Information technology for healthcare transformation

Abstract

Rising costs, decreasing quality of care, diminishing productivity, and increasing complexity have all contributed to the present state of the healthcare industry. The interactions between payers (e.g., insurance companies and health plans) and providers (e.g., hospitals and laboratories) are growing and are becoming more complicated. The constant upsurge in and enhanced complexity of diagnostic and treatment information has made the clinical decision-making process more difficult. Medical transaction charges are greater than ever. Population-specific financial requirements are increasing the economic burden on the entire system. Medical insurance and identity theft frauds are on the rise. The current lack of comparative cost analytics hampers systematic efficiency. Redundant and unnecessary interventions add to medical expenditures that add no value. Contemporary payment models are antithetic to outcome-driven medicine. The rate of medical errors and mistakes is high. Slow inefficient processes and the lack of best practice support for care delivery do not create productive settings. Information technology has an important role to play in approaching these problems. This paper describes IBM Research's approach to helping address these issues, i.e., the evidence-based healthcare platform.

Patient Similarity via Joint Embeddings of Medical Knowledge Graph and Medical Entity Descriptions

“…With generated representations of each patient, we calculate the similarity score among all patient pairs using two different criteria: hospital readmission rate and incident rate difference for mortality. With the inherent difficulty of measuring the patient similarity, these two criteria are chosen since (1) both hospital readmission rate and incident rate difference for mortality play a significant role in many patient matching applications [52] and (2) they are recorded in most routinely collected data, and hence have a broad prospect of application [53], [54]. Also, we use Rand Index [55] and Normalized Mutual Information [56] to evaluate the patient clustering.…”

Untitled

“… The use of automated tools for evidence generation, distillation, or synthesis (Cohen et al, 2010;Kim, Martinez, Cavedon, & Yencken, 2011),  The integration of evidence across multiple computational sources (O'Sullivan, Wilk, Michalowski, & Farion, 2010),  Decision support for incorporating evidence-based protocols into clinical workflow (El-Kareh, Hasan, & Schiff, 2013;Sim et al, 2001),  Standard clinical vocabularies to ensure understanding among systems (Sim, Sanders, & McDonald, 2002),  Web-based platforms to facilitate physician-patient communication (Swan, 2012), and  The technological bases for institutional learning and improvement (Abernethy et al, 2010;Bigus et al, 2011). Despite the shared interests between the EBHC and HIT communities, there is a fundamental disconnect between the two.…”