There have been numerous stories over the past several years highlighting how mobile health apps and devices have assisted in the diagnosis and treatment plan of people around the world. Recently, a 64 year old man was able to use heart rate data collected via his Apple smartwatch which utilized cardiology algorithms along with an internet search to determine that he was likely suffering from sick sinus syndrome. Using the data that had been recorded over the few weeks prior to his presentation to the ER, doctors were able to confirm his self-diagnosis and he was able to have surgical intervention much sooner than in most cases because of the data available via his smartwatch.
Other apps and device attachments enable a smartphone or tablet to obtain a mobile ECG which a cardiologist can review for detection and monitoring of cardiac rhythms.
Medical researchers and healthcare providers are also able to gather demographic information and laboratory values and combine them with ECG and other mobile health data to monitor numerous cardiovascular risk factors and diseases. Here are five examples:
- Risk score for atrial fibrillation from the Framingham heart study — evaluates an adult for the risk of developing atrial fibrillation. Populations can be followed and interventions to reduce risk for atrial fibrillation may be instituted earlier, having the potential to reduce the number of new cases.
- Risk Factors for the Tachycardia-Bradycardia Syndrome (Sinoatrial Disorder, Sick Sinus Syndrome) – this algorithm allows healthcare providers to review a patient’s risk for a sick sinus syndrome-related disorder (similar to the case mentioned above).
- NICE Criteria for Risk of Stroke in a Patient with Atrial Fibrillation –medical researchers using ResearchKit can evaluate a large group of people with atrial fibrillation with ease by incorporating this algorithm into their research study. This will give researchers the ability to follow the group in order to identify and monitor those at highest risk for stroke.
- Probability of Acute Myocardial Infarction in the Presence of Left Bundle Branch Block – emergency room clinicians may be able to improve “door-to-balloon” time during acute myocardial infarction by incorporating this algorithm into their review of electrocardiograms.
- Reynolds Risk Score for Cardiovascular Disease in Women – Researchers using Apple’s ResearchKit can identify and track women for cardiovascular disease. By alerting subjects enrolled in the study, the women identified as high risk can be encouraged to visit with their primary care provider for complete evaluation and treatment as indicated to lower risk for cardiovascular disease.
Heart disease is the leading cause of death in the United States, responsible for about 1 in 4 deaths. Medical algorithms have the potential to help physicians reduce the number of cardiac-related deaths, by incorporating them into the assessment and plan of patient care as well as clinical research studies.
There are thousands of algorithms among the 21,000+ medical algorithms from The Medical Algorithms Company that can assist physicians, researchers, and other members of the healthcare team to better assess and care for patients.