With the wide-distribution of smart wearables, it seems as though ubiquitous healthcare can finally permeate into our everyday lives, opening the possibility to realize clinical-grade applications. However, given that clinical applications require reliable sensing, there is a need to understand how accurate healthcare sensors on wearable devices (e.g., heart rate sensors) are. To answer this question, this work starts with a thorough investigation on the accuracy of widely used wearable devices' heart rate sensors. Specifically, we show that when actively moving, heart rate readings can diverge far from the ground truth, and also show that such inaccuracies cannot be easily correlated, nor predicted, using accelerometer and gyroscope measurements. Rather, we point out that the light intensity readings at the photoplethysmography (PPG) sensor can be an effective indicator of heart rate accuracy. Using a Viterbi algorithm-based Hidden Markov Model, we show that it is possible to design a filter that allows smartwatches to self-classify measurement quality with ∼ 98% accuracy. Given that such capabilities allow the smartwatch to internally filter misleading values from being application input, we foresee this as an essential step in catalyzing novel clinical-grade wearable applications.