Search

The global burden of diabetes is rapidly increasing, from 451 million people in 2019 to 693 million by 20451. The insidious onset of type 2 diabetes delays diagnosis and increases morbidity2. Given the multifactorial vascular effects of diabetes, we hypothesized that smartphone-based photoplethysmography could provide a widely accessible digital biomarker for diabetes. Here we developed a deep neural network (DNN) to detect prevalent diabetes using smartphone-based photoplethysmography from an initial cohort of 53,870 individuals (the ‘primary cohort’), which we then validated in a separate cohort of 7,806 individuals (the ‘contemporary cohort’) and a cohort of 181 prospectively enrolled individuals from three clinics (the ‘clinic cohort’). The DNN achieved an area under the curve for prevalent diabetes of 0.766 in the primary cohort (95% confidence interval: 0.750–0.782; sensitivity 75%, specificity 65%) and 0.740 in the contemporary cohort (95% confidence interval: 0.723–0.758; sensitivity 81%, specificity 54%). When the output of the DNN, called the DNN score, was included in a regression analysis alongside age, gender, race/ethnicity and body mass index, the area under the curve was 0.830 and the DNN score remained independently predictive of diabetes. The performance of the DNN in the clinic cohort was similar to that in other validation datasets. There was a significant and positive association between the continuous DNN score and hemoglobin A1c (P ≤ 0.001) among those with hemoglobin A1c data. These findings demonstrate that smartphone-based photoplethysmography provides a readily attainable, non-invasive digital biomarker of prevalent diabetes. A deep neural network applied to smartphone-based vascular imaging can detect diabetes, opening new possibilities for non-invasive diagnosis.

IntroductionThere is emerging evidence supporting the use of the radial artery (RA) as a preferred secondary conduit for coronary artery bypass grafting (CABG) as it is associated with higher rates of graft patency at 5 years when compared with saphenous vein grafts (SVG). The modified Allen’s test (MAT) is traditionally regarded as the standard of care in the assessment of ulnar artery (UA) patency prior to RA harvesting. Unfortunately, due to high false-positive rates, a substantial number of pre-CABG patients are found to have an abnormal MAT despite normal UA patency, resulting in inappropriate exclusion from RA harvesting. The SVG is generally used in its place when this occurs, resulting in potentially lower rates of long-term graft patency.Methods and analysisThe CAPITAL iRADIAL-CABG trial is currently enrolling participants 18 years of age or older undergoing CABG for whom the treating physician is considering the use of an RA conduit. Eligible patients will be randomised in a 1:1 fashion to MAT or smartphone-based photoplethysmography application assessment to assess collateral palmar circulation prior to RA harvesting. The primary outcome of the trial is the use of the RA as a conduit during CABG. The primary safety outcome is postoperative palmar ischaemia as determined by clinical assessment or requirement of vascular intervention. Secondary outcomes include vascular complications, early graft failure, need for rescue percutaneous coronary intervention during the index hospitalisation and a composite cardiovascular outcome of myocardial infarction, stroke and cardiovascular death prior to discharge from hospital. A total of 236 participants are planned to be recruited.Ethics and disseminationThe study was approved by the Ottawa Heart Science Network Research Ethics Board (approval number 20180865-01H). The study results will be disseminated via conference presentations and peer-reviewed publications.Trial registration numberNCT03810729.

The global burden of diabetes is rapidly increasing, from 451 million people in 2019 to 693 million by 2045

Background— The 6-minute walk test (6MWT) independently predicts congestive heart failure severity, death, and heart failure hospitalizations, but must be administered in clinic by qualified staff on a premeasured course. As part of the Health eHeart Study, we sought to develop and validate a self-administered 6MWT mobile application (SA-6MWTapp) for independent use at home by patients. Methods and Results— We performed a validation study of an SA-6MWTapp in 103 participants. In phase 1 (n=52), we developed a distance-estimation algorithm for the SA-6MWTapp by comparing step counts from an Actigraph and measured distance on a premeasured 6MWT course with step counts and estimated distance obtained simultaneously from our SA-6MWTapp (best estimation algorithm, r=0.89 [95% confidence interval 0.78–0.99]). In phase 2, 32 participants (including those with congestive heart failure and pulmonary hypertension) used the SA-6MWTapp independently in clinic, and the distance estimated by the SA-6MWTapp was compared with the measured distance (r=0.83 [95% confidence interval 0.79–0.92]). In phase 3, 19 patients with congestive heart failure and pulmonary hypertension consecutively enrolled from clinic performed 3.2±1 SA-6MWTapp tests per week at home over 2 weeks. Distances estimated from the SA-6MWTapp during home 6MWTs were highly repeatable (coefficient of variation =4.6%) and correlated with in-clinic–measured distance (r=0.88 [95% confidence interval 0.87–0.89]). Usability surveys performed during the second (in-clinic) and third (at-home) phases demonstrated that the SA-6MWTapp was simple and easy to use independently. Conclusions— An SA-6MWTapp is easy to use and yields accurate repeatable measurements in the clinic and at home.