Carbohydrate Counting App Using Image Recognition for Youth With Type 1 Diabetes: Pilot Randomized Control Trial

Jeffrey E Alfonsi, Elizabeth E Y Choi, Taha Arshad, Stacie-Ann S Sammott, Vanita Pais, Cynthia Nguyen, Bryan R Maguire, Jennifer N Stinson, Mark R Palmert, Jeffrey E Alfonsi, Elizabeth E Y Choi, Taha Arshad, Stacie-Ann S Sammott, Vanita Pais, Cynthia Nguyen, Bryan R Maguire, Jennifer N Stinson, Mark R Palmert

Abstract

Background: Carbohydrate counting is an important component of diabetes management, but it is challenging, often performed inaccurately, and can be a barrier to optimal diabetes management. iSpy is a novel mobile app that leverages machine learning to allow food identification through images and that was designed to assist youth with type 1 diabetes in counting carbohydrates.

Objective: Our objective was to test the app's usability and potential impact on carbohydrate counting accuracy.

Methods: Iterative usability testing (3 cycles) was conducted involving a total of 16 individuals aged 8.5-17.0 years with type 1 diabetes. Participants were provided a mobile device and asked to complete tasks using iSpy app features while thinking aloud. Errors were noted, acceptability was assessed, and refinement and retesting were performed across cycles. Subsequently, iSpy was evaluated in a pilot randomized controlled trial with 22 iSpy users and 22 usual care controls aged 10-17 years. Primary outcome was change in carbohydrate counting ability over 3 months. Secondary outcomes included levels of engagement and acceptability. Change in HbA1c level was also assessed.

Results: Use of iSpy was associated with improved carbohydrate counting accuracy (total grams per meal, P=.008), reduced frequency of individual counting errors greater than 10 g (P=.047), and lower HbA1c levels (P=.03). Qualitative interviews and acceptability scale scores were positive. No major technical challenges were identified. Moreover, 43% (9/21) of iSpy participants were still engaged, with usage at least once every 2 weeks, at the end of the study.

Conclusions: Our results provide evidence of efficacy and high acceptability of a novel carbohydrate counting app, supporting the advancement of digital health apps for diabetes care among youth with type 1 diabetes. Further testing is needed, but iSpy may be a useful adjunct to traditional diabetes management.

Trial registration: ClinicalTrials.gov NCT04354142; https://ichgcp.net/clinical-trials-registry/NCT04354142.

Keywords: carbohydrate counting; digital health applications (apps); image recognition; mHealth; type 1 diabetes; youth.

Conflict of interest statement

Conflicts of Interest: EEYC and JEA are the inventors of iSpy and currently own rights to its intellectual property; thus, it is feasible that they could benefit financially should iSpy become a commercial product. This conflict was acknowledged and included in relevant study documentation. Moreover, the duality of interest was mitigated by having data collection and entry conducted by 2 individuals (S-ASS, TA) with no conflicts of interest and who are independent from the inventors. Data analysis was conducted by an independent, institution-based statistician (BRM), also without conflict. The remaining authors declare no conflict of interest.

©Jeffrey E Alfonsi, Elizabeth E Y Choi, Taha Arshad, Stacie-Ann S Sammott, Vanita Pais, Cynthia Nguyen, Bryan R Maguire, Jennifer N Stinson, Mark R Palmert. Originally published in JMIR mHealth and uHealth (http://mhealth.jmir.org), 28.10.2020.

Figures

Figure 1
Figure 1
Usability testing errors per cycle representing tasks completed during each cycle of usability testing. The total number of tasks varied per cycle (cycle 1: 222; cycle 2: 157; cycle 3: 224).
Figure 2
Figure 2
Participant flowchart.
Figure 3
Figure 3
Engagement levels with the number of participants in each category displayed for each time frame.

References

    1. Chapter 5: Diabetes in Canada: facts and figures from a public health perspective – youth and children. Government of Canada Public Health Agency of Canada. [2020-04-27]. .
    1. Canadian Diabetes Association Clinical Practice Guidelines Expert Committee. Cheng AYY. Canadian Diabetes Association 2013 clinical practice guidelines for the prevention and management of diabetes in Canada. Introduction. Can J Diabetes. 2013 Apr;37 Suppl 1:S1–3. doi: 10.1016/j.jcjd.2013.01.009.
    1. Gökşen Damla, Atik Altınok Y, Ozen S, Demir G, Darcan S. Effects of carbohydrate counting method on metabolic control in children with type 1 diabetes mellitus. J Clin Res Pediatr Endocrinol. 2014;6(2):74–8. doi: 10.4274/Jcrpe.1191. doi: 10.4274/Jcrpe.1191.
    1. Brazeau AS, Mircescu H, Desjardins K, Leroux C, Strychar I, Ekoé J M, Rabasa-Lhoret R. Carbohydrate counting accuracy and blood glucose variability in adults with type 1 diabetes. Diabetes Res Clin Pract. 2013 Jan;99(1):19–23. doi: 10.1016/j.diabres.2012.10.024.
    1. Mehta SN, Quinn N, Volkening LK, Laffel LMB. Impact of carbohydrate counting on glycemic control in children with type 1 diabetes. Diabetes Care. 2009 Jun;32(6):1014–6. doi: 10.2337/dc08-2068.
    1. Bell KJ, Barclay AW, Petocz P, Colagiuri S, Brand-Miller JC. Efficacy of carbohydrate counting in type 1 diabetes: a systematic review and meta-analysis. Lancet Diabetes Endocrinol. 2014 Mar;2(2):133–40. doi: 10.1016/S2213-8587(13)70144-X.
    1. Ahola AJ, Mäkimattila Sari, Saraheimo M, Mikkilä Vera, Forsblom C, Freese R, Groop P, FinnDIANE Study Group Many patients with Type 1 diabetes estimate their prandial insulin need inappropriately. J Diabetes. 2010 Sep;2(3):194–202. doi: 10.1111/j.1753-0407.2010.00086.x. doi: 10.1111/j.1753-0407.2010.00086.x.
    1. Bishop FK, Maahs DM, Spiegel G, Owen D, Klingensmith GJ, Bortsov A, Thomas J, Mayer-Davis EJ. The Carbohydrate Counting in Adolescents With Type 1 Diabetes (CCAT) Study. Diabetes Spectrum. 2009 Jan 01;22(1):56–62. doi: 10.2337/diaspect.22.1.56.
    1. Lancaster BM, Pfeffer B, McElligott M, Ferguson AT, Miller M, Wallace D, Lane JT. Assessing treatment barriers in young adults with type 1 diabetes. Diabetes Res Clin Pract. 2010 Dec;90(3):243–9. doi: 10.1016/j.diabres.2010.07.003.
    1. White RO, Wolff K, Cavanaugh KL, Rothman R. Addressing health literacy and numeracy to improve diabetes education and care. Diabetes Spectr. 2010 Oct 02;23(4):238–243. doi: 10.2337/diaspect.23.4.238.
    1. Eng DS, Lee JM. The promise and peril of mobile health applications for diabetes and endocrinology. Pediatr Diabetes. 2013 Jun 30;14(4):231–8. doi: 10.1111/pedi.12034.
    1. Danaher BG, Seeley JR. Methodological issues in research on web-based behavioral interventions. Ann Behav Med. 2009 Aug;38(1):28–39. doi: 10.1007/s12160-009-9129-0.
    1. Campbell M, Fitzpatrick R, Haines A, Kinmonth AL, Sandercock P, Spiegelhalter D, Tyrer P. Framework for design and evaluation of complex interventions to improve health. BMJ. 2000 Sep 16;321(7262):694–6. doi: 10.1136/bmj.321.7262.694.
    1. Rockett HR, Breitenbach M, Frazier AL, Witschi J, Wolf AM, Field AE, Colditz GA. Validation of a youth/adolescent food frequency questionnaire. Prev Med. 1997;26(6):808–16. doi: 10.1006/pmed.1997.0200.
    1. Smart CE, King BR, McElduff P, Collins CE. In children using intensive insulin therapy, a 20-g variation in carbohydrate amount significantly impacts on postprandial glycaemia. Diabet Med. 2012 Jul;29(7):e21–4. doi: 10.1111/j.1464-5491.2012.03595.x.
    1. Diabetes Canada Clinical Practice Guidelines Expert Committee . Definition, classification and diagnosis of diabetes, prediabetes and metabolic syndrome. In: Sellers Elizabeth., editor. Diabetes Canada 2018 Clinical Practice Guidelines for the Prevention and Management of Diabetes in Canada. Winnipeg: Canadian Journal of Diabetes; 2018. Apr, pp. S10–S15.
    1. . U.S. General Services Administration Technology Transformation Services; [2020-04-25]. Usability testing. .
    1. Pais V, Patel BP, Ghayoori S, Hamilton JK. Counting carbs to be in charge: a comparison of an internet-based education module with in-class education in adolescents with type 1 diabetes. Clinical Diabetes. 2020 Oct; (forthcoming)
    1. National database for standard reference release 28. The United States Department of Agriculture. [2018-03-01]. .
    1. Canadian nutrient file. Government of Canada. [2018-03-01]. .
    1. Koontz MB, Cuttler L, Palmert MR, O'Riordan M, Borawski EA, McConnell J, Kern EO. Development and validation of a questionnaire to assess carbohydrate and insulin-dosing knowledge in youth with type 1 diabetes. Diabetes Care. 2010 Mar;33(3):457–62. doi: 10.2337/dc09-0390.
    1. Ingersoll GM, Marrero DG. A modified quality-of-life measure for youths: psychometric properties. Diabetes Educ. 1991;17(2):114–8. doi: 10.1177/014572179101700219.
    1. Skinner TC, Hoey H, McGee HM, Skovlund SE, Hvidøre Study Group on Childhood Diabetes A short form of the Diabetes Quality of Life for Youth questionnaire: exploratory and confirmatory analysis in a sample of 2,077 young people with type 1 diabetes mellitus. Diabetologia. 2006 Apr;49(4):621–8. doi: 10.1007/s00125-005-0124-0.
    1. La Greca AM, Swales T, Klemp S, Madigan S. Self care behaviors among adolescents with diabetes. Ninth Annual Sessions of the Society of Behavioural Medicine; April 27-30, 1988; Boston, MA. 1988. Apr 30, p. A42.
    1. Greco P, La Greca AM, Ireland A, Wick P, Freeman C, Agramonte R. Assessing adherence in IDDM: A comparison of two methods. Miami, FL: Diabetes 40(Suppl 1); 1990. p. A165.
    1. Lewin AB, LaGreca AM, Geffken GR, Williams LB, Duke DC, Storch EA, Silverstein JH. Validity and reliability of an adolescent and parent rating scale of type 1 diabetes adherence behaviors: the Self-Care Inventory (SCI) J Pediatr Psychol. 2009 Oct;34(9):999–1007. doi: 10.1093/jpepsy/jsp032.
    1. Wu W, Johnson R, Schepp KG, Berry DL. Electronic self-report symptom and quality of life for adolescent patients with cancer: a feasibility study. Cancer Nurs. 2011;34(6):479–86. doi: 10.1097/NCC.0b013e31820a5bdd.
    1. Goyal S, Nunn CA, Rotondi M, Couperthwaite AB, Reiser S, Simone A, Katzman DK, Cafazzo JA, Palmert MR. A mobile app for the self-management of type 1 diabetes among adolescents: a randomized controlled trial. JMIR Mhealth Uhealth. 2017 Jun 19;5(6):e82. doi: 10.2196/mhealth.7336.
    1. Cafazzo JA, Casselman M, Hamming N, Katzman DK, Palmert MR. Design of an mHealth app for the self-management of adolescent type 1 diabetes: a pilot study. J Med Internet Res. 2012;14(3):e70. doi: 10.2196/jmir.2058.
    1. Veazie S, Winchell K, Gilbert J, Paynter R, Ivlev I, Eden K, Nussbaum K, Weiskopf N, Guise J, Helfand M. AHRQ Comparative Effectiveness Technical Briefs. Rockville, Maryland: Agency for Healthcare Research and Quality; 2018. May, [2020-09-30]. Mobile Applications for Self-Management of Diabetes. .
    1. Tascini G, Berioli MG, Cerquiglini L, Santi E, Mancini G, Rogari F, Toni G, Esposito S. Carbohydrate counting in children and adolescents with type 1 diabetes. Nutrients. 2018 Jan 22;10(1) doi: 10.3390/nu10010109.
    1. Gokosmanoglu F, Onmez A. Influence of flexible insulin dosing with carbohydrate counting method on metabolic and clinical parameters in type 1 diabetes patients. Open Access Maced J Med Sci. 2018 Aug 20;6(8):1431–1434. doi: 10.3889/oamjms.2018.256. doi: 10.3889/oamjms.2018.256.
    1. Yamada E, Okada S, Nakajima Y, Bastie CC, Tagaya Y, Osaki A, Shimoda Y, Shibusawa R, Saito T, Ozawa A, Yamada M. Effect of carbohydrate counting using bolus calculators on glycemic control in type 1 diabetes patients during continuous subcutaneous insulin infusion. J Diabetes Investig. 2017 Jul;8(4):496–500. doi: 10.1111/jdi.12604. doi: 10.1111/jdi.12604.
    1. Smart CE, Ross K, Edge JA, Collins CE, Colyvas K, King BR. Children and adolescents on intensive insulin therapy maintain postprandial glycaemic control without precise carbohydrate counting. Diabet Med. 2009 Mar;26(3):279–85. doi: 10.1111/j.1464-5491.2009.02669.x.
    1. Fallaize R, Zenun Franco R, Pasang J, Hwang F, Lovegrove JA. Popular nutrition-related mobile apps: an agreement assessment against a UK reference method. JMIR Mhealth Uhealth. 2019 Feb 20;7(2):e9838. doi: 10.2196/mhealth.9838.
    1. Fadhil A. Cornell University: Computer Science - Computers and Society. Ithaca, New York: Cornell University; 2019. Apr 17, [2020-09-30]. Comparison of Self-monitoring Feedback Data from Electronic Food and Nutrition Tracking Tools. .
    1. Franco RZ, Fallaize R, Lovegrove JA, Hwang F. Popular nutrition-related mobile apps: a feature assessment. JMIR Mhealth Uhealth. 2016 Aug 01;4(3):e85. doi: 10.2196/mhealth.5846.
    1. Skrøvseth Stein Olav, Årsand Eirik, Godtliebsen F, Joakimsen RM. Data-driven personalized feedback to patients with type 1 diabetes: a randomized trial. Diabetes Technol Ther. 2015 Jul;17(7):482–9. doi: 10.1089/dia.2014.0276.
    1. Jeffrey B, Bagala M, Creighton A, Leavey T, Nicholls S, Wood C, Longman J, Barker J, Pit S. Mobile phone applications and their use in the self-management of Type 2 Diabetes Mellitus: a qualitative study among app users and non-app users. Diabetol Metab Syndr. 2019;11:84. doi: 10.1186/s13098-019-0480-4.
    1. Mookherji S, Mehl G, Kaonga N, Mechael P. Unmet Need: Improving mHealth Evaluation Rigor to Build the Evidence Base. J Health Commun. 2015;20(10):1224–9. doi: 10.1080/10810730.2015.1018624.
    1. Rhyner D, Loher H, Dehais J, Anthimopoulos M, Shevchik S, Botwey RH, Duke D, Stettler C, Diem P, Mougiakakou S. Carbohydrate estimation by a mobile phone-based system versus self-estimations of individuals with type 1 diabetes mellitus: a comparative study. J Med Internet Res. 2016 May 11;18(5):e101. doi: 10.2196/jmir.5567.
    1. Domhardt M, Tiefengrabner M, Dinic R, Fötschl U, Oostingh GJ, Stütz T, Stechemesser L, Weitgasser R, Ginzinger SW. Training of carbohydrate estimation for people with diabetes using mobile augmented reality. J Diabetes Sci Technol. 2015 May;9(3):516–24. doi: 10.1177/1932296815578880.
    1. Rollo ME, Ash S, Lyons-Wall P, Russell AW. Evaluation of a mobile phone image-based dietary assessment method in adults with type 2 diabetes. Nutrients. 2015 Jun 17;7(6):4897–910. doi: 10.3390/nu7064897.
    1. Rossi MC, Nicolucci A, Lucisano G, Pellegrini F, Di Bartolo Paolo, Miselli V, Anichini R, Vespasiani G, Study Group Did. Impact of the "Diabetes Interactive Diary" telemedicine system on metabolic control, risk of hypoglycemia, and quality of life: a randomized clinical trial in type 1 diabetes. Diabetes Technol Ther. 2013 Aug;15(8):670–9. doi: 10.1089/dia.2013.0021.
    1. Pham Q, Wiljer D, Cafazzo JA. Beyond the randomized controlled trial: a review of alternatives in mHealth clinical trial methods. JMIR Mhealth Uhealth. 2016 Sep 09;4(3):e107. doi: 10.2196/mhealth.5720.
    1. Thorlund K, Haggstrom J, Park JJ, Mills EJ. Key design considerations for adaptive clinical trials: a primer for clinicians. BMJ. 2018 Mar 08;360:k698. doi: 10.1136/bmj.k698.

Source: PubMed

Patrocinadores y Colaboradores

Condiciones médicas

Intervenciones de drogas

3
Suscribir