A method and a system are provided for processing electronic medical records for predicting a health condition of a patient. The method may determine a first set of datasets of a first patient based on one or more first electronic medical records. The method may extract one or more second sets of datasets of one or more second patients from a database server based on the first set of datasets. The method may generate one or more bipartite graphs based on the first set of datasets and the one or more second sets of datasets. The method may determine a set of edges from the one or more edges based on a matching score in each bipartite graph. The method may further predict the health condition of the first patient based on at least the matching score associated with each of the one or more bipartite graphs.

Systems and methods to improve the optical character recognition of records, and in particular health records, are provided. An image of a medical record is received, and an initial optical image recognition (OCR) on the image is performed to identify text information. The OCR signal quality may be measured, and areas of insufficient OCR signal quality may be isolated. The signal quality is determined by a weighted average of semantic analysis of the resulting text, and/or OCR accuracy measures. The OCR process may be repeated on the isolated regions of lower signal quality, each time using a different OCR transform, until all regions are completed with a desired degree of signal quality (accuracy). All the regions of the document may then be recompiled into a single document for outputting.

Systems and methods are disclosed for question generation to obtain more related medical information based on observed symptoms from a patient. In embodiments, possible diseases associated with the observed symptoms are generated by querying a knowledge graph. In embodiments, candidate symptoms associated with the possible diseases are also identified and are combined with the observed symptoms to obtain combined symptom sets. In embodiments, discriminative scores for the candidate symptom sets are determined and candidate symptoms with top discriminative scores are selected. In embodiments, these selected candidate symptoms may be checked for conflicts with observed symptoms and removed from further consideration if a conflict exists. In embodiments, one or more questions may be generated based on the remaining selected candidate systems to aid in collecting information about the patient. In embodiments, the process may be repeated with the updated observed symptoms.

Systems and methods for enabling construction of complex Boolean chemical substructure queries in a structured graphical user interface are provided. The chemical substructures (molecules) may be represented graphically in standard molecular notation, and may be arranged horizontally and vertically on the interface, along with Boolean logical operators. Boolean logical operators of a first type may logically associate molecules arranged in horizontal fashion to form row queries, whereas Boolean logical operators of a different, second type may logically associate the row queries to form a composite query to be applied to a database of molecules. The operators of the first type may comprise disjunctive operators, whereas the operators of the second type may comprise conjunctive operators.

A system for identifying records that likely include information about new records or individuals includes a candidate component, a relationship component, and a marking component. The candidate component is configured to obtain information about a candidate record that includes information matching information of a target record. The target record is stored in a database that includes a plurality of records and relationships between the records. The relationship component is configured to determine that the candidate record includes a greater number of hierarchal relationships of a specific relationship type than the target record. The marking component is configured to mark one or more of the candidate record and the target record for review to indicate that a potentially new record or individual for the database has been identified.

Systems and devices for regulation of self-management of a medication schedule are provided. A system can include a pill dispenser cap, a plurality of insulating layers; a near field communication (NFC) tag, and a pill dispenser. The system can further include a graphical user interface (GUI), and first and second mobile devices each having a display unit, a sensor, a processor, and a computer readable medium.

Example embodiments of a system, apparatus, and method are disclosed for determining eligibility of a prescription for a discount benefit program from one or more electronic prescription data streams. The embodiments may specify at least one eligibility check on the one or more electronic prescription data streams for confirming whether the covered entity is eligible to replenish dispensed medication under a drug discount program, and process prescription data associated with medication that has been dispensed. The example embodiments may include applying the at least one eligibility check to the electronic prescription data to generate an eligibility determination indicating whether the covered entity is eligible to replenish the dispensed medication under the drug discount program, and, in response to the eligibility determination indicating that the covered entity is eligible, automatically ordering replenishment of the medication and causing physical delivery of the ordered medication.

Systems and methods to automatically generate classifiers are provided. A labeled dataset is initially received. The dataset may be for a positive class, or may be a negative for a class, or a false positive class. N features that are predictive for the class (or false positive or the negative class) are identified. These features are combined within a classifier dictionary. Medical records received may be processed in order to be machine readable. Features within the medical records are identified and are compared against the dictionary of classifiers. Matches indicate classes within the medical record. The classifier dictionary may be periodically updated in response to insufficient classification accuracy, or when new data becomes available.

Disclosed is a registry system, including member institutions, in which transfusion donors and recipients are registered following genotyping, which would typically take place in a member institution, or a member institution would have access to the genotyping information, if performed outside. The registry database can be accessed and searched by members seeking samples of particular type(s). Systems are disclosed for maintaining economic viability of genotyping in connection with transfusions, by maximizing the number of units placed with the minimal number of candidate donors typed. Genotyping of potential donors, and product supply, is matched to forecasted demand. Genotyping can also be limited to the more clinically relevant markers. The registry system can also be integrated with one format of assay which generates an image for analysis, whereby the imaged results can be analyzed and redacted by experts in a central location, and then transmitted back to the patient or their representative.

A method and kit related thereto are described for the collection and maintenance of detectability of a plurality of species of microbiological agents in a single clinical sample as well as an integral method for handling a plurality of the samples and managing information associated therewith for reporting a sum of diagnostic results for each sample.