Marissa Burgermaster1, Jung H Son2, Patricia G Davidson3, Arlene M Smaldone4, Gilad Kuperman5, Daniel J Feller2, Katherine Gardner Burt6, Matthew E Levine2, David J Albers7, Chunhua Weng2, Lena Mamykina2. 1. Nutritional Sciences & Population Health, University of Texas at Austin, Austin, TX, USA; Biomedical Informatics, Columbia University, New York, NY, USA. Electronic address: marissa.burgermaster@austin.utexas.edu. 2. Biomedical Informatics, Columbia University, New York, NY, USA. 3. Nutrition, West Chester University, West Chester, PA, USA. 4. School of Nursing & College of Dental Medicine, Columbia University, New York, NY, USA. 5. Biomedical Informatics, Columbia University, New York, NY, USA; Memorial Sloan Kettering Cancer Center, New York, NY, USA. 6. Health Sciences, Lehman College, Bronx, NY, USA. 7. Biomedical Informatics, Columbia University, New York, NY, USA; Pediatrics & Informatics, University of Colorado, Aurora, CO, USA.
Abstract
INTRODUCTION: Self-monitoring technologies produce patient-generated data that could be leveraged to personalize nutritional goal setting to improve population health; however, most computational approaches are limited when applied to individual-level personalization with sparse and irregular self-monitoring data. We applied informatics methods from expert suggestion systems to a challenging clinical problem: generating personalized nutrition goals from patient-generated diet and blood glucose data. MATERIALS AND METHODS: We applied qualitative process coding and decision tree modeling to understand how registered dietitians translate patient-generated data into recommendations for dietary self-management of diabetes (i.e., knowledge model). We encoded this process in a set of functions that take diet and blood glucose data as an input and output diet recommendations (i.e., inference engine). Dietitians assessed face validity. Using four patient datasets, we compared our inference engine's output to clinical narratives and gold standards developed by expert clinicians. RESULTS: To dietitians, the knowledge model represented how recommendations from patient data are made. Inference engine recommendations were 63 % consistent with the gold standard (range = 42 %-75 %) and 74 % consistent with narrative clinical observations (range = 63 %-83 %). DISCUSSION: Qualitative modeling and automating how dietitians reason over patient data resulted in a knowledge model representing clinical knowledge. However, our knowledge model was less consistent with gold standard than narrative clinical recommendations, raising questions about how best to evaluate approaches that integrate patient-generated data with expert knowledge. CONCLUSION: New informatics approaches that integrate data-driven methods with expert decision making for personalized goal setting, such as the knowledge base and inference engine presented here, demonstrate the potential to extend the reach of patient-generated data by synthesizing it with clinical knowledge. However, important questions remain about the strengths and weaknesses of computer algorithms developed to discern signal from patient-generated data compared to human experts.
INTRODUCTION: Self-monitoring technologies produce patient-generated data that could be leveraged to personalize nutritional goal setting to improve population health; however, most computational approaches are limited when applied to individual-level personalization with sparse and irregular self-monitoring data. We applied informatics methods from expert suggestion systems to a challenging clinical problem: generating personalized nutrition goals from patient-generated diet and blood glucose data. MATERIALS AND METHODS: We applied qualitative process coding and decision tree modeling to understand how registered dietitians translate patient-generated data into recommendations for dietary self-management of diabetes (i.e., knowledge model). We encoded this process in a set of functions that take diet and blood glucose data as an input and output diet recommendations (i.e., inference engine). Dietitians assessed face validity. Using four patient datasets, we compared our inference engine's output to clinical narratives and gold standards developed by expert clinicians. RESULTS: To dietitians, the knowledge model represented how recommendations from patient data are made. Inference engine recommendations were 63 % consistent with the gold standard (range = 42 %-75 %) and 74 % consistent with narrative clinical observations (range = 63 %-83 %). DISCUSSION: Qualitative modeling and automating how dietitians reason over patient data resulted in a knowledge model representing clinical knowledge. However, our knowledge model was less consistent with gold standard than narrative clinical recommendations, raising questions about how best to evaluate approaches that integrate patient-generated data with expert knowledge. CONCLUSION: New informatics approaches that integrate data-driven methods with expert decision making for personalized goal setting, such as the knowledge base and inference engine presented here, demonstrate the potential to extend the reach of patient-generated data by synthesizing it with clinical knowledge. However, important questions remain about the strengths and weaknesses of computer algorithms developed to discern signal from patient-generated data compared to human experts.
Authors: Heather J Cole-Lewis; Arlene M Smaldone; Patricia R Davidson; Rita Kukafka; Jonathan N Tobin; Andrea Cassells; Elizabeth D Mynatt; George Hripcsak; Lena Mamykina Journal: Int J Med Inform Date: 2015-08-08 Impact factor: 4.046
Authors: Rachel L Richesson; W Ed Hammond; Meredith Nahm; Douglas Wixted; Gregory E Simon; Jennifer G Robinson; Alan E Bauck; Denise Cifelli; Michelle M Smerek; John Dickerson; Reesa L Laws; Rosemary A Madigan; Shelley A Rusincovitch; Cynthia Kluchar; Robert M Califf Journal: J Am Med Inform Assoc Date: 2013-08-16 Impact factor: 4.497
Authors: Thomas H Payne; Sarah Corley; Theresa A Cullen; Tejal K Gandhi; Linda Harrington; Gilad J Kuperman; John E Mattison; David P McCallie; Clement J McDonald; Paul C Tang; William M Tierney; Charlotte Weaver; Charlene R Weir; Michael H Zaroukian Journal: J Am Med Inform Assoc Date: 2015-05-28 Impact factor: 4.497
Authors: K Clarke; R O'Moore; R Smeets; J Talmon; J Brender; P McNair; P Nykanen; J Grimson; B Barber Journal: Artif Intell Med Date: 1994-04 Impact factor: 5.326
Authors: Pavel S Roshanov; Natasha Fernandes; Jeff M Wilczynski; Brian J Hemens; John J You; Steven M Handler; Robby Nieuwlaat; Nathan M Souza; Joseph Beyene; Harriette G C Van Spall; Amit X Garg; R Brian Haynes Journal: BMJ Date: 2013-02-14
Authors: Paul C Tang; J Marc Overhage; Albert Solomon Chan; Nancy L Brown; Bahar Aghighi; Martin P Entwistle; Siu Lui Hui; Shauna M Hyde; Linda H Klieman; Charlotte J Mitchell; Anthony J Perkins; Lubna S Qureshi; Tanya A Waltimyer; Leigha J Winters; Charles Y Young Journal: J Am Med Inform Assoc Date: 2012-11-20 Impact factor: 4.497