← Back to 2020 Archive
📄

Slide Presentation Only

There is no video recording available for this scientific session. You can view the fully indexed slide text contents below or download the presentation file.

Download Presentation slides (PDF)

Apps and Wearables to Keep Track of Your Heart Failure Patient

Speaker: Abhinav Sharma Event Year: 2020 Video Stream: Not Available

Indexed Presentation Slide Text (SEO searchable)

Apps and Wearables to Keep Track of Your Heart Failure Patient Abhinav Sharma MDDivision of CardiologyMcGill University Abhinav.sharma@mcgill.ca Disclosures•AHA Strategically Focused Research Network•ESC Young Investigator Research Grant•Bayer-Vascular Canadian Cardiovascular Society grant•Roche Diagnostics•Takeda •BMS-Pfizer•B.I-CVCT Fellow•Boeringer-Ingelhiem 2 3 Agenda•Introduction•How can apps and wearables help our patients with HF?-Vital signs -Medication optimization-Physical activity -Comorbidity management •Conclusion and discussion Sharma et al. JACC 2018;71:2680-2690 5 Role of Appsin Heart Failure 7 Vital Signs ▪Limited by need for blue-tooth linked devices ▪Often challenging for older patients to set this up▪New technologies to use facial scans to identify vital signs Facial Scan to Identify Vital Signs Drug Adherence •Applications can play a significant role in encouraging patients to adhere to medication regimens•Many of these strategies remain untested•‘Nudges’ can play an important role in changing patient behavior Sharma et al. JACC 2018;71:2680-2690; Brown and Gaggin. JCF 2019;25:5 Utilizing mobile technologies to improve physical activity and medication adherence in patients with heart failure and diabetes mellitus: Rationale and design of the TARGET-HF-DM Trial12 13 Sharma et al. (under review) Circulation Heart Failure 14 Sharma; Am Heart J.2019 May;211:22-33 Drug Adherence Physical Activity Moore et al PLoSMed. 2012 17 18 MHC App Integrates Three Sources of Physical Activity Data Daily step count and distance walked from Apple platform Self-reported survey responses about daily and weekly physical activity levels Core motion activity detection from phone accelerometry 19 User Flow Through Baseline Week of MHC Study 20 Based on a Week of Baseline Activity Levels, Participants Assigned to One of Five Activity Clusters Most active WeekendWarriors Least active Worker beesDrivers 21 ●Primary outcome: Daily step count●Secondary outcomes: ○Sleep duration ○Sleep quality ○Self-reported daily happiness on a scale of 1 -10 MyHeartCounts Study: Fully Digital Randomized Controlled Trial of Physical Activity e-Coaching 22 Mobile Study Consent 23 Four Interventions Delivered By The MHC Application Lancet Digital Health 2019; 1: e344–52 25 Long-term user engagement is one of the main challengesof digital RCT Diagnosing Comorbidities •Challenge in diagnosing and managing comorbidities in patients with HF•Diabetes is one of the most common comorbidities•Given the emergence of therapies that can aid in reducing the risk of outcomes of patients with diabetes, we need to increase our ability to screen for such disorders 27 28 Deep learning: ECG screening for diabetes 31 Key Questions if Making Your Own App or Wearable•Who is the app targeted towards –i.e. what is the ONE key user•What is defined as ‘success’ if the app works well•What is defined as ‘failure’•How is the project/app going to sabotage itself•What is the plan for sustainability Thank You! Questions?Please submit your questions by clicking on the Q&A icon on your screen