International Business Machines Corporation

Other

Merative US L.p.

Yufan Guo

Tanveer Fathima Syeda-Mahmood

Jalal U Mahmud

Rama Kalyani T Akkiraju

Zhe Liu

Tyler Shore Baldwin

Yu Long Cao

David James Beymer

Anbang Xu

Mehdi Moradi

Haibin Liu

Vandana Mukherjee

Yaniv Gur

Mark D Bronkalla

Peifeng Yin

Weber Marett

A system includes a memory having instructions therein and at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to determine a global-level importance magnitude value for a global-level importance of an explainable feature of a machine learning base model based on a first prediction of the machine learning base model. The at least one processor is also configured to execute the instructions to determine a global-level importance direction label for the global-level importance of the explainable feature based on the first prediction. The at least one processor is also configured to execute the instructions to generate a communication for presentation to a user based on a second prediction of the machine learning base model, based on the global-level importance magnitude value, and based on the global-level importance direction label.

Machine learning model error detection

A mechanism is provided for implement a discrepancy detection mechanism for detecting discrepancies between clinical notes and administrative records. Clinical concepts are extracted from the clinical notes and the administrative records in a patient's electronic medical records (EMRs). The extracted clinical concepts are filtered based on semantic type information to identify concepts that reference diseases or syndromes while also removing negated instances. Utilizing the positive mentions of diseases in clinical notes, the positive mentions of diseases or syndromes in the clinical notes are compared against each positive entry in the administrative records. A discrepancy summary is then generated for diseases or syndromes that failed to translate correctly from clinical notes to the administrative records in the patient's EMRs.

Detecting discrepancies between clinical notes and administrative records

Methods and systems of summarizing medical data. One system includes an electronic processor configured to analyze medical data to extract a medical concept and a plurality of additional attributes of the medical concept and store the medical concept and the plurality of additional attributes. The electronic processor is configured to generate a first medical summary associated with the patient, where the first medical summary is based on the stored medical concept and at least a first additional attribute included in the stored plurality of additional attributes. The electronic processor is configured to receive a user interaction with the first medical summary. The electronic processor is configured to generate a second medical summary associated with the patient based on the user interaction, the second medical summary is based on the stored medical concept and at least a second additional attribute included in the stored plurality of additional attributes.

Dynamic medical summary

Embodiments provide a computer implemented method of evaluating one or more IR systems, the method including: providing, by a processor, a pre-indexed knowledge-based document to a pre-trained sentence identification model; identifying, by the sentence identification model, a predetermined number of query-worthy sentences from the pre-indexed knowledge-based document, wherein the query-worthy sentences are ranked based on a prediction probability value of each query-worthy sentence; providing, by the sentence identification model, the query-worthy sentences to a pre-trained query generation model; generating, by the query generation model, a query for each query-worthy sentence; and evaluating, by the processor, the one or more IR systems using the generated queries, wherein one or more searches are performed via the one or more IR systems, and the one or more searches are performed in a set of knowledge-based documents including the pre-indexed knowledge-based document.

Knowledge-based information retrieval system evaluation

A cross-modality neural network transform for semi-automatic medical image annotation is provided. In various embodiments, an input medical image is mapped to a first vector in a text vector space. The first vector corresponds to the features of the medical image. A set of predetermined vectors is searched for a closest one of the predetermined vectors to the first vector. From the closest one of the predetermined vectors, one or more keywords is determined describing the input medical image.

Cross-modality neural network transform for semi-automatic medical image annotation

A system configured to predict fine-grained affective states. The system comprising a processor configured to execute instructions to create training data comprising content conveying emotions, and to create a trained model by performing an emotion vector space model training process using the training data to train a model using a feed forward neural network that converts discrete emotions into emotion vector representations. The system uses the trained model to predict fine-grained affective states for text conveying an emotion.

System for fine-grained affective states understanding and prediction

Negation scope analysis for negation detection is provided. In various embodiments, a phrase is read from a report collection. The phrase is searched for at least one of a predetermined set of negation keywords. A dependency parse tree is generated of the phrase. The dependency parse tree is traversed starting with the at least one of the predetermined set of negation keywords. Based on the traversal, a plurality of words of the phrase are determined that are spanned by the at least one of the predetermined set of negation keywords.

Negation scope analysis for negation detection

Automatic detection of disease presence from combining disease-specific measurements with textual descriptions of disease and its severity in unstructured textual reports is provided. In various embodiments, a knowledge graph of clinical concepts is read. Based on the knowledge graph, a plurality of associations are determined between disease names, symptoms, anatomical abnormalities, and qualifiers. A corpus of clinical reports is read. Based on the plurality of associations, a plurality of portions indicative of a disease condition are located within the corpus of clinical reports. Within each of the plurality of portions, name/value pairs are detected corresponding to measurements indicative of the disease condition. The measurements indicative of the disease condition are extracted.

Automatic disease detection from unstructured textual reports

A computer-implemented method for fine-grained affective states prediction. The computer-implemented method creates training data comprising content conveying emotions. The method creates a trained model by performing an emotion vector space model training process using the training data to train a model using a feed forward neural network that converts discrete emotions into emotion vector representations. The trained model can be used to predict fine-grained affective states for text conveying an emotion.

Method for fine-grained affective states understanding and prediction

A mechanism is provided that implements a cognitive data processing system for automatically processing ambiguously labeled data associated with a medical image. The cognitive data processing system receives an ambiguously labeled set of training data in which the ambiguously labeled set of training data comprises portions of data and associated labels, and wherein at least one portion of data in the ambiguously labeled set of training data has a plurality of different labels that together render the portion of data ambiguously labeled. The cognitive data processing system configures an implementation of a model that comprises a loss term, a maximizing term, and a sparsity term. The cognitive data processing system processes the ambiguously labeled set of training data based on the model to identifying a mapping that minimizes a loss function and thereby train the cognitive data processing system.

Automatic processing of ambiguously labeled data

Local abbreviation expansion is provided through context correlation. In various embodiments, an abbreviation within a phrase is identified. The abbreviation is surrounded by a plurality of words. The words surrounding the abbreviation are provided to a trained neural network. The neural network includes a projection layer adapted to map inputs of the neural network onto a continuous vector space. An expansion is received from the trained neural network. The expansion corresponds to the abbreviation based on the surrounding plurality of words.

Local abbreviation expansion through context correlation

Semi-automatic annotation of medical images is provided. In various embodiments, a classifier is applied to each of a first plurality of medical images to generate a label and an associated confidence value for each of the first plurality of medical images. The classifier is pre-trained using a manually labeled set of medical images. Those of the first plurality of medical images having an associated confidence value below a predetermined threshold are selected. The selected medical images are provided to a user. Updated labels are received from the user for the selected medical images. The classifier is retrained using the first plurality of medical images, with the updated labels for the selected medical images and the generated labels for medical images not selected.

Growing community of inventors

San Jose, CA, United States of America

Yufan Guo