Abstract: A method predicts an interpretation time for a medical image examination of a subject comprising one or more medical images. A plurality of data inputs is obtained, where the data inputs are associated with the medical image examination or the subject of the medical image examination, and the data points represent parameters affecting the interpretation time. The plurality of data inputs are input to a trained artificial intelligence algorithm, wherein the algorithm automatically provides a predicted interpretation time based on said plurality of data inputs. The predicted interpretation time is output to a clinical management system. A clinical management system incorporating the aforementioned method and a computer program product encoded with the aforementioned method are also provided.

Abstract: A system (100) for context aware medical recommendations includes a recommendation engine (138) and a user interface (122). The recommendation engine (138) identifies at least one suggested recommendation (140) according to a medical guideline and context in response to a first input indicating a finding (150) in a medical image (112) of a patient. The user interface (122) displays on a display device (120) the at least one suggested recommendation selectable as a second input.

Abstract: A system (400) configured to generate an expanded query for an electronic health database, the system comprising: a user interface (410) configured to receive a query comprising a search string and information about a clinical context in which the search is being performed; and a processor (460) comprising: (i) a model creation module (420) configured to generate a clinical information model comprising one or more clinical concepts; (ii) a prioritization module (430) configured to prioritize the one or more clinical concepts identified in the generated clinical information model based on the received information about the clinical context in which the search is being performed and a clinical guideline or management plan for the patient; (iii) a query expansion module (440) configured to create an expanded query using the prioritized clinical concepts; and (iv) a query module (450) configured to query the electronic health database using the expanded query.

Abstract: A system (100) for context aware medical recommendations includes a recommendation engine (138) and a user interface (122). The recommendation engine (138) identifies at least one suggested recommendation (140) according to a medical guideline and context in response to a first input indicating a finding (150) in a medical image (112) of a patient. The user interface (122) displays on a display device (120) the at least one suggested recommendation selectable as a second input.

Abstract: A system (102) includes a digital information repository (106) configured to store information about performances of individuals, including performances of an individual of interest. The system further includes a computing apparatus (103). The computing apparatus includes a memory (110) configured to store instructions for a performance benchmarking engine trained to learn factors of the performances that impact key performance indicators independent of the individuals’ performance. The computing apparatus further includes a processor (108) configured execute the stored instructions for the performance benchmarking engine to determine a key performance indicator of interest for the individual of interest based at least in part on the information in the digital information repository about the performances of the individual of interest and the learned factors that impact the key performance indicator of interest.

Abstract: Techniques disclosed herein relate to generating and applying subject event timelines for various purposes. In various embodiments, data indicative of medical events associated with a subject may be retrieved from various data sources. Each of the medical events may be associated with a respective timestamp. Based on the medical events and associated timestamps, a timeline data structure associated with the subject may be assembled. The timeline data structure may be analyzed to identify inconsistenc(ies) between medical events associated with the subject. A visual timeline indicative of the medical events may be rendered on a display based on the timeline data structure. Each respective medical event may be represented in the visual timeline by a graphical element. Two or more of the graphical elements that are associated with the medical events for which the inconsistenc(ies) were identified may be visually distinguished.

Abstract: The vocabulary of pertinent terms used to highlight/filter medical records in a text annotation system is continually updated based on user feedback. To maximize the effectiveness of this updating, feedback is extracted from all users of the system, thereby providing a ‘group-sourced’ vocabulary of pertinent terms. As each user modifies the provided vocabulary of pertinent terms to customize the text annotation system to conform to the user's preferences, the modifications are collected and communicated to the provider of the vocabulary of pertinent terms. The provider of the vocabulary of pertinent terms assimilates the modifications implemented by each user of the word annotation system to determine whether to modify the vocabulary of pertinent terms for subsequent users of the common vocabulary of pertinent terms.

Abstract: A system and method creates guideline-based summaries for imaging exams. The method includes extracting clinical concepts from a patient medical record to create a patient profile. The method includes identifying an appropriate use criteria based on a current clinical workflow. The method includes generating an appropriate use criteria summary including key elements from the patient profile which are used to determine a recommendation based on the appropriate use criteria. The method includes determining whether a user selected action is in violation of the recommendation.

Abstract: Implementations described herein relate to processing concept-based conflicts, between different instances of clinical data, in response to a user initializing a transfer of previously existing clinical data into a current report. The current report can thereafter be referenced by another user who, as a result of the concept-based conflict check, will be put on notice of conflict(s) between instances of clinical data. Conflicts can be based on criterion corresponding to particular clinical concepts, and a clinical concept can be identified using clinical data that is the subject of transfer to a current report. For instance, natural language processing can be performed on clinical data to identify clinical concepts characterized by the clinical data. In some implementations, criterion can be generated for a clinical concept based on one or more trained machine learning models, which can be trained using medical reference data and/or patient medical records.

Abstract: A system includes a computing system (102) a processor (104) that performs the following: establish syntactic interoperability with a plurality of healthcare data sources (114); extract health care episode concepts from the sources, including concepts from a radiology report; classify the extracted concepts into cognitive classes, wherein the cognitive classes include: observation; evaluation; instruction and action; map the classified concepts to terminologies/ontologies; create a linked list of the events, including observations, evaluations, instructions and actions, to be contextualized; reconstruct the events from the linked list using time and location to order the events in a predetermined way; receive a query, including a unique identifier; for the events; construct, in response to the query, an output in electronical format that includes the events organized according to the cognitive classes and indexed by time from the reconstructed events; and transmit the constructed output via a network to a rem

Abstract: A system (400) configured to generate an expanded query for an electronic health database, the system comprising: a user interface (410) configured to receive a query comprising a search string and information about a clinical context in which the search is being performed; and a processor (460) comprising: (i) a model creation module (420) configured to generate a clinical information model comprising one or more clinical concepts; (ii) a prioritization module (430) configured to prioritize the one or more clinical concepts identified in the generated clinical information model based on the received information about the clinical context in which the search is being performed and a clinical guideline or management plan for the patient; (iii) a query expansion module (440) configured to create an expanded query using the prioritized clinical concepts; and (iv) a query module (450) configured to query the electronic health database using the expanded query.

Abstract: The present disclosure pertains to modeling free-text clinical documents into a hierarchical graph-like data structure based on semantic relationships among clinical concepts present in the documents. A method comprises parsing, identifying, and annotating clinical terms within free-text clinical documents. This is accomplished by storing identified clinical terms in a concept node. The concept node is a data structure that has a set of properties to categorize stored concepts. Clinical concepts of free-text clinical documents are classified into clinical event classes. The free-text clinical documents include clinical terms that were associated with clinical concept categories. Classifying clinical concepts includes organizing clinical text-free documents into sections that describe a specific aspect of the clinical text-free documents that include one or more of clinical, technical, or administrative aspects of the documents.

Abstract: A health care performance assessment apparatus (10) includes at least one processor (16, 20, 22, 24) programmed to: collect information associated with medically-related events from a plurality of databases; group the collected information associated with medically-related events into episode of care (EOC) data structures wherein each EOC data structure contains the collected information for a single EOC treating a medical condition or providing a medical procedure to a single patient; store the EOC data structures in an EOC repository (18); group EOC data structures having a chosen commonality into at least one cohort; and calculate at least one key performance indicators (KPIs) for the cohorts. A display (2) is configured to display the KPIs for at least one selected cohort.

Abstract: System and method for generating structured finding object (“SFO”) description recommendations. The system and method are configured to extract a plurality of first findings for a patient, assemble the first findings into a timeline for the patient, extract a plurality of second findings for a population of patients, determine a set of timelines for the population of patients, and determine conditional probabilities of findings occurring for each of the second findings in the set of timelines. Further, the system and method are configured to display the SFO description recommendations for each of the first findings in the patient's timeline based, at least in part, on the conditional probabilities for the first finding.

Abstract: Techniques disclosed herein relate to generating and applying subject event timelines for various purposes. In various embodiments, data indicative of medical events associated with a subject may be retrieved from various data sources. Each of the medical events may be associated with a respective timestamp. Based on the medical events and associated timestamps, a timeline data structure associated with the subject may be assembled. The timeline data structure may be analyzed to identify inconsistenc(ies) between medical events associated with the subject. A visual timeline indicative of the medical events may be rendered on a display based on the timeline data structure. Each respective medical event may be represented in the visual timeline by a graphical element. Two or more of the graphical elements that are associated with the medical events for which the inconsistenc(ies) were identified may be visually distinguished.

Abstract: Techniques disclosed herein relate to generating and applying subject event timelines for various purposes. In various embodiments, data indicative of a plurality of medical events associated with a subject may be retrieved (502) from data sources (102-110). For example, natural language processing may be performed (504) on a narrative data record to extract concept(s) associated with a first medical event. Each of the plurality of medical events may be associated (508) with a respective timestamp. Based on the plurality of medical events and associated timestamps, a timeline data structure associated with the subject may be assembled (510) and used to render a visual timeline (232) indicative of the plurality of medical events on a display. Each respective medical event of the plurality of medical events may be represented by a graphical element (234) that is operable to cause additional information (236) about the respective medical event to be output.

Abstract: A biopsy reporting system (101) employs a biopsy procedure database (11) and a biopsy reporting controller (102). In operation, the biopsy procedure database (11) stores a biopsy procedure registration and a pathology report. The biopsy procedure registration includes sample tissue data record informative of biopsy extractions of a plurality of biopsy samples from a patient anatomy. The pathology report includes pathological data informative of a pathological diagnosis of each biopsy sample of the plurality of biopsy samples. Responsive to a storage of the biopsy procedure registration and the pathology report within the biopsy procedure database (11), the biopsy reporting controller (102) automatically links the pathology report to the biopsy procedure registration.

Abstract: The present disclosure pertains to modeling free-text clinical documents into a hierarchical graph-like data structure based on semantic relationships among clinical concepts present in the documents. A method comprises parsing, identifying, and annotating clinical terms within free-text clinical documents. This is accomplished by storing identified clinical terms in a concept node. The concept node is a data structure that has a set of properties to categorize stored concepts. Clinical concepts of free-text clinical documents are classified into clinical event classes. The free-text clinical documents include clinical terms that were associated with clinical concept categories. Classifying clinical concepts includes organizing clinical text-free documents into sections that describe a specific aspect of the clinical text-free documents that include one or more of clinical, technical, or administrative aspects of the documents.

Abstract: A system and method for generating a radiological report. The system and method displaying, on a display, an image of a region of interest, determining an image characteristic of the region of interest, determining, via a processor, a recommendation based on the image characteristic, and generating, via the processor, a report including the recommendation.

Abstract: Methods and apparatus for assigning patients to hospital beds to prevent the spread of healthcare-associated infection (HAI). HAI is a major patient safety problem worldwide, affecting hundreds of millions of individuals each year. By considering probabilities that patients will acquire and/or spread infections, embodiments of the present invention can reduce the spread of HAI by selectively assigning patients to beds within healthcare institutions.