If your heart’s aflutter, a poet may say the tremulous excitement you feel is because you are in love. Your doctor, however, will say your heart’s flutter could be a sign of a serious condition: atrial fibrillation.
According to the American Heart Association, atrial fibrillation (also called AFib or AF) is a “quivering or irregular heartbeat (arrhythmia) that can lead to blood clots, stroke, heart failure and other heart-related complications.”
People with AFib can experience some of the following symptoms:
Watch an animation of Atrial Fibrillation.
The Centers for Disease Control and Prevention (CDC) estimate that 2.7 to 6.1 million Americans are currently diagnosed with AFib, a number that will surely grow as America’s population ages. AFib is more likely to strike patients 65 years and older.
These numbers coincide with a recent study by data scientists at Perception Health. In this study, when looking at de-identified medical claims of 10,000 patients with commercial insurance, the analysis revealed that 1.72% of those patients had a diagnosis of AFib. Extrapolating this percentage to the U.S. population of 327 million people, the data scientists projected 5.6 million Americans with AFib.
The study’s more alarming fact, however, is that 28% of the patients in the sample set were trending towards a future diagnosis of AFib. These patients had not been not diagnosed with AFib, but had many of the same symptoms and treatment codes in their claims as did patients with an AFib diagnosis. If ignored, these symptoms could result in a future diagnosis of AFib.
The predictions were made by the data scientists at Perception Health, using the company's CARE disease prediction algorithms.
“Our CARE predictive models are machine-learning disease algorithms," says Katie Kruzan, mathematician at Perception Health. "We take our claims dataset, which has about 26 billion rows, and track de-identified patients across the entire continuum of care. We are then able to see what diagnoses, procedure codes, and frequency lead to particular diagnoses, like atrial fibrillation."
Perception Health works with hospitals, ACOs, and other providers to help identify patients who are trending towards specific diseases. "Ultimately, this is all about improving patients' lives, says Kruzan. "We can apply this algorithm to a hospital's patient database to see which of their patients may be trending towards a particular diagnosis, so to encourage those patients to get a screening for that disease."
The American Journal of Managed Care (AJMC) predicts that more than 12 million people will be diagnosed with AFib by 2030. That number is projected to increase to 15.9 million by 2050.
AFib increases the risk for a stroke by 4-5 times. The AJMC also reports that by some estimates, 15-20% of all strokes can be attributed to AFib. While a stroke is the fifth leading cause of death for men and fourth for women, it is also the leading preventable cause of disability.
If you have any of the following conditions / risk factors, especially the first two, you have a higher risk for AFib:
AFib can be treated with:
The growth in the number of AFib diagnoses is expected to continue for the next 30 years. Patients with the risk factors listed above should contact their primary care physician for more information on steps to better manage their health.
For the Perception Health study, a sample set of 10,000 patients were chosen with an ICD-10 Diagnosis Code related to atrial fibrillation rendered by a healthcare provider after January 1, 2016. Any patient that met this criteria had their entire claims history since January 1, 2016 pulled into the dataset. A comparable dataset was created with patients who did not have an ICD-10 Diagnosis Code related to AFib.
The ICD-10 Diagnoses and CPT Codes that are commonly found in people who had been diagnosed with Atrial Fibrillation involve cardiology, hospital visits, radiology, and respiratory/circulatory.
The data set used to train the model was comprised of 33% patients (those who had been diagnosed with AFib) and 66% non-patients (people without AFib related codes in their claims history). The model was then trained on 70% of that data set and then tested on 30% of that same data set.
From the ROC curve, the area under curve (AUC) is calculated as 0.797, and the Random Forest model was accepted with a model confidence value of 0.80.
From the sample of 10,000 medical claims, 172 had a diagnosis of AFib in their claims history. After applying the disease prediction algorithm in Perception Health's CARE module, the scientists predicted another 2,827 patients are trending toward an AFib diagnosis. By projecting the findings nationally, the data scientists estimated that 92 million people may be trending towards AFib.
