Machine-Learning Powered Optoacoustic Sensor for Diabetes Progression

The assessment of diabetes severity relies primarily on a count of clinical complications to empirically characterize disease. Disease staging based on clinical complications also employs a scoring system that may not be optimally suited for analysis of earlier stages of diabetes development or for monitoring smaller increments of disease progress with high precision. We propose a novel sensor, which goes beyond the abilities of current state-of-the-art approaches and introduces a new concept in the assessment of biomedical markers by means of ultra-broadband optoacoustic detection. Being insensitive to photon scattering, the new sensor can resolve optical biomarkers in fine detail and as a function of depth and relates epidermal and dermal morphological and micro-vascular density features to diabetes state. We demonstrate basic sensor characteristics in phantoms and examine the novel sensing concept presented in a pilot study using data from 86 participants (20 healthy and 66 diabetic) at an ultra-wide optoacoustic bandwidth of 120 MHz. Machine learning based on ensemble trees was developed and trained in a supervised fashion and subsequently used to examine the relation of sensor data to disease severity, in particular as it associates to diabetes without complications vs. diabetic neuropathy or atherosclerotic cardiovascular disease. We also investigated the sensor performance in relation to HbA1C values. The proposed method achieved statistically significant detection in all different patient groups. The effect of technical parameters, in particular sensor area size and the time window of optoacoustic signals used in data training were also examined in measurements from phantoms and humans. We discuss how optoacoustic sensors fundamentally solve limitations present in optical sensing and, empowered by machine learning, open a new chapter in non-invasive portable sensing for biomedical applications.