Abstract: A method for creating and searching medical ontologies includes providing a semi-structured information source comprising a plurality of articles linked to each other, each article having one or more sections and each article is associated with a concept, creating a directed unlabeled graph representative of the information source, providing a plurality of labels, labeling a subset of edges, and assigning each unlabeled edge an equal probability of being assigned one of the labels. For each node, the probability of each outgoing edge is updated by smoothing each probability by an overall probability distribution of labels over all outgoing edges of each node, and the probability of each incoming edge is updated the same way. A label with a maximum probability is assigned to an edge if said maximum probability is greater than a predetermined threshold to create a labeled graph.

Abstract: A method for training classifiers for ICD-9 patient codes includes providing a set of documents regarding patient hospital visits, combining the documents for each patient visit to create a hospital visit profile, defining a feature as an ngram with a frequency of occurrence greater or equal to a predetermined value that does not appear in a standard list of ngrams, processing the profiles to remove redundancy at a paragraph level and perform tokenization and sentence splitting, performing feature selection, randomly dividing the documents into training, validation, and test sets, and training a set of binary classifiers using a weighted ridge regression, each binary classifier targeting a single ICD-9 code using the training set, wherein each classifier is adapted to determining a specific ICD-9 code by analyzing a patient's hospital records.

Abstract: Medical or other data is de-identified by obfuscation. Located instances are replaced. By replacing with values in a same format and level of generality, multiple possible identifications—the replacement values and the instances not located—are provided in the data, obfuscating the original identification. By replacing as a function of a probability, the resulting data set has different instances distributed in a way making identification of the actual or original instances not located by searching more difficult.

Abstract: Members of a medical entity class are extracted from patient data. A semi-supervised approach uses one or more initial medical terms such as terms from an ontology, for a given category or medical canonical entity. A larger set of medical terms is extracted from the medical information. In one example, the extraction is performed using lexical surface form features, rather than syntactical parsing.

Abstract: A method for interpreting date information from unstructured text includes performing phrase tokenization on the unstructured text to identify one or more temporal phrases. Word categorization is performed on the one or more temporal phrases to categorize one or more words of each temporal phrase. Grammar analysis is performed to match each temporal phrase to an understood syntax using the categorizations of the words of each temporal phrase. Each temporal phrase is interpreted based on the matched syntax.

Abstract: A method and system for determining patient states is provided. The method includes the steps of data mining a patient record using a domain knowledge base relating to a disease of interest; inputting the mined data into a model of the disease of interest; and determining a state of the patient based on the model. The system includes a data miner for mining information from a patient record using a domain knowledge base relating to a disease of interest; and a processor for creating a patient model of the disease of interest, processing the mined data in the model to determine a current state of the patient and future states for different courses of treatment, and recommending a therapy based on the determined future state.

Abstract: Systems and methods for automated processing of medical information in electronic patient medical record databases, wherein billing information (e.g., diagnosis codes, procedural codes) is automatically extracted from electronic patient medical records through comprehensive analysis of clinical information included in the patient medical records using a knowledge base of domain-specific criteria. The extracted billing information can be automatically processed for purposes of, e.g., medical claims correction, medical claims billing, quality assurance of recorded billing information, or claim reimbursement tracking.

Abstract: A technique is provided for automatically generating performance measurement information. At least some of the obtained performance measurement information may be derived from unstructured data sources, such as free text physician notes, medical images, and waveforms. The performance measurement may be sent to a health care accreditation organization. The health care accreditation organization can use the performance measurement to evaluate a health care provider for its quality of patient care. Alternatively, performance measurement information can be provided directly to consumers.

Abstract: A method and system for determining patient states is provided. The method includes the steps of data mining a patient record using a domain knowledge base relating to a disease of interest; inputting the mined data into a model of the disease of interest; and determining a state of the patient based on the model. The system includes a data miner for mining information from a patient record using a domain knowledge base relating to a disease of interest; and a processor for creating a patient model of the disease of interest, processing the mined data in the model to determine a current state of the patient and future states for different courses of treatment, and recommending a therapy based on the determined future state.

Abstract: The present invention provides a graphical user interface for presentation, exploration and verification of patient information. In various embodiments, a method is provided for browsing mined patient information. The method includes selecting patient information to view, at least some of the patient information being probabilistic, presenting the selected patient information on a screen, the selected patient information including links to related information. The selected patient information may include elements, factoids, and/or conclusions. The selected patient information may include an element linked to unstructured information. For example, an element linked to a note with highlighted information may be presented. Additionally, the unstructured information may include medical images and waveform information.

Abstract: The present invention provides a data mining framework for mining high-quality structured clinical information. The data mining framework includes a data miner that mines medical information from a computerized patient record (CPR) based on domain-specific knowledge contained in a knowledge base. The data miner includes components for extracting information from the CPR, combining all available evidence in a principled fashion over time, and drawing inferences from this combination process. The mined medical information is stored in a structured CPR which can be a data warehouse.