Diabetic foot ulcers represent a significant source of morbidity in the U.S., with rapidly escalating costs to the health care system. Multiple pathophysiological disturbances converge to result in delayed epithelialization and persistent inflammation. Serotonin (5-hydroxytryptamine [5-HT]) and the selective serotonin reuptake inhibitor fluoxetine (FLX) have both been shown to have immunomodulatory effects. Here we extend their utility as a therapeutic alternative for nonhealing diabetic wounds by demonstrating their ability to interact with multiple pathways involved in wound healing. We show that topically applied FLX improves cutaneous wound healing in vivo. Mechanistically, we demonstrate that FLX not only increases keratinocyte migration but also shifts the local immune milieu toward a less inflammatory phenotype in vivo without altering behavior. By targeting the serotonin pathway in wound healing, we demonstrate the potential of repurposing FLX as a safe topical for the challenging clinical problem of diabetic wounds.

Real-time detection of Atrial Fibrillation (AFib) is made possible by the quality-assessment via a 1-dimensional convolution neural network (1D-CNN) in a processor of a PPG sensor patch and a 2-dimensional convolution neural network (2D-CNN) for AFib detection in cloud. The 1D-CNN is able to filter out the unqualified PPG that is contaminated by motion artifacts and/or ambient light interference. The remaining qualified PPG is then inputted to another built 2D-CNN for detecting AFib. This 1D-CNN consists of 4 layers of convolutions and max pooling, one long short-term memory (LSTM) and an output dense layer. The 2D-CNN is pre-trained based on the electrocardiography (ECG) data from MIMIC III database, for which the RR-intervals (RRIs) of ECG data are first extracted in Poincaré Images and then regarded as input features to the model for training. This 2D-CNN has also 4 layers of convolutions and max pooling and four output dense layers. The pre-trained model is next fine-tuned based on peak-to-peak intervals (PPIs) of PPG (Photoplethysmography) measured from wearable devices as input features for detecting AFib effectively. The quality-assessment 1D-CNN model is implemented in the wearable device to transmit only qualified data to the 2D-CNN model in cloud for AFib detection, achieving power efficiency. Both models are trained by the Adam optimizer. To validate the models, the PPIs of PPG were collected to evaluate the performance of the established models in real time. Experimental results show that the fine-tuned 2D-CNN for AFib detection achieves the accuracy, sensitivity and specificity were 98.08%, 96.82%, and 98.86%, respectively, the most favorables as opposed to other reported works based on PPG. The models are able to not only assist clinicians in AFib detection but also provides a mechanism to detect AFib via wearable devices in real time.

Blood pressure (BP) is predicted by this effort based on photoplethysmography (PPG) data to provide effective pre-warning of possible preeclampsia of pregnant women. Towards frequent BP measurement, a PPG sensor device is utilized in this study as a solution to offer continuous, cuffless blood pressure monitoring frequently for pregnant women. PPG data were collected using a flexible sensor patch from the wrist arteries of 194 subjects, which included 154 normal individuals and 40 pregnant women. Deep-learning models in 3 stages were built and trained to predict BP. The first stage involves developing a baseline deep-learning BP model using a dataset from common subjects. In the 2 ^nd stage, this model was fine-tuned with data from pregnant women, using a 1-Dimensional Convolutional Neural Network (1D-CNN) with Convolutional Block Attention Module (CBAMs), followed by bi-directional Gated Recurrent Units (GRUs) layers and attention layers. The fine-tuned model results in a mean error (ME) of -1.40 ± 7.15 (standard deviation, SD) for systolic blood pressure (SBP) and -0.44 (ME) ± 5.06 (SD) for diastolic blood pressure (DBP). At the final stage is the personalization for individual pregnant women using transfer learning again, enhancing further the model accuracy to -0.17 (ME) ± 1.45 (SD) for SBP and 0.27 (ME) ± 0.64 (SD) for DBP showing a promising solution for continuous, non-invasive BP monitoring in precision by the proposed 3-stage of modeling, fine-tuning and personalization.

A machine learning (ML) algorithm is successfully developed to assess the signal quality of measured photoplethysmography (PPG) waveforms for effective real-time prediction of blood flow volume (BFV). This algorithm is essential to achieve high prediction accuracy of BFV for hemodialysis patients to monitor the quality of their arteriovenous fistulas (AVFs) at home by themselves using a new hand-held device. The algorithm is built on an ML classifier of 1-dimensional convolutional neural network (1D-CNN), calibrated by two groups of PPG waveforms that are pre-identified by experienced experts to 300 qualified and 202 un-qualified PPG waveforms in 6-second windows, as the ones to render accurate BFV predictions and the others to inaccurates, respectively. The qualified ones satisfy at least the deterministic criteria such as adequate signal-to-noise-ratio (SNR), stable/small fluctuations of AC/DC components, and also the presence of secondary bio-features, to ensure minimized influence from mis-positioning, hand movement, pressurization and varied ambient lighting. With the classifier algorithm in hand, together with another fully-connected neural network for estimating BFV, a combined real-time computation algorithm is built, being able to achieve much better accuracy for real-time measurement ubiquitously. In results, using the newly-developed quality-assessment algorithm, the error of predicted BFVs is improved from ±175.577 ml/min to ±122.8259 ml/min significantly.

A high-accuracy biometric identification system based on photoplethysmography (PPG) is proposed in this study. Equipped with continuous quality assessment on PPG in real-time by calculated power spectral density (PSD) and large-area organic photodetectors (OPDs) in the PPG sensor offering low-noise PPG, the deep learning model built herein is able to acquire delicate PPG features varying clearly from subject to subject, and then achieves high accuracy for biometric applications. It is known that PPG is a technology capable of measuring blood volume changes by emitting optical power into skin, reaching blood vessels and collects the reflected optical power back and out of skin, suitable for ensuring live-body bio-metrics while many other bio-metrics are unable to. The raw PPG measured by the PPG device is first pre-processed by a bandpass filter, and then those with low power spectral density (PSD) of PPG versus noise or large DC drifts are screened out in real time to ensure the signal quality of PPG prior to bio-metrics. This pre-processing step is crucial to disregard all the unqualified PPG that may lead to wrongful result of biometrics later. The bio-metrics is next conducted by a built deep-learning (DL) model of a convolutional neural network (CNN) and long short-term memory (LSTM) layers. The DL model is trained by the PPG data collected from 42 subjects. Experimental results show an accuracy of 99.64% for binary while 98.8% for multi-class classification, outperforming other related works using PPG.

A fingerprint sensor array of pixels with photo-diodes for sensing and thin film transistors (TFTs) as switches was developed for the first time together with new algorithms to estimate blood pressure (BP) based on quality photoplethysmogram (PPG) sensed from this array device. Towards obtaining PPG in high quality, i.e., low noise, the pixels in the sensor array for under-screen fingerprint sensing in mobile devices are designed capable of being operated in a different mode, connected in parallel to output larger current signals than the original mode of fingerprint sensing, for better SNRs (signal-to-noise ratio) of sensed PPGs. The sensed PPG is next pre-processed with being filtered to remove noise, normalized and re-sampled, etc., followed by a quality check engineered to assess further the sensed PPG in real time by a built deep learning (DL) model, a 1-dimensional convolutional neural network (1D-CNN) with Long Short-Term Memory (LSTM). The model in intended to disqualify the PPGs contaminated by ambient light interference and motion artifacts. Data was collected from 88 subjects, including 52 men and 36 women, by measuring PPG signals from a fingerprint sensor, with systolic blood pressure (SBP) ranging from 90 to 150 mmHg while diastolic blood pressure (DBP) from 50 to 85 mmHg. An OMRON HEM-7127 device was used to obtain reference BPs. In results, an accuracy of 97.13% for distinguishing between qualified and unqualified PPGs has been achieved by the afore-mentioned 1D-CNN trained by ground-truths, pre-collected PPGs judged and labeled into 2 groups, qualified and unqualified PPGs. Next, only the qualified PPGs are fed to another DL model built for estimating BP, in a structure of 1D-CNN with 3 consecutive sections of convolution, batch normalization and max pooling. This BP model is next optimized to a structure and parameters to achieve the best combined estimation of SBP and DBP. The results show accuracy with 1.31 (mean absolute error, MAE) ± 1.34 (standard deviation, SD) for SBP and 4.11 (MAE) ± 3.32 (SD) for DBP, favorable as compared to all the prior arts using an image sensor to estimate BPs.