Vol. 23 No. Special Issue 3 (2024): Mapana - Journal of Sciences
Research Articles

Effectiveness of Machine Learning Models and Performance Enhancement with Threshold Tuning Method Adopted in Diabetes Prediction

PDF
  • Priyabrata Sahu,
  • Jibendu Kumar Mantri
Priyabrata Sahu
Research Scholar, P G Department of Computer Application, MSCBD, University, Odisha
DOI: https://doi.org/10.12723/mjs.sp3.2

Published 2024-11-06

Keywords

  • diabetes care,
  • artificial intelligence,
  • retinal imaging,
  • glucose monitoring

Copyright (c) 2024

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Abstract

Using machine learning algorithms to predict diabetes has been the focus of extensive research by a few researchers. The objective of this paper is to provide PWDs, clinicians, family members, and carers with a better understanding of the possible uses of current AI advancements in the treatment of PWDs. Millions of PWD could benefit from the enhanced blood glucose management, lower frequency of hypoglycemic episodes, and decreased risk of diabetes-related comorbidities that could be facilitated by AI applications. AI applications enhance the lives of people with disabilities (PWDs), by enhancing accuracy, efficiency, usability, and satisfaction. In this study, the performance metrics of the top three machine learning models currently available are compared. Four out of the five parameters analyzed, the KNN model fared the best. KNN is superior in terms of accuracy, area under the curve (AUC), precision, and f1 score. Logistic Regression achieves the optimal Recall/Sensitivity of 93%.

PDF

References

  1. . International Diabetes Federation (IDF). IDF diabetes atlas,7th edition. Brussels, Belgium: International Diabetes Federation, 2015.
  2. . Centres for Disease Control and Prevention. Estimates of diabetes and its burden in the United States. Washington, DC: US Department of Health and Human Services, 2017: 1–20.
  3. . Lewis K. “Humans and systems: creating natural interfaces to augment human ability”. https://www.ibm.com/blogs/internetof- things/creating-natural-interfaces/ Accessed July 18, 2018.
  4. . Yeung S, Downing NL, Fei-Fei L, Milstein A.,” Bedside computer vision—moving artificial intelligence from driver assistance to patient safety”. N Engl J Med 2018;378:1271– 1273.
  5. . Young K. “Newly approved software uses AI to improve diabetic retinopathy”. https://www.jwatch.org/fw114063/2018/ 04/12/newly- approved-software-uses-ai-detect-diabetic Accessed July 18, 2018.
  6. . “Turing Archive for the History of Computing”. www
  7. .alanturing.net/turing_archive/archive/index/archive index .html Accessed July 18, 2018.
  8. . Pfaffl MW. “A new mathematical model for relative quantification in real-time RT-PCR”. Nucleic Acids Res 2001;29: 45e.
  9. . Lo´pez B,Martin C,Vin˜as PH. Special section on artificial intelligence for diabetes. ArtifIntell Med2018;85:27-28.
  10. . Vijan S, Hofer TP, Hayward RA. “Cost-utility analysis of screening intervals for diabetic retinopathy in patients with type 2 diabetes mellitus”. JAMA 2000;283:889–896.
  11. . Gulshan V, Peng L, Coram M, et al. “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs”. JAMA 2016;316:2402–2410.
  12. . “US Food and Drug Administration. FDA permits marketing of artificial intelligence-based device to detect certain diabetes-related eye problems”. https://www.fda.gov/ News Events/Newsroom/Press Announcements/ucm604357 .htm Accessed July 18, 2018.
  13. . Keel S, Lee PY, Scheetz J, et al. “Feasibility and patient acceptability of a novel artificial intelligence-based screening model for diabetic retinopathy at endocrinology outpatient services: a pilot study. Sci Rep 2018;8:4330.
  14. . Shankaracharya, Odedra D, Samanta S, Vidyarthi AS.”Computational intelligence-based diagnosis tool for the detection of prediabetes and type 2 diabetes in India”. Rev Diabetes Stud 2012;9:55–62.
  15. . Corey KE, Kartoun U, Zheng H, Shaw SY. “Development and validation of an algorithm to identify non-alcoholic fatty liver disease in the electronic medical record”. Dig Dis Sci 2016;61:913–919.
  16. . Vyas R, Bapat S, Jain E, Karthikeyan M, Tambe S, Kulkarni BD. “Building, and analysis of protein-protein interactions related to diabetes mellitus using support vector machine, biomedical text mining and network analysis”. Comput Biol Chem 2016;65:37–44.
  17. . Lo´pez B, Torrent-Fontbona F, Vin˜as R, Ferna´ndez-Real JM. “Single nucleotide polymorphism relevance learning with random forests for type 2 diabetes risk prediction”. Artif Intell Med 2018;85:43–49.
  18. . Shu T, Zhang B, Yan Tang Y. “An extensive analysis of various texture feature extractors to detect diabetes mellitus using facial specific regions”. Comput Biol Med 2017;83: 69–83.
  19. . Katigari MR, Ayatollahi H, Malek M, Haghighi MK. “Fuzzy expert system for diagnosing diabetic neuropathy”. World J Diabetes 2017;8:80–88.
  20. . Wang L, Pedersen PC, Agu E, Strong DiM, Tulu B. “Area determination of diabetic foot ulcer images using a cascaded two-wtage SVM-based classification.” IEEE Trans Biomed Eng 2017;64:2098–2109.
  21. . Mauseth R, Lord SM, Hirsch IB, Kircher RC, Matheson DP, “Greenbaum CJ. Stress testing of an artificial pancreas system with pizza and exercise leads to improvements in the system’s fuzzy logic controller”. J Diabetes Sci Technol 2015;9:1253–1259.
  22. . Ling SH, Nguyen HT. “Natural occurrence of nocturnalhypoglycemia detection using hybrid particle swarm optimized fuzzy reasoning model”. Artif Intell Med 2012;55: 177–184.
  23. . Herrero P, Pesl P, Reddy M, Oliver N, Georgiou P, Toumazou C. “Advanced insulin bolus advisor based on run-torun control and case- based reasoning”. IEEE J Biomed Health Inform 2015;19:1087–1096.
  24. . DeJournett L, DeJournett J. “In silico testing of an artificial intelligence-based artificial pancreas designed for use in the intensive care unit setting”. J Diabetes Sci Technol 2016;10: 1360–1371.
  25. . Cvetkovic´ B, Janko V, Romero AE, Kafalı O¨ , Stathis K, Lusˇtrek
  26. M. “Activity recognition for diabetic patients using a smartphone”. J Med Syst 2016;40:256.
  27. . Wang L, Pedersen PC, Strong DM, Tulu B, Agu E, IgnotzR. “Smartphone-based wound assessment system for patients with diabetes”. IEEE Trans Biomed Eng 2015;62:477– 488.
  28. . Rigla M, Martı´nez-Sarriegui I, Garcı´a-Sa´ez G, Pons B, Hernando ME. Gestational diabetes management using smart mobile telemedicine. J Diabetes Sci Technol 2018; 12:260–264.
  29. . ClinicalTrails.gov. “Adult accuracy study of the Elite 3 Glucose Sensor” (E3). https://www.clinicaltrials.gov/ct2/show/study/NCT02246582?term= NCT02246582&rank=1& sect=X0123456 Accessed July 18, 2018.
  30. . Neemuchwala H. Sugar.”IQ improves time-in-range by36mins/day, time >180 by 30mins/day, time <70 by 6mins/ day”. Presented at: American Diabetes Association 78th Scientific Session, June 22–26, 2018, Orlando, FL.
  31. . Hutson TM. “Missing data hinder replication of artificial intelligence studies”. www.sciencemag.org/news/2018/02/ missing-data-hinder- replication-artificial-intelligence-studies? Accessed July 18, 2018.
  32. . Benson T. “Principles of health interoperability” HL7 and SNOMED, 2nd edition. London: Springer Verlag, 2012.