Download PDF
CC BY-NC-ND 4.0 · Methods Inf Med 2021; 60(S 01): e32-e43
DOI: 10.1055/s-0041-1728757
Original Article

Leveraging Artificial Intelligence to Improve Chronic Disease Care: Methods and Application to Pharmacotherapy Decision Support for Type-2 Diabetes Mellitus

Shinji Tarumi
1   Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
,
Wataru Takeuchi
1   Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
,
George Chalkidis
1   Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
,
Salvador Rodriguez-Loya
2   Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
,
Junichi Kuwata
3   Department of Product Design, Center for Social Innovation, Hitachi Ltd., Kokubunji, Tokyo, Japan
,
Michael Flynn
4   Departments of Internal Medicine and Pediatrics, University of Utah, Salt Lake City, Utah, United States
,
Kyle M. Turner
5   Department of Pharmacotherapy, University of Utah, Salt Lake City, Utah, United States
,
Farrant H. Sakaguchi
6   Department of Family and Preventive Medicine, University of Utah, Salt Lake City, Utah, United States
,
Charlene Weir
2   Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
,
Heidi Kramer
2   Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
,
David E. Shields
2   Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
,
Phillip B. Warner
2   Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
,
Polina Kukhareva
2   Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
,
Hideyuki Ban
1   Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
,
Kensaku Kawamoto
2   Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
› Author Affiliations Funding This work was supported by Hitachi, Ltd.
› Further Information
   Permissions and Reprints

Abstract

Objectives Artificial intelligence (AI), including predictive analytics, has great potential to improve the care of common chronic conditions with high morbidity and mortality. However, there are still many challenges to achieving this vision. The goal of this project was to develop and apply methods for enhancing chronic disease care using AI.

Methods Using a dataset of 27,904 patients with diabetes, an analytical method was developed and validated for generating a treatment pathway graph which consists of models that predict the likelihood of alternate treatment strategies achieving care goals. An AI-driven clinical decision support system (CDSS) integrated with the electronic health record (EHR) was developed by encapsulating the prediction models in an OpenCDS Web service module and delivering the model outputs through a SMART on FHIR (Substitutable Medical Applications and Reusable Technologies on Fast Healthcare Interoperability Resources) web-based dashboard. This CDSS enables clinicians and patients to review relevant patient parameters, select treatment goals, and review alternate treatment strategies based on prediction results.

Results The proposed analytical method outperformed previous machine-learning algorithms on prediction accuracy. The CDSS was successfully integrated with the Epic EHR at the University of Utah.

Conclusion A predictive analytics-based CDSS was developed and successfully integrated with the EHR through standards-based interoperability frameworks. The approach used could potentially be applied to many other chronic conditions to bring AI-driven CDSS to the point of care.

Keywords

artificial intelligence - clinical decision support system - health information technology - disease management - chronic disease

Supplementary Material



Publication History

Received: 10 December 2020

Accepted: 21 February 2021

Article published online:
11 May 2021

© 2021. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/)

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Contreras I, Vehi J. Artificial intelligence for diabetes management and decision support: literature review. J Med Internet Res 2018; 20 (05) e10775
    CrossrefPubMedGoogle Scholar
  • 2 Rigla M, García-Sáez G, Pons B, Hernando ME. artificial intelligence methodologies and their application to diabetes. J Diabetes Sci Technol 2018; 12 (02) 303-310
    CrossrefPubMedGoogle Scholar
  • 3 Battineni G, Sagaro GG, Chinatalapudi N, Amenta F. Applications of machine learning predictive models in the chronic disease diagnosis. J Pers Med 2020; 10 (02) E21
    CrossrefPubMedGoogle Scholar
  • 4 Polat H, Danaei Mehr H, Cetin A. Diagnosis of chronic kidney disease based on support vector machine by feature selection methods. J Med Syst 2017; 41 (04) 55
    CrossrefPubMedGoogle Scholar
  • 5 Mcheick H, Saleh L, Ajami H, Mili H. Context relevant prediction model for COPD domain using Bayesian belief network. Sensors (Basel) 2017; 17 (07) 1486
    CrossrefPubMedGoogle Scholar
  • 6 Jain D, Singh V. Feature selection and classification systems for chronic disease prediction: a review. Egypt Inform J 2018; 19 (03) 179-189
    CrossrefPubMedGoogle Scholar
  • 7 Huang GM, Huang KY, Lee TY, Weng J. An interpretable rule-based diagnostic classification of diabetic nephropathy among type 2 diabetes patients. BMC Bioinformatics 2015; 16 01, Suppl 1): S5
    CrossrefPubMedGoogle Scholar
  • 8 Contreras I, Quirós C, Giménez M, Conget I, Vehi J. Profiling intra-patient type I diabetes behaviors. Comput Methods Programs Biomed 2016; 136: 131-141
    CrossrefPubMedGoogle Scholar
  • 9 Dagliati A, Marini S, Sacchi L. et al. Machine learning methods to predict diabetes complications. J Diabetes Sci Technol 2018; 12 (02) 295-302
    CrossrefPubMedGoogle Scholar
  • 10 Debon R, Coleone JD, Bellei EA, De Marchi ACB. Mobile health applications for chronic diseases: a systematic review of features for lifestyle improvement. Diabetes Metab Syndr 2019; 13 (04) 2507-2512
    CrossrefPubMedGoogle Scholar
  • 11 Sanchez-Morillo D, Fernandez-Granero MA, Leon-Jimenez A. Use of predictive algorithms in-home monitoring of chronic obstructive pulmonary disease and asthma: a systematic review. Chron Respir Dis 2016; 13 (03) 264-283
    CrossrefPubMedGoogle Scholar
  • 12 Forlenza GP, Li Z, Buckingham BA. et al. Predictive low-glucose suspend reduces hypoglycemia in adults, adolescents, and children with type 1 diabetes in an at-home randomized crossover study: results of the PROLOG trial. Diabetes Care 2018; 41 (10) 2155-2161
    CrossrefPubMedGoogle Scholar
  • 13 Miller DD, Brown EW. Artificial intelligence in medical practice: the question to the answer?. Am J Med 2018; 131 (02) 129-133
    CrossrefPubMedGoogle Scholar
  • 14 Montani S, Striani M. Artificial intelligence in clinical decision support: a focused literature survey. Yearb Med Inform 2019; 28 (01) 120-127
    Article in Thieme ConnectPubMedGoogle Scholar
  • 15 Lourdusamy R, Mattam XJ. Clinical decision support systems and predictive analytics. In: Jain V, Chatterjee JM. eds. Machine Learning with Health Care Perspective. Cham: Springer; 2020: 317-355
    Google Scholar
  • 16 O'Connor PJ, Sperl-Hillen JM, Fazio CJ, Averbeck BM, Rank BH, Margolis KL. Outpatient diabetes clinical decision support: current status and future directions. Diabet Med 2016; 33 (06) 734-741
    CrossrefPubMedGoogle Scholar
  • 17 Bertsimas D, Kallus N, Weinstein AM, Zhuo YD. Personalized diabetes management using electronic medical records. Diabetes Care 2017; 40 (02) 210-217
    CrossrefPubMedGoogle Scholar
  • 18 Wang Y, Li PF, Tian Y, Ren JJ, Li JS. A shared decision-making system for diabetes medication choice utilizing electronic health record data. IEEE J Biomed Health Inform 2017; 21 (05) 1280-1287
    CrossrefPubMedGoogle Scholar
  • 19 Segagni D, Sacchi L, Dagliati A. et al. Improving clinical decisions on T2DM patients integrating clinical, administrative and environmental data. Stud Health Technol Inform 2015; 216: 682-686
    PubMedGoogle Scholar
  • 20 Dagliati A, Sacchi L, Tibollo V. et al. A dashboard-based system for supporting diabetes care. J Am Med Inform Assoc 2018; 25 (05) 538-547
    CrossrefPubMedGoogle Scholar
  • 21 Curran RL, Kukhareva PV, Taft T. et al. Integrated displays to improve chronic disease management in ambulatory care: a SMART on FHIR application informed by mixed-methods user testing. J Am Med Inform Assoc 2020; 27 (08) 1225-1234
    CrossrefPubMedGoogle Scholar
  • 22 Breiman L. Random forests. Mach Learn 2001; 45 (01) 5-32
    CrossrefPubMedGoogle Scholar
  • 23 Friedman J. Greedy function approximation: a gradient boosting machine. Ann Stat 2000; 29: 1189-1232
    PubMedGoogle Scholar
  • 24 Fang G, Annis IE, Elston-Lafata J, Cykert S. Applying machine learning to predict real-world individual treatment effects: insights from a virtual patient cohort. J Am Med Inform Assoc 2019; 26 (10) 977-988
    CrossrefPubMedGoogle Scholar
  • 25 American Diabetes Association. Standards of medical care in diabetes—2018. Diabetes Care 2018; 41 (Suppl. 01) S1-S2
    CrossrefPubMedGoogle Scholar
  • 26 Edelman SV, Polonsky WH. Type 2 diabetes in the real world: the elusive nature of glycemic control. Diabetes Care 2017; 40 (11) 1425-1432
    CrossrefPubMedGoogle Scholar
  • 27 Khunti K, Gomes MB, Pocock S. et al. Therapeutic inertia in the treatment of hyperglycaemia in patients with type 2 diabetes: a systematic review. Diabetes Obes Metab 2018; 20 (02) 427-437
    CrossrefPubMedGoogle Scholar
  • 28 Stark Casagrande S, Fradkin JE, Saydah SH, Rust KF, Cowie CC. The prevalence of meeting A1C, blood pressure, and LDL goals among people with diabetes, 1988-2010. Diabetes Care 2013; 36 (08) 2271-2279
    CrossrefPubMedGoogle Scholar
  • 29 Kirkman MS, Rowan-Martin MT, Levin R. et al. Determinants of adherence to diabetes medications: findings from a large pharmacy claims database. Diabetes Care 2015; 38 (04) 604-609
    CrossrefPubMedGoogle Scholar
  • 30 Okemah J, Peng J, Quiñones M. Addressing clinical inertia in type 2 diabetes mellitus: a review. Adv Ther 2018; 35 (11) 1735-1745
    CrossrefPubMedGoogle Scholar
  • 31 Reach G, Pechtner V, Gentilella R, Corcos A, Ceriello A. Clinical inertia and its impact on treatment intensification in people with type 2 diabetes mellitus. Diabetes Metab 2017; 43 (06) 501-511
    CrossrefPubMedGoogle Scholar
  • 32 Strain WD, Blüher M, Paldánius P. Clinical inertia in individualising care for diabetes: is there time to do more in type 2 diabetes?. Diabetes Ther 2014; 5 (02) 347-354
    CrossrefPubMedGoogle Scholar
  • 33 Khunti K, Millar-Jones D. Clinical inertia to insulin initiation and intensification in the UK: a focused literature review. Prim Care Diabetes 2017; 11 (01) 3-12
    CrossrefPubMedGoogle Scholar
  • 34 Künzel SR, Sekhon JS, Bickel PJ, Yu B. Metalearners for estimating heterogeneous treatment effects using machine learning. Proc Natl Acad Sci U S A 2019; 116 (10) 4156-4165
    CrossrefPubMedGoogle Scholar
  • 35 Athey S, Imbens G. Recursive partitioning for heterogeneous causal effects. Proc Natl Acad Sci U S A 2016; 113 (27) 7353-7360
    CrossrefPubMedGoogle Scholar
  • 36 HCUP. HCUP User Support. Accessed October 2020 at: https://www.hcup-us.ahrq.gov/
    PubMedGoogle Scholar
  • 37 Drucker H, Burges CJC, Kaufman L, Smola A, Vapnik V. Support vector regression machines. Adv Neural Inf Process Syst 1997; 9: 155-161
    PubMedGoogle Scholar
  • 38 Cox DR. The regression analysis of binary sequences (with discussion). J R Stat Soc B 1958; 20: 215-242
    CrossrefPubMedGoogle Scholar
  • 39 Gummesson A, Nyman E, Knutsson M, Karpefors M. Effect of weight reduction on glycated haemoglobin in weight loss trials in patients with type 2 diabetes. Diabetes Obes Metab 2017; 19 (09) 1295-1305
    CrossrefPubMedGoogle Scholar
  • 40 Brier GW. Verification of forecasts expressed in terms of probability. Mon Weather Rev 1950; 78: 1-3
    CrossrefPubMedGoogle Scholar
  • 41 Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classifiers 1999; 10 (03) 61-74
    PubMedGoogle Scholar
  • 42 HL7 FHIR. Welcome to FHIR®. Accessed December 2020 at: https://www.hl7.org/fhir/
    PubMedGoogle Scholar
  • 43 Mandel JC, Kreda DA, Mandl KD, Kohane IS, Ramoni RB. SMART on FHIR: a standards-based, interoperable apps platform for electronic health records. J Am Med Inform Assoc 2016; 23 (05) 899-908
    CrossrefPubMedGoogle Scholar
  • 44 Mandl KD, Mandel JC, Murphy SN. et al. The SMART platform: early experience enabling substitutable applications for electronic health records. J Am Med Inform Assoc 2012; 19 (04) 597-603
    CrossrefPubMedGoogle Scholar
  • 45 Ratpack. Accessed December 2020 at: https://ratpack.io/
    PubMedGoogle Scholar
  • 46 Flask. Users Guide. Accessed December 2020 at: http://flask.pocoo.org/
    PubMedGoogle Scholar
  • 47 Hooks CDS. . Accessed December 2020 at: https://cds-hooks.hl7.org/
    PubMed
  • 48 OpenCDS. . Accessed December 2020 at: http://www.opencds.org/
    PubMed
  • 49 HAPI-FHIR. Global Good: Powering Interoperability Around the World for 18 Years. Accessed December 2020 at: http://hapifhir.io/
    PubMedGoogle Scholar
  • 50 The Centers for Medicare & Medicaid Services. Data.CMS.GOV. Accessed December 2020 at: https://data.cms.gov/
    PubMedGoogle Scholar
  • 51 Rosenbaum PR, Rubin DB. The central role of the propensity score in observational studies for causal effects. Biometrika 1983; 70: 41-55
    CrossrefPubMedGoogle Scholar