International Business Machines Corporation

Ching-Huei Tsou

Murthy V Devarakonda

Anca Sailer

Kenneth James Barker

Bharath Dandala

Ananya Aniruddha Poddar

Keerthana Boloor

Diwakar Mahajan

Dongyang Zhang

Eric William Brown

Aisha Walcott

Eric W Brown

Piyush Madan

Maria Eleftheriou

Divya Pathak

Michal Rosen-Zvi

Safa Messaoud

Parthasarathy Suryanarayanan

Systems, devices, computer-implemented methods, and/or computer program products that facilitate artificial intelligence (AI)-assisted curation of non-pharmaceutical intervention (NPI) data from heterogeneous data sources. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise an extraction component and a change detection component. The extraction component can extract candidate non-pharmaceutical intervention (NPI) events from data associated with a defined disease. The change detection component can evaluate the candidate NPI events for inclusion in a dataset storing NPI events in a defined format.

Artificial intelligence-assisted non-pharmaceutical intervention data curation

A mechanism is provided in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to specifically configure the processor to implement a repetitive portion identification and weighting engine. A machine learning model is trained for weighting repetitive portions of patient electronic medical records (EMRs). A repetitive portion identification component applies a plurality of templates to clinical notes of a patient EMR to identify one or more candidate portions that match at least one of the plurality of templates. A content analysis component performs content analysis on the one or more candidate portions to determine whether each given candidate portion is relevant. A weighting component assigns a relative weight to each given candidate portion based on relevance. A cognitive summary graphical user interface (GUI) generation component generates cognitive summary reflecting at least a subset of the one or more candidate portions of the patient EMR. The mechanism outputs the cognitive summary in a GUI to a user.

Identifying repetitive portions of clinical notes and generating summaries pertinent to treatment of a patient based on the identified repetitive portions

Methods, devices, and systems (for outputting a case summary) receive an electronic medical record (EMR) (and generally electronic records) for the medical patient, extract medical data from the EMR, provide a list of medical problems relevant to the EMR, identifying relations between the medical problems and the medical data using a question-answering (QA) system, and output the clinical summary for the EMR. The clinical summary comprises the list of medical problems, the medical data, and the relations.

Electronic medical record summary and presentation

Text data including at least named entities can be received. From the named entities, continuous entities, overlapping entities and disjoint entities can be identified. The overlapping entities can be transformed into continuous entities. The continuous entities, the transformed entities and the disjoint entities can be encoded. The encoded entities can be input to a machine learning language model to train the machine learning model to predict candidate entities. The predicted entities can be decoded to reconstruct the predicted entities.

Lightweight tagging for disjoint entities

Automatic determination of underlying reasons for lack of treatment adherence is provided. In various embodiments, patient information for a patient is retrieved. The patient information comprises a treatment plan. A failure of compliance with the treatment plan by the patient is determined from the patient information. The failure of compliance and the patient information are evaluated to determine one or more potential cause of the failure of compliance. The one or more potential cause is provided to a user for review.

Automatic determination of underlying reasons for patient failures to adhere to patient care plans

Embodiments of the invention include methods, systems, and computer program products for generating a medical problem list. A non-limiting example of the method includes receiving, by a processor, a plurality of disease categories. A disease category set that includes a plurality of top level disease categories is defined using the processor, wherein the disease category set is based at least in part upon the plurality of disease categories. The processor is used to extract a plurality of candidate training problems from an electronic patient record training set. The processor is used to assign each of the candidate training problems to the plurality of top level disease categories. The processor is used to generate a disease category model for each of the top level disease categories from the electronic patient record training set using a machine learning technique.

Medical record problem list generation

The present invention embodiments are directed to methods, systems, and computer programs for identifying relations, within at least one taxonomy, between taxonomy categories and concepts extracted from electronic content. The relations represent semantic similarities for the concepts. The concepts are clustered based on the identified relations within the at least one taxonomy.

Clinically relevant medical concept clustering

Methods, devices, and systems (for outputting a case summary) receive an electronic medical record (EMR) for the medical patient, extract medical data from the EMR, provide a list of medical problems relevant to the EMR, identifying relations between the medical problems and the medical data using a question-answering (QA) system, and output the clinical summary for the EMR. The clinical summary comprises the list of medical problems, the medical data, and the relations.

Methods, systems, and devices map data of an electronic medical record to standardized medical concepts. The standardized medical concepts are defined by medical industry standards organizations. The methods, systems, and devices identify medical problem concepts, from the standardized medical concepts, generate feature values of the medical problem concepts based on features within the mapped standardized medical concepts, and weight the medical problem concepts based on the feature values according to a weighting function. These methods, systems, and devices identify medical problems as ones of the medical problem concepts that have a weighted score above a threshold, according to the weighting, and output a list of the medical problems.

Growing community of inventors

Briarcliff Manor, NY, United States of America

Ching-Huei Tsou