Building Trustworthy Generative Artificial Intelligence for Diabetes Care and Limb Preservation: A Medical Knowledge Extraction Case.

BACKGROUND: Large language models (LLMs) offer significant potential in medical information extraction but carry risks of generating incorrect information. This study aims to develop and validate a retriever-augmented generation (RAG) model that provides accurate medical knowledge about diabetes and diabetic foot care to laypersons with an eighth-grade literacy level. Improving health literacy through patient education is paramount to addressing the problem of limb loss in the diabetic population. In addition to affecting patient well-being through improved outcomes, improved physician well-being is an important outcome of a self-management model for patient health education. METHODS: We used an RAG architecture and built a question-and-answer artificial intelligence (AI) model to extract knowledge in response to questions pertaining to diabetes and diabetic foot care. We utilized GPT-4 by OpenAI, with Pinecone as a vector database. The NIH National Standards for Diabetes Self-Management Education served as the basis for our knowledge base. The model's outputs were validated through expert review against established guidelines and literature. Fifty-eight keywords were used to select 295 articles and the model was tested against 175 questions across topics. RESULTS: The study demonstrated that with appropriate content volume and few-shot learning prompts, the RAG model achieved 98% accuracy, confirming its capability to offer user-friendly and comprehensible medical information. CONCLUSION: The RAG model represents a promising tool for delivering reliable medical knowledge to the public which can be used for self-education and self-management for diabetes, highlighting the importance of content validation and innovative prompt engineering in AI applications.

A Novel Machine-Learning Framework Based on a Hierarchy of Dispute Models for the Identification of Fish Species Using Multi-Mode Spectroscopy.

Seafood mislabeling rates of approximately 20% have been reported globally. Traditional methods for fish species identification, such as DNA analysis and polymerase chain reaction (PCR), are expensive and time-consuming, and require skilled technicians and specialized equipment. The combination of spectroscopy and machine learning presents a promising approach to overcome these challenges. In our study, we took a comprehensive approach by considering a total of 43 different fish species and employing three modes of spectroscopy: fluorescence (Fluor), and reflectance in the visible near-infrared (VNIR) and short-wave near-infrared (SWIR). To achieve higher accuracies, we developed a novel machine-learning framework, where groups of similar fish types were identified and specialized classifiers were trained for each group. The incorporation of global (single artificial intelligence for all species) and dispute classification models created a hierarchical decision process, yielding higher performances. For Fluor, VNIR, and SWIR, accuracies increased from 80%, 75%, and 49% to 83%, 81%, and 58%, respectively. Furthermore, certain species witnessed remarkable performance enhancements of up to 40% in single-mode identification. The fusion of all three spectroscopic modes further boosted the performance of the best single mode, averaged over all species, by 9%. Fish species mislabeling not only poses health-related risks due to contaminants, toxins, and allergens that could be life-threatening, but also gives rise to economic and environmental hazards and loss of nutritional benefits. Our proposed method can detect fish fraud as a real-time alternative to DNA barcoding and other standard methods. The hierarchical system of dispute models proposed in this work is a novel machine-learning tool not limited to this application, and can improve accuracy in any classification problem which contains a large number of classes.

Medical Imaging Applications of Federated Learning.

Since its introduction in 2016, researchers have applied the idea of Federated Learning (FL) to several domains ranging from edge computing to banking. The technique's inherent security benefits, privacy-preserving capabilities, ease of scalability, and ability to transcend data biases have motivated researchers to use this tool on healthcare datasets. While several reviews exist detailing FL and its applications, this review focuses solely on the different applications of FL to medical imaging datasets, grouping applications by diseases, modality, and/or part of the body. This Systematic Literature review was conducted by querying and consolidating results from ArXiv, IEEE Xplorer, and PubMed. Furthermore, we provide a detailed description of FL architecture, models, descriptions of the performance achieved by FL models, and how results compare with traditional Machine Learning (ML) models. Additionally, we discuss the security benefits, highlighting two primary forms of privacy-preserving techniques, including homomorphic encryption and differential privacy. Finally, we provide some background information and context regarding where the contributions lie. The background information is organized into the following categories: architecture/setup type, data-related topics, security, and learning types. While progress has been made within the field of FL and medical imaging, much room for improvement and understanding remains, with an emphasis on security and data issues remaining the primary concerns for researchers. Therefore, improvements are constantly pushing the field forward. Finally, we highlighted the challenges in deploying FL in medical imaging applications and provided recommendations for future directions.

The Effect of Skeletal Muscle-Pump on Blood Pressure and Postural Control in Parkinson's Disease.

PURPOSE: Activation of the calf (gastrocnemius and soleus) and tibialis anterior muscles play an important role in blood pressure regulation (via muscle-pump mechanism) and postural control. Parkinson's disease is associated with calf (and tibialis anterior muscles weakness and stiffness, which contribute to postural instability and associated falls. In this work, we studied the role of the medial and lateral gastrocnemius, tibialis anterior, and soleus muscle contractions in maintaining blood pressure and postural stability in Parkinson's patients and healthy controls during standing. In addition, we investigated whether the activation of the calf and tibialis anterior muscles is baroreflex dependent or postural-mediated. METHODS: We recorded electrocardiogram, blood pressure, center of pressure as a measure of postural sway, and muscle activity from the medial and lateral gastrocnemius, tibialis anterior, and soleus muscles from twenty-six Parkinson's patients and eighteen sex and age-matched healthy controls during standing and with eyes open. The interaction and bidirectional causalities between the cardiovascular, musculoskeletal, and postural variables were studied using wavelet transform coherence and convergent cross-mapping techniques, respectively. RESULTS: Parkinson's patients experienced a higher postural sway and demonstrated mechanical muscle-pump dysfunction of all individual leg muscles, all of which contribute to postural instability. Moreover, our results showed that coupling between the cardiovascular, musculoskeletal, and postural variables is affected by Parkinson's disease while the contribution of the calf and tibialis anterior muscles is greater for blood pressure regulation than postural sway. CONCLUSION: The outcomes of this study could assist in the development of appropriate physical exercise programs that target lower limb muscles to improve the muscle-pump function and reduce postural instability in Parkinson's disease.

Rapid Assessment of Fish Freshness for Multiple Supply-Chain Nodes Using Multi-Mode Spectroscopy and Fusion-Based Artificial Intelligence.

This study is directed towards developing a fast, non-destructive, and easy-to-use handheld multimode spectroscopic system for fish quality assessment. We apply data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy data features to classify fish from fresh to spoiled condition. Farmed Atlantic and wild coho and chinook salmon and sablefish fillets were measured. Three hundred measurement points on each of four fillets were taken every two days over 14 days for a total of 8400 measurements for each spectral mode. Multiple machine learning techniques including principal component analysis, self-organized maps, linear and quadratic discriminant analyses, k-nearest neighbors, random forest, support vector machine, and linear regression, as well as ensemble and majority voting methods, were used to explore spectroscopy data measured on fillets and to train classification models to predict freshness. Our results show that multi-mode spectroscopy achieves 95% accuracy, improving the accuracies of the FL, VIS-NIR and SWIR single-mode spectroscopies by 26, 10 and 9%, respectively. We conclude that multi-mode spectroscopy and data fusion analysis has the potential to accurately assess freshness and predict shelf life for fish fillets and recommend this study be expanded to a larger number of species in the future.

Using machine learning methods and EEG to discriminate aircraft pilot cognitive workload during flight.

Pilots of aircraft face varying degrees of cognitive workload even during normal flight operations. Periods of low cognitive workload may be followed by periods of high cognitive workload and vice versa. During such changing demands, there exists potential for increased error on behalf of the pilots due to periods of boredom or excessive cognitive task demand. To further understand cognitive workload in aviation, the present study involved collection of electroencephalogram (EEG) data from ten (10) collegiate aviation students in a live-flight environment in a single-engine aircraft. Each pilot possessed a Federal Aviation Administration (FAA) commercial pilot certificate and either FAA class I or class II medical certificate. Each pilot flew a standardized flight profile representing an average instrument flight training sequence. For data analysis, we used four main sub-bands of the recorded EEG signals: delta, theta, alpha, and beta. Power spectral density (PSD) and log energy entropy of each sub-band across 20 electrodes were computed and subjected to two feature selection algorithms (recursive feature elimination (RFE) and lasso cross-validation (LassoCV), and a stacking ensemble machine learning algorithm composed of support vector machine, random forest, and logistic regression. Also, hyperparameter optimization and tenfold cross-validation were used to improve the model performance, reliability, and generalization. The feature selection step resulted in 15 features that can be considered an indicator of pilots' cognitive workload states. Then these features were applied to the stacking ensemble algorithm, and the highest results were achieved using the selected features by the RFE algorithm with an accuracy of 91.67% (± 0.11), a precision of 93.89% (± 0.09), recall of 91.67% (± 0.11), F-score of 91.22% (± 0.12), and the mean ROC-AUC of 0.93 (± 0.06). The achieved results indicated that the combination of PSD and log energy entropy, along with well-designed machine learning algorithms, suggest the potential for the use of EEG to discriminate periods of the low, medium, and high workload to augment aircraft system design, including flight automation features to improve aviation safety.

Cardio-respiratory interactions in response to lower-body negative pressure.

The relationship between heart rate and blood pressure, as well as cardiorespiratory coupling, play a critical role in maintaining blood pressure and organ perfusion during conditions of blood loss. Traditional vital signs such as blood pressure, breathing rate, and oxygen saturation are poor markers of blood loss, making it difficult for medics to assess the severity of central hypovolemia. Monitoring hemorrhage is further complicated by the fact that some patients have a low tolerance to hemorrhage and would reach the point of cardiovascular collapse in less time than high tolerant individuals. Therefore, this study aimed to investigate the potential of the physiological interaction between heart rate and blood pressure, and cardiorespiratory coupling to track the progression of simulated hemorrhage, as well as distinguish individuals with low tolerance (LT) from the ones with high tolerance (HT) to hypovolemia. Nineteen subjects (age: 28 ± 6 years; height: 170 ± 7 cm; weight: 68 ± 10 kg) underwent a progressive lower body negative pressure (LBNP) protocol in which the participant was supine inside the chamber for 12 min (baseline) before 12 min of chamber decompression at -20, -30, -40, -50 and -60 mmHg followed by a 12 min recovery period. Twelve subjects reached presyncope before or during -60 mmHg LBNP stage and were considered low tolerant (LT, 12 participants), while the ones who completed -60 mmHg were considered high tolerant (HT, 7 participants). Continuous blood pressure (BP), respiration (RSP), and electrocardiogram (ECG) signals were acquired simultaneously during baseline and each LBNP stage. RR interval was calculated using ECG, while systolic blood pressure (SBP), and pulse pressure were derived from BP waveform. Wavelet transform coherence and convergent cross-mapping techniques were employed to study the physiological interdependence and the causal relationship between heart rate, blood pressure, and respiration. The interaction between blood pressure and heart rate in terms of gain, active gain, and fraction time active(SBP↔RR,PP↔RR)to maintain homeostasis was higher in the LT group during baseline, and LBNP simulated mild, moderate, and severe hemorrhage. The significant time of interaction between SBP and RSP, and the causal effect of blood pressure on respiration were higher in the HT group during baseline compared to the LT group. HT participants also had a higher causal effect of respiration on blood pressure(RSP→SBP,RSP→PP)during -30 and -40 mmHg compared to LT. Moreover, the HT group displayed a higher causal drive of respiratory-related changes in heart rate(RSP→RR)and heart rate mediated changes in respirationRR→RSPduring severe simulated hemorrhage (-40 mmHg) compared to the LT group. The calculated metrics to distinguish between individual LT from HT subjects achieved a sensitivity of 58%-83%, an accuracy of 63%-84%, and an area under the ROC curve of 74%-86%, while the overlap of LT individual responses with HT was 0%-33%. These results indicate the potential of cardiorespiratory coupling, and heart rate and blood pressure interaction toward tracking the progression of hemorrhage and distinguishing individuals with low tolerance to hypovolemia from those with high tolerance. Measurements of such interactions could improve clinical outcomes for patients with low tolerance to hypovolemia and therefore reduce morbidity and mortality through early implementation of life-saving interventions.

Canadian aging and inactivity study: Spaceflight-inspired exercises during head-down tilt bedrest blunted reductions in muscle-pump but not cardiac baroreflex in older persons.

As part of the first Canadian aging and inactivity study (CAIS) we assessed the efficacy of space-based exercise countermeasures for maintenance of cardiac and muscle-pump baroreflex in older persons during bedrest. An initiative of the Canadian Space Agency, Canadian Institutes of Health Research and the Canadian Frailty Network, CAIS involved 14 days of 6-degree head-down tilt bedrest (HDBR) with (Exercise) or without (Control) combined upper and lower body strength, aerobic, and high-intensity interval training exercise countermeasures. Twenty healthy men and women aged 55 to 65, randomly divided into control and exercise groups (male control (MC, n = 5), male exercise (ME, n = 5), female control (FC, n = 6), female exercise (FE, n = 4)) (age: 58.7 ± 0.5 years, height: 1.67 ± 0.02 m, body mass: 70.2 ± 3.2 kg; mean ± SEM), completed the study. Cardiac and muscle-pump baroreflex activity were assessed with supine-to-stand tests. Wavelet transform coherence was used to characterise cardiac and muscle-pump baroreflex fraction time active (FTA) and gain values, and convergent cross-mapping was used to investigate causal directionality between blood pressure (BP) and heart rate, as well as BP and lower leg muscle electromyography (EMG). Seven of the twenty participants were unable to stand for 6 minutes after HDBR, with six of those being female. Our findings showed that 2 weeks of bedrest impaired skeletal muscle's ability to return blood to the venous circulation differently across various sexes and intervention groups. Comparing values after bed rest with before bed rest values, there was a significant increase in heart rates (∆ of +25%; +17% in MC to +33% in FC; p < 0.0001), beat-to-beat EMG decreased (∆ of -43%; -25% in ME to -58% in MC; p < 0.02), while BP change was dependent on sex and intervention groups. Unlike their male counterparts, in terms of muscle-pump baroreflex, female participants had considerably decreased FTA after HDBR (p < 0.01). All groups except female control demonstrated parallel decreases in cardiac active gain and causality, while the FC demonstrated an increase in cardiac causality despite a similar decline in cardiac active gain. Results showed that the proposed exercises may alleviate muscle-pump baroreflex declines but could not influence the cardiac baroreflex decline from 14 days of inactivity in older adults.

Mechanical deconditioning of the heart due to long-term bed rest as observed on seismocardiogram morphology.

During head-down tilt bed rest (HDT) the cardiovascular system is subject to headward fluid shifts. The fluid shift phenomenon is analogous to weightlessness experienced during spaceflight microgravity. The purpose of this study was to investigate the effect of prolonged 60-day bed rest on the mechanical performance of the heart using the morphology of seismocardiography (SCG). Three-lead electrocardiogram (ECG), SCG and blood pressure recordings were collected simultaneously from 20 males in a 60-day HDT study (MEDES, Toulouse, France). The study was divided into two campaigns of ten participants. The first commenced in January, and the second in September. Signals were recorded in the supine position during the baseline data collection (BDC) before bed rest, during 6° HDT bed rest and during recovery (R), post-bed rest. Using SCG and blood pressure at the finger, the following were determined: Pulse Transit Time (PTT); and left-ventricular ejection time (LVET). SCG morphology was analyzed using functional data analysis (FDA). The coefficients of the model were estimated over 20 cycles of SCG recordings of BDC12 and HDT52. SCG fiducial morphology AO (aortic valve opening) and AC (aortic valve closing) amplitudes showed significant decrease between BDC12 and HDT52 (p < 0.03). PTT and LVET were also found to decrease through HDT bed rest (p < 0.01). Furthermore, PTT and LVET magnitude of response to bed rest was found to be different between campaigns (p < 0.001) possibly due to seasonal effects on of the cardiovascular system. Correlations between FDA and cardiac timing intervals PTT and LVET using SCG suggests decreases in mechanical strength of the heart and increased arterial stiffness due to fluid shifts associated with the prolonged bed rest.

Effect of Parkinson's Disease on Cardio-postural Coupling During Orthostatic Challenge.

Cardiac baroreflex and leg muscles activation are two important mechanisms for blood pressure regulation, failure of which could result in syncope and falls. Parkinson's disease is known to be associated with cardiac baroreflex impairment and skeletal muscle dysfunction contributing to falls. However, the mechanical effect of leg muscles contractions on blood pressure (muscle-pump) and the baroreflex-like responses of leg muscles to blood pressure changes is yet to be comprehensively investigated. In this study, we examined the involvement of the cardiac baroreflex and this hypothesized reflex muscle-pump function (cardio-postural coupling) to maintain blood pressure in Parkinson's patients and healthy controls during an orthostatic challenge induced via a head-up tilt test. We also studied the mechanical effect of the heart and leg muscles contractions on blood pressure. We recorded electrocardiogram, blood pressure and electromyogram from 21 patients with Parkinson's disease and 18 age-matched healthy controls during supine, head-up tilt at 70°, and standing positions with eyes open. The interaction and bidirectional causalities between the cardiovascular and musculoskeletal signals were studied using wavelet transform coherence and convergent cross mapping techniques, respectively. Parkinson's patients displayed an impaired cardiac baroreflex and a reduced mechanical effect of the heart on blood pressure during supine, tilt and standing positions. However, the effectiveness of the cardiac baroreflex decreased in both Parkinson's patients and healthy controls during standing as compared to supine. In addition, Parkinson's patients demonstrated cardio-postural coupling impairment along with a mechanical muscle pump dysfunction which both could lead to dizziness and falls. Moreover, the cardiac baroreflex had a limited effect on blood pressure during standing while lower limb muscles continued to contract and maintain blood pressure via the muscle-pump mechanism. The study findings highlighted altered bidirectional coupling between heart rate and blood pressure, as well as between muscle activity and blood pressure in Parkinson's disease. The outcomes of this study could assist in the development of appropriate physical exercise programs to reduce falls in Parkinson's disease by monitoring the cardiac baroreflex and cardio-postural coupling effect on maintaining blood pressure.

Design and evaluation of a dynamic air cushion for pressure ulcers prevention.

Wheelchair users have a higher risk of developing pressure ulcers due to prolonged seated pressure. Pressure ulcers can be painful, may require surgical intervention, and even become life-threatening if infection occurs. To prevent pressure ulcers from forming the patient must either offload themselves or rely on a caregiver to move them allowing pressure redistribution over the seated area. In this work, we designed a dynamic air cushion to relieve pressure on loaded areas using sequences of inflation and deflation of the air cushion cells. The purpose of these sequences is to offload pressure from high-risk areas. To evaluate the effect of the alternating sequences on seated pressure and blood perfusion, we recorded interface pressure, skin blood flow, superficial tissue oxygen saturation, blood concentrations of oxygenated hemoglobin, and deoxygenated hemoglobin from twenty-one healthy volunteers who were asked to sit on the air cushion for static mode recording (3 min) and during the inflation/deflation sequences (up to 22 min). The alternating sequences consisted of ten combined inflation and deflation steps. Results showed that, after applying the alternating sequences, interface pressure reduced significantly (p=0.02) compared to the static mode. Moreover, the coefficient of variation of the seated pressure was higher (p<0.001) during the alternation sequence compared to the static mode. However, interface pressure under the right and left ischial tuberosities increased (p<0.001) during the alternation sequence compared to the static mode. In addition, during the alternating sequences, males had larger dispersion index values of both right and left ischial tuberosities pressure compared to females. Furthermore, the maximum value of oxygen saturation (p=0.04) and skin blood flow (p=0.001) increased during the pressure alternation sequences compared to the static mode. The study findings highlighted the positive effects of the designed dynamic air-cushion to relieve pressure on compressed areas and enhance blood perfusion similar to manual offloading approaches. The outcomes of this study are encouraging to evaluate the performance of the designed air cushion in studies involving wheelchair users.

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses.

Food safety and foodborne diseases are significant global public health concerns. Meat and poultry carcasses can be contaminated by pathogens like E. coli and salmonella, by contact with animal fecal matter and ingesta during slaughter and processing. Since fecal matter and ingesta can host these pathogens, detection, and excision of contaminated regions on meat surfaces is crucial. Fluorescence imaging has proven its potential for the detection of fecal residue but requires expertise to interpret. In order to be used by meat cutters without special training, automated detection is needed. This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images using EfficientNet-B0 to determine which meat surface images showed fecal contamination and then U-Net to precisely segment the areas of contamination. The EfficientNet-B0 model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discriminating clean and contaminated areas on carcasses. U-Net segmented areas with fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can improve food safety assurance by allowing the industry to use CSI-D fluorescence imaging to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero-tolerance plan.

Association between Arsenic Level, Gene Expression in Asian Population, and In Vitro Carcinogenic Bladder Tumor.

The IARC classified arsenic (As) as "carcinogenic to humans." Despite the health consequences of arsenic exposure, there is no molecular signature available yet that can predict when exposure may lead to the development of disease. To understand the molecular processes underlying arsenic exposure and the risk of disease development, this study investigated the functional relationship between high arsenic exposure and disease risk using gene expression derived from human exposure. In this study, a three step analysis was employed: (1) the gene expression profiles obtained from two diverse arsenic-exposed Asian populations were utilized to identify differentially expressed genes associated with arsenic exposure in human subjects, (2) the gene expression profiles induced by arsenic exposure in four different myeloma cancer cell lines were used to define common genes and pathways altered by arsenic exposure, and (3) the genetic profiles of two publicly available human bladder cancer studies were used to test the significance of the common association of genes, identified in step 1 and step 2, to develop and validate a predictive model of primary bladder cancer risk associated with arsenic exposure. Our analysis shows that arsenic exposure to humans is mainly associated with organismal injury and abnormalities, immunological disease, inflammatory disease, gastrointestinal disease, and increased rates of a wide variety of cancers. In addition, arsenic exerts its toxicity by generating reactive oxygen species (ROS) and increasing ROS production causing the imbalance that leads to cell and tissue damage (oxidative stress). Oxidative stress activates inflammatory pathways leading to transformation of a normal cell to tumor cell specifically; there is significant evidence of the advancing changes in oxidative/nitrative stress during the progression of bladder cancer. Therefore, we examined the relation of differentially expressed genes due to exposure of arsenic in human and bladder cancer and developed a bladder cancer risk prediction model. In this study, integrin-linked kinase (ILK) was one of the most significant pathways identified between both arsenic exposed population which plays a key role in eliciting a protective response to oxidative damage in epidermal cells. On the other hand, several studies showed that arsenic trioxide (ATO) is useful for anticancer therapy although the mechanisms underlying its paradoxical effects are still not well understood. ATO has shown remarkable efficacy for the treatment of multiple myeloma; therefore, it will be helpful to understand the underlying cancer biology by which ATO exerts its inhibitory effect on the myeloma cells. Our study found that MAPK is one of the most active network between arsenic gene and ATO cell line which is involved in indicative of oxidative/nitrosative damage and well associated with the development of bladder cancer. The study identified a unique set of 147 genes associated with arsenic exposure and linked to molecular mechanisms of cancer. The risk prediction model shows the highest prediction ability for recurrent bladder tumors based on a very small subset (NKIRAS2, AKTIP, and HLA-DQA1) of the 147 genes resulting in AUC of 0.94 (95% CI: 0.744-0.995) and 0.75 (95% CI: 0.343-0.933) on training and validation data, respectively.

Fetal ECG Extraction From Maternal ECG Using Attention-Based CycleGAN.

A non-invasive fetal electrocardiogram (FECG) is used to monitor the electrical pulse of the fetal heart. Decomposing the FECG signal from the maternal ECG (MECG) is a blind source separation problem, which is hard due to the low amplitude of the FECG, the overlap of R waves, and the potential exposure to noise from different sources. Traditional decomposition techniques, such as adaptive filters, require tuning, alignment, or pre-configuration, such as modeling the noise or desired signal to map the MECG to the FECG. The high correlation between maternal and fetal ECG fragments decreases the performance of convolution layers. Therefore, the masking region of interest based on the attention mechanism was performed to improve the signal generators' precision. The sine activation function was also used to retain more details when converting two signal domains. Three available datasets from the Physionet, including the A&D FECG, NI-FECG, and NI-FECG challenge, and one synthetic dataset using FECGSYN toolbox, were used to evaluate the performance. The proposed method could map an abdominal MECG to a scalp FECG with an average of 98% R-Square [CI 95%: 97%, 99%] as the goodness of fit on the A&D FECG dataset. Moreover, it achieved 99.7% F1-score [CI 95%: 97.8-99.9], 99.6% F1-score [CI 95%: 98.2%, 99.9%] and 99.3% F1-score [CI 95%: 95.3%, 99.9%] for fetal QRS detection on the A&D FECG, NI-FECG and NI-FECG challenge datasets, respectively. Also, the distortion was in the "very good" and "good" ranges. These results are comparable to the state-of-the-art results; thus, the proposed algorithm has the potential to be used for high-performance signal-to-signal conversion.

FootAssure: A multimodal, in-home wound detection device for diabetic peripheral neuropathy.

Currently, there is no single technology capable of assessing all the multitude of factors associated with peripheral complications of diabetic neuropathy. In this work, a multimodal wound detection system is proposed to help facilitate in-home examinations, utilizing a combination of thermal, multi-spectral 3D imaging modalities. The proposed system is capable of the 3D surface rendering of the foot and would overlay thermal, blood oxygenation, besides other skin health information to aid with foot health monitoring. Examples of biomarkers include pre-ulcer formation, blood circulation, temperature change, oxygenation, swelling, blisters/ulcer formation and healing, and toe health.

Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography.

In this study, we present a non-invasive solution to identify patients with coronary artery disease (CAD) defined as ⩾50% stenosis in at least one coronary artery. The solution is based on the analysis of linear acceleration (seismocardiogram, SCG) and angular velocity (gyrocardiogram, GCG) of the heart recorded in the x, y, and z directional axes from an accelerometer/gyroscope sensor mounted on the sternum. The database was collected from 310 individuals through a multicenter study. The time-frequency features extracted from each SCG and GCG data channel were fed to a one-dimensional Convolutional Neural Network (1D CNN) to train six separate classifiers. The results from different classifiers were later fused to estimate the CAD risk for each participant. The predicted CAD risk was validated against related results from angiography. The SCG z and SCG y classifiers showed better performance relative to the other models (p < 0.05) with the area under the curve (AUC) of 91%. The sensitivity range for CAD detection was 92-94% for the SCG models and 73-87% for the GCG models. Based on our findings, the SCG models achieved better performance in predicting the CAD risk compared to the GCG models; the model based on the combination of all SCG and GCG classifiers did not achieve higher performance relative to the other models. Moreover, these findings showed that the performance of the proposed 3-axial SCG/GCG solution based on recordings obtained during rest was comparable, or better than stress ECG. These data may indicate that 3-axial SCG/GCG could be used as a portable at-home CAD screening tool.

Early Detection of Parkinson's Disease Using Center of Pressure Data and Machine Learning.

Parkinson's disease (PD) is a progressive neurodegenerative disorder resulting in abnormal body movements. Postural instability is one of the primary motor symptoms of PD and contributes to falls. Measurement of postural sway through center of pressure (COP) data might be an objective indicator of Parkinson's disease. The goal of this work is to use machine learning to evaluate if different features of postural sway can differentiate PD patients from healthy controls. Time domain, frequency domain, time-frequency, and structural features were extracted from COP data collected from 19 PD patients and 13 healthy controls (HC). The calculated parameters were input to various machine-learning models to classify PD and HC. Random Forest outperformed the rest of the classifiers in terms of accuracy, false negative rate, F1-score, and precision. Time domain features had the best performance in differentiating PD from HC compared to other feature groups.

Handheld Multispectral Fluorescence Imaging System to Detect and Disinfect Surface Contamination.

Contamination inspection is an ongoing concern for food distributors, restaurant owners, caterers, and others who handle food. Food contamination must be prevented, and zero tolerance legal requirements and damage to the reputation of institutions or restaurants can be very costly. This paper introduces a new handheld fluorescence-based imaging system that can rapidly detect, disinfect, and document invisible organic residues and biofilms which may host pathogens. The contamination, sanitization inspection, and disinfection (CSI-D) system uses light at two fluorescence excitation wavelengths, ultraviolet C (UVC) at 275 nm and violet at 405 nm, for the detection of organic residues, including saliva and respiratory droplets. The 275 nm light is also utilized to disinfect pathogens commonly found within the contaminated residues. Efficacy testing of the neutralizing effects of the ultraviolet light was conducted for Aspergillus fumigatus, Streptococcus pneumoniae, and the influenza A virus (a fungus, a bacterium, and a virus, respectively, each commonly found in saliva and respiratory droplets). After the exposure to UVC light from the CSI-D, all three pathogens experienced deactivation (> 99.99%) in under ten seconds. Up to five-log reductions have also been shown within 10 s of UVC irradiation from the CSI-D system.

Effect of Blood Volume Shift Simulated via Head-up Tilt on Photoplethysmography Morphology.

PPG can provide information on cardiovascular responses to fluid shifts from upper to lower part of body under the condition of orthostatic stress. The current study investigated ability of PPG derived LVET and other PPG derived features to identify progressive central hypovolemia induced by head up tilt (HUT) and evaluated potential use of LVET as early noninvasive indicator of blood loss. Continuous finger PPG, blood pressure, and electrocardiography were recorded simultaneously during 5-minutes of baseline and HUT of 20°, 40°, and 60° from 15 participants (age: 26.5 ± 3 years; height: 177 ± 8 cm; weight: 72 ± 10 kg, mean ± SD). Beat-by-beat pulse rate (PR), systolic amplitude (SA), systolic time (ST), diastolic time (DT), and PP Interval (PPI) and Ratio of pulse rate over systolic amplitude (PR/SA) were derived for each stage. LVET was derived from each stage. Friedman test followed by post-hoc analysis using Tukey-HSD was conducted to highlight the significance of changes induced by HUT. Application of 60° HUT (i.e. moderate category simulated hypovolemia) resulted in a significant change in PR (80±3 bpm vs 68±3 bpm, p=0.0008), DT (264±7 ms vs 303±4 ms, p=0.0008), ST (110±6 ms vs 117±7 ms, p=0.02), PP interval (764±39 ms vs 869±25 ms, p=0.0045), PR/SA (112±16 vs 82±21, p=0.012) , SA (0.875± 0.2 vs 1.69±0.6, p=0.012) and LVET(292 vs 351ms,p=0.0008) compared to baseline. LVET has a strong association with the change in central blood volume and may be used as a sensitive early marker of progressive hypovolemia. The findings of the study support the hypothesis of differentiating simulated hypovolemia based on PPG alone. Keywords: Hypovolemia, HUT, LVET.