Collapsing clinical event data into meaningful states of patient care

Abstract

Techniques are described herein for collapsing clinical event data into meaningful states of patient care. In various embodiments, time-ordered streams of clinical data associated with a plurality ofrespective patients may be divided (402) into one or more respective pluralities of temporal segments. Each stream of clinical data may indicate a clinical history of a particular patient of the plurality of patients. Each of the one or more pluralities of temporal segments may have a different duration. In some embodiments, embedding(s) of the one or more pluralities of temporal segments into reduced dimensionality space(s) may be generated (404). Process mining may be performed (408) on the embedding(s). Based on the process mining, one or more temporal health trajectories shared among the plurality of patients may be identified (410).

Description

[0001] Cross References to Related Applications [0002] This application claims priority to US Provisional Patent Application US 62 / 548478, filed August 22, 2017, the entire disclosure of which is hereby incorporated by reference for all purposes. technical field [0003] Various embodiments described herein relate generally to artificial intelligence. More specifically, but not exclusively, various methods and apparatus disclosed herein relate to collapsing clinical event data into meaningful patient care states. Background technique [0004] Diagnosis of a clinical condition is a difficult task that often requires extensive medical investigation. After observing several variables (eg, a patient's past medical history, current condition, and various clinical measures), clinicians perform complex cognitive processes to infer a possible diagnosis. By automatically generating information about the current patient state, the most likely diagnostic options for optimal clinica...

AI Technical Summary

Problems solved by technology

All this noise can make process mining difficult

Deep learning methods may create consistent, clean stages of care progression from this data, but tools derived for NLP are not well suited for time-ordered (e.g. streaming) logs of clinical events

Images