Abstract: A sentence classification apparatus, a sentence classification method, and a sentence classification program that can appropriately classify sentences by adjusting parameters are provided. The sentence classification apparatus includes: a case sentence obtention unit for obtaining plural case sentences which are associated with effect values that are values obtained by evaluating effects; a case value creation unit for creating case values obtained by numerizing the case sentences for each of parameters with different values; a correlation coefficient calculation unit for calculating a correlation coefficient between the case values and the effect values for each of the values of the parameters; and a parameter selection unit for selecting a parameter among the parameters with different values on the basis of the correlation coefficient.

Abstract: A sentence classification apparatus, a sentence classification method, and a sentence classification program that can appropriately classify sentences by adjusting parameters are provided. The sentence classification apparatus includes: a case sentence obtention unit for obtaining plural case sentences which are associated with effect values that are values obtained by evaluating effects; a case value creation unit for creating case values obtained by numerizing the case sentences for each of parameters with different values; a correlation coefficient calculation unit for calculating a correlation coefficient between the case values and the effect values for each of the values of the parameters; and a parameter selection unit for selecting a parameter among the parameters with different values on the basis of the correlation coefficient.

Abstract: In screening of documents based on a similarity between keywords, it is difficult to exclude documents having similar background but different conclusions. In a document review assistance method executed by a computer system, a storage unit stores data on a plurality of documents, and the document review assistance method includes: a step of creating, by a control unit, a sentence vector based on a sentence included in the plurality of documents; a step of classifying, by the control unit, the plurality of documents into a plurality of clusters based on the created sentence vector; a step of specifying, by the control unit, a subgraph on a network of a word in a first document set included in at least one of the clusters; and a step of controlling, by the control unit, the creation of the sentence vector based on the specified subgraph.

Abstract: A computer system calculates an execution probability of a cell therapy using therapy result data, generate a second model by incorporating an evaluation model for evaluating deterioration over time of a stored cells into a first model, the first model is a model for calculating a success probability of the cell therapy, executes a simulation of estimating a profit of a business operator due to success of the cell therapy by varying a storage period of the cells in a storage facility and a payment amount of the business operator to the storage facility using the execution probability of the cell therapy and the second model, and calculates an optimum storage period and an optimum payment amount that maximize the profit of the business operator based on the result of the simulation.

Abstract: To infer a value of an assignment variable with high accuracy. In a causal relation inference device including a processor configured to execute a program and a storage device storing the program, the processor is configured to execute a first calculation process of calculating an internal vector based on a feature vector of a plurality of samples and a first learning parameter, a second calculation process of calculating a reallocation vector based on a second learning parameter and the internal vector calculated by the first calculation process, and a third calculation process of calculating a pointwise weight vector for each of the plurality of samples based on a third learning parameter and the reallocation vector calculated by the second calculation process.

Abstract: A device that holds a medical dictionary indicating medical concepts, drug information, medical care information and documents indicating a medical concept not included in the medical care information, identifies from the documents, for each combination of a medical concept not included in the medical care information and a drug included in the drug information, a document indicating the medical concept and the drug. The device generates a medical concept list including the medical concept indicated by the medical dictionary included in each identified document and determines, based on a probability of each medical concept not included in the medical care information appearing in a context of the document indicated by the medical concept list, from among the medical concepts not included in the medical care information, a medical concept having an influence on a prescription of the drug included in the drug information.

Abstract: A multistage inference system includes a causality expression storage unit that stores a plurality of sentences including a pair of a phrase representing a cause and a phrase representing an effect, and a scenario reliability calculator that calculates a score for evaluating causality chain possibility among the sentences. The score is calculated based on type identity of documents including the sentences or information on authors of the documents.

Abstract: A medical information processing device holds: a medical dictionary indicating medical concepts; drug information; medical care information; and documents indicating a medical concept not included in the medical care information, identifies from the documents, for each combination of a medical concept not included in the medical care information and a drug included in the drug information, a document indicating the medical concept and the drug; generates, for each combination, a medical concept list including the medical concept indicated by the medical dictionary included in each identified document; and determines, based on a probability of each medical concept not included in the medical care information appearing in a context of the document indicated by the medical concept list, from among the medical concepts not included in the medical care information, a first medical concept having an influence on a prescription of the drug included in the drug information.

Abstract: It becomes possible to implement a route search fast, and furthermore routes whose meanings are easy to understand are searched for by linking routes on the basis of relations with similar backgrounds. A provided relevance analyzing device includes a control section and a database. The database stores: node data about nodes on a network representing relevance between a plurality of events, and edge data about edges representing interrelationships between the events. The control section includes: an inter-edge background similarity computing section that computes a similarity between documents corresponding to two edges by using the node data and edge data stored in the database; and a route computing section that computes routes with high similarities as routes on the network.

Abstract: A sentence classification apparatus, a sentence classification method, and a sentence classification program that can appropriately classify sentences by adjusting parameters are provided. The sentence classification apparatus includes: a case sentence obtention unit for obtaining plural case sentences which are associated with effect values that are values obtained by evaluating effects; a case value creation unit for creating case values obtained by numerizing the case sentences for each of parameters with different values; a correlation coefficient calculation unit for calculating a correlation coefficient between the case values and the effect values for each of the values of the parameters; and a parameter selection unit for selecting a parameter among the parameters with different values on the basis of the correlation coefficient.

Abstract: It is provided a clinical test support system, comprising an arithmetic unit and a storage device coupled to the arithmetic unit, and a visit plan preparation unit to prepare a visit plan for the execution facility of a clinical development monitor; and a prediction unit to calculate the evaluation index of the visit plan. The storage device stores evaluation index information including the record of information for the evaluation of the visit plan and a risk evaluation model including the record of the risk evaluation result of each execution facility. The prediction unit calculates an evaluation index used to execute the visit plan prepared by the visit plan preparation unit by referring to the evaluation index information and the risk evaluation model; and output a visit plan selected based on the evaluation index.

Abstract: The task is to provide a system which supports smooth patient referral from a referral source medical institution to a referral destination medical institution and which particularly prevents readmission due to cases that are difficult to determine simply based on patient attributes or due to the quality of medical services. To achieve this task, a referral difficult degree calculation unit calculates a referral difficulty degree which quantifies the risk that a patient cannot be discharged because a referral destination cannot be found, in consideration of a readmission risk calculated by a readmission risk calculation unit, the geographical distance between the patient and the referral destination medical institution, the total number of patients accepted, and the number of beds available. This referral difficulty degree is outputted to an output unit of the referral source medical institution or the referral destination medical institution.

Abstract: Provided is a trial planning support apparatus, including a processor and a storage unit, wherein the storage unit stores therein data of a plurality of documents about clinical trials implemented in the past, and wherein the processor is configured to receive information about a clinical trial, and search the plurality of documents for a plurality of sentences relevant to the received information, classify the plurality of sentences that have been found by the search into a plurality of clusters based on a degree of similarity, and output information about the sentences classified into clusters.

Abstract: Provided is a training data creation method includes a step to create a training set that includes, as an index term for extracting a document used for learning, one or more of the index terms assigned to applicable documents or non-applicable documents, a step to create the document identification model that learns the document data assigned the index term included in the training set, and create an evaluation value by using the created document identification model to identify prescribed evaluation data, a step to determine whether to use each index term included in the training set for creating the training data on the basis of the evaluation value, and a step to create the training data by adding document data that is assigned an index term determined to be appropriate for use in creating the training data.

Abstract: A processor is configured to: acquire clinical information containing cases each indicating a disease of a patient and a medical care event performed on the patient; acquire literature information containing literature indicating a name of the disease and a word indicating the medical care event; calculate a frequency of one case indicating a combination of a plurality of diseases based on the clinical information; analyze the literature information using each of the name of the disease and the word indicating the medical care event; acquire a criterion for determining a disease for which the medical care event has been performed; acquire first relevance information indicating whether the medical care event has been performed for the disease based on the analysis result, the calculated frequency and the acquired criterion; and generate medical information indicating a relationship between the medical care event and the disease based on the first relevance information.

Abstract: Upon evaluation of a value of a diagnostic process, the value of a diagnostic process is evaluated not based on a simple cost but on a cost required for all processes of a patient who was in the diagnostic process through a follow-up survey. Diagnostic processes that are not relevant to a target diagnostic process are eliminated, clustering is performed on patients to divide the patients into clinically meaningful homogeneous groups, and the target diagnostic process is evaluated for each of the homogeneous groups. For the purpose, importance scores of data pieces of the clinical data are calculated and the relevant data is output using the output result of the medical knowledge extraction unit, clustering is performed on patients in the clinical data, and a clinical index and a cost are output for each of the clusters.

Abstract: A system for retrieving an encrypted graph, in which a first computer generates an encrypted graph, and a second computer retrieves the encrypted graph, wherein: the first computer generates a secret key, encrypts a graph that includes a start point, an edge, and an end point to generate an encrypted graph, generates an encryption query, transmits encrypted graph data in which the encrypted graph and the encryption query are correlated for each edge and a searchable encryption matching function to the second computer, generates an encrypted graph retrieval query in which a graph to be retrieved is encrypted by the retrievable cryptogram query function, and transmits the generated retrieval query to the second computer; and the second computer, accepts the received encrypted graph retrieval query and encrypted graph data as inputs, and executes a retrieval process using the searchable encryption matching function.

Abstract: A processor is configured to; acquire clinical information containing cases each indicating a disease of a patient and a medical care event performed on the patient; acquire literature information containing literature indicating a name of the disease and a word indicating the medical care event; calculate a frequency of one case indicating a combination of a plurality of diseases based on the clinical information; analyze the literature information using each of the name of the disease and the word indicating the medical care event; acquire a criterion for determining a disease for which the medical care event has been performed; acquire first relevance information indicating whether the medical care event has been performed for the disease based on the analysis result, the calculated frequency and the acquired criterion; and generate medical information indicating a relationship between the medical care event and the disease based on the first relevance information.

Abstract: A medical care data retrieval system includes a storage device including a medical care data database in which medical care contents for symptoms of patients are stored and a medical care pattern database in which relations between the symptoms and the medical care contents are stored and a graph processing unit that creates, on the basis of the medical care data database and the medical care pattern database, a graph including a root node representing the symptom, at least one intermediate node representing a name of the medical care content, and at least one leaf node representing a reference number of the medical care content. When there are a plurality of the graphs concerning a certain symptom, the graph processing unit integrates redundant portions of the intermediate node among the plurality of graphs.