Objectives: Electronic health records (EHRs) are only a first step in capturing and utilizing healthrelated data-the challenge is turning that data into useful information. Furthermore, EHRs are increasingly likely to include data relating to patient outcomes, functionality such as clinical decision support, and genetic information as well, and, as such, can be seen as repositories of increasingly valuable information about patients' health conditions and responses to treatment over time.Methods: We describe a case study of 423 patients treated by Centerstone within Tennessee and Indiana in which we utilized electronic health record data to generate predictive algorithms of individual patient treatment response. Multiple models were constructed using predictor variables derived from clinical, financial and geographic data.Results: For the 423 patients, 101 deteriorated, 223 improved and in 99 there was no change in clinical condition. Based on modeling of various clinical indicators at baseline, the highest accuracy in predicting individual patient response ranged from 70% to 72% within the models tested. In terms of individual predictors, the Centerstone Assessment of Recovery Level-Adult (CARLA) baseline score was most significant in predicting outcome over time (odds ratio 4.1 + 2.27). Other variables with consistently significant impact on outcome included payer, diagnostic category, location and provision of case management services.Conclusions: This approach represents a promising avenue toward reducing the current gap between research and practice across healthcare, developing data-driven clinical decision support based on real-world populations, and serving as a component of embedded clinical artificial intelligences that ''learn'' over time.

No abstract

BackgroundThe consumer health technologies used by patients on a daily basis can be effectively leveraged to assist them in the treatment of depression. However, because treatment for depression is a collaborative endeavor, it is important to understand health practitioners’ perspectives on the benefits, drawbacks, and design of such technologies.ObjectiveThe objective of this research was to understand how patients and health practitioners can effectively and successfully influence the design of consumer health treatment technologies for treating patients with depression.MethodsA group of 10 health practitioners participated in individual semistructured contextual interviews at their offices. Health practitioners rated an a priori identified list of depression indicators using a 7-point Likert scale and generated a list of depression indicators. Finally, health practitioners were asked to rate the perceived usefulness of an a priori identified list of depression treatment technologies using a 7-point Likert scale.ResultsOf the 10 health practitioners interviewed, 5 (50%) were mental health practitioners, 3 (30%) nurses, and 2 (20%) general practitioners. A total of 29 unique depression indicators were generated by the health practitioners. These indicators were grouped into 5 high-level categories that were identified by the research team and 2 clinical experts: (1) daily and social functioning, (2) medication, (3) nutrition and physical activity, (4) demographics and environment, and (5) suicidal thoughts. These indicators represent opportunities for designing technologies to support health practitioners who treat patients with depression. The interviews revealed nuances of the different health practitioners’ clinical practices and also barriers to using technology to guide the treatment of depression. These barriers included (1) technology that did not fit within the current practice or work infrastructure, (2) technology that would not benefit the current treatment process, (3) patients forgetting to use the technology, and (4) patients not being able to afford the technology.ConclusionsIn order to be successful in the treatment of depression, consumer health treatment technologies must address health practitioners’ technology concerns early on in the design phase, account for the various types of health practitioners, treatment methods, and clinical practices, and also strive to seamlessly integrate traditional and nontraditional depression indicators within various health practitioners’ clinical practices.