters during retraining of the mental disorder prediction artificial neural network module 12 in detail. based on parameters such as the counseling data encoder 10, the activity data encoder 11, the mental disorder prediction artificial neural network module 12, the output depression prediction data 400, and the PTSD prognosis prediction data 500. It can be configured to output hyperparameters. The output depression prediction data 400 can be used to calculate the gradient, weight, loss, etc. of the learned mental disorder prediction artificial neural network module 12 . Including the output depression prediction data 400, the gradient, weight, loss, learning rate, and amount of data of the mental disorder prediction artificial neural network module 12 can be used to train the upper-layer artificial neural network. .

In relation to another embodiment of the present invention, reinforcement learning may be used to predict mental illness of the artificial neural network module 12 for predicting mental illness. 9 is a schematic diagram showing reinforcement learning of the artificial neural network module 12 for predicting mental illness according to another embodiment of the present invention. As shown in FIG. 9, in the case of reinforcement learning of the mental disorder prediction artificial neural network module 12, the counseling encoding vector and activity encoding vector of the mentally ill person are Environment, and the mental disorder prediction artificial neural network module 12 is Agent, mental disorder The mental disorder prediction artificial neural network module 12 can be updated by constructing reinforcement learning in which the prediction of mental illness of the prediction artificial neural network module 12 is composed of Action and the mental illness status of the questionnaire item 300 is composed of Reward. According to reinforcement learning according to an embodiment of the present invention, even when the environment is non-linear, such as the counseling data 100 and activity data 200 of a mentally ill patient, the accuracy of the artificial neural network module 12 for predicting mental illness can be improved. effect occurs.

10 is a flowchart illustrating a method for predicting mental illness using a multimodal artificial neural network according to an embodiment of the present invention. As shown in FIG. 10, the method for predicting mental illness using a multimodal artificial neural network according to an embodiment of the present invention includes a learning step (S10) of learning the apparatus 1 for predicting mental illness using a multimodal artificial neural network. , a new data input step (S11) of inputting data of a new mentally ill patient, and an inference step (S12) of predicting the mental illness of a new mentally ill patient.

The learning step (S10) is a step of learning the mental disorder prediction device 1 using the multimodal artificial neural network by inputting the counseling encoding vector and the activity encoding vector of the existing mentally ill patient. At this time, separate artificial neural network modules are formed for mental disorders such as suicide attempts, PTSD, depression, and anxiety disorders of existing mentally ill patients, and each artificial neural network module is separately learned.

The new data input step (S11) is a step of inputting counseling data and activity data of a new mentally ill patient into the mental disorder prediction apparatus 1 using the multimodal artificial neural network learned in S10.

Inference step (S12), mental disease prediction data (depression prediction data, PTSD prognosis prediction data, etc. ) is inferred (predicted) and outputted.

As described above, those skilled in the art to which the present invention pertains will be able to understand that the present invention can be embodied in other specific forms without changing its technical spirit or essential features. Therefore, the above-described embodiments should be understood as illustrative in all respects and not restrictive. The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts should be construed as being included in the scope of the present invention.

The features and advantages described in this specification are not all inclusive, and many additional features and advantages will become apparent to those skilled in the art, particularly from consideration of the drawings, specification, and claims. Moreover, it should be noted that the language used herein has been chosen primarily for readability and instructional purposes, and may not have been chosen to delineate or limit the subject matter of the invention.

The foregoing description of embodiments of the present invention has been presented for purposes of illustration. It is not intended to limit the invention to the precise form disclosed or to make it without omission. Those skilled in the art can appreciate that many modifications and variations are possible in light of the above disclosure.

Therefore, the scope of the present invention is not limited by the detailed description, but by any claims of the application based thereon. Accordingly, the disclosure of embodiments of the invention is illustrative and not limiting of the scope of the invention set forth in the claims below.

1: Mental disease prediction device using multimodal artificial neural network
10: Activity Data Encoder
11: consultation data encoder
100: consultation data
200: activity data
300: Survey question
400: Depression prediction data
500: PTSD prognosis prediction data

Claims (7)

Artificial intelligence trained to predict the specific mental illness of the new mental illness who has not been diagnosed for the specific mental illness through the counseling data and activity data of the existing mental illness, who is the mental illness diagnosed for the specific mental illness. A memory module for storing program codes of a mental disorder predictive artificial neural network module, which is a neural network; and
a processing module processing the program code of the mental disorder prediction artificial neural network module;
including,
The program code of the mental disorder prediction artificial neural network module,
an input step of inputting the counseling data and the activity data of the new mentally ill person; and
an inference step of inferring and outputting mental disorder prediction data, which is data for prediction of the specific mental disorder of the new mental disorder patient;
It is configured to be performed on a computer, including
Characterized in that the specific mental disorder includes depression of the mentally ill person,
Mental disease prediction device using multimodal artificial neural network.

According to claim 1,
The specific mental disorder includes a plurality of mental disorders including depression of the mentally ill and PTSD prognosis of the mentally ill,
The mental disorder prediction artificial neural network module includes a plurality of artificial neural networks learned for each of the plurality of mental disorders,
In the inference step, inferring and outputting the mental disorder prediction data for each of the plurality of mental disorders of the new mental disorder patient,
Mental disease prediction device using multimodal artificial neural network.
Artificial intelligence trained to predict the specific mental illness of the new mental illness who has not been diagnosed for the specific mental illness through the counseling data and activity data of the existing mental illness, who is the mental illness diagnosed for the specific mental illness. Artificial neural network module for predicting mental illness, which is a neural network;
including,
The mental disorder prediction artificial neural network module receives the counseling data and the activity data of the new mentally ill person, infers and outputs mental disorder prediction data, which is data for prediction of the specific mental disorder of the new mentally ill person,
Characterized in that the specific mental disorder includes depression of the mentally ill person,
Mental disease prediction device using multimodal artificial neural network.
Artificial intelligence trained to predict the specific mental illness of the new mental illness who has not been diagnosed for the specific mental illness through the counseling data and activity data of the existing mental illness, who is the mental illness diagnosed for the specific mental illness. an input step of inputting the counseling data and the activity data of the new mentally ill person to a mental disorder prediction artificial neural network module, which is a neural network; and
an inference step in which the mental disorder prediction artificial neural network module infers and outputs mental disorder prediction data that is data for prediction of the specific mental disorder of the new mental disorder patient;
including,
Characterized in that the specific mental disorder includes depression of the mentally ill person,
A machine learning method for predicting mental illness using multimodal artificial neural networks.
A computer-readable recording medium recording a program for executing the machine learning method for predicting mental illness using the multimodal artificial neural network of claim 4 on a computer.
An application stored in a computer-readable recording medium recording a program for executing the machine learning method for predicting mental illness using the multimodal artificial neural network of claim 4 on a computer.
A program stored in a computer-readable recording medium recording a program for executing the machine learning method for predicting mental illness using the multimodal artificial neural network of claim 4 on a computer.

Images