Abstract Background Cardiovascular and thromboembolic complications remain a major burden in diabetes. We aimed to determine whether peripheral thermometry is suited to detect plantar temperature downshifts (PTDs). Plantar infrared images (PIRIs) and sensor recordings were correlated with atrial fibrillation (AF) and thromboembolic events in patients with diabetes. Methods A secondary analysis of the SmartPreventDiabeticFeet study including 239 patients monitored by PIRIs and sensor-equipped insoles (median follow-up 67.1 months) was conducted. In a structured telephone survey, histories of AF and thromboembolic events (stroke, pulmonary embolism [PE], peripheral arterial disease [PAD]) were captured from enrollment to post-intervention period. Patients with >30 days of temperature recordings ( n = 118) were classified according to pre-specified PTD definitions, unsupervised clustering of bilateral plantar temperature variability, and plantar infrared image symmetry. Associations were tested using χ² or Fisher’s exact tests and multivariable logistic/Cox models. Results Our findings show that PTDs in sensor recordings as well as PIRI asymmetry are associated with a higher incidence of a composite of AF and thromboembolic events. Overall, 45 patients experience AF ( n = 26), stroke ( n = 6), PE ( n = 4) or PAD ( n = 11). Event rates are higher in patients with PTDs (25.8% vs 11.5%; p = 0.09; exploratory trend). For the elevated temperature variability cluster, the adjusted OR reaches 13.5 [95% CI 3.8–58.6] (34.0% vs 9.9%; p = 0.003; adjusted HR 13.3 [95% CI 1.5–120.4]). In individuals with plantar infrared image asymmetry, the likelihood is 48.6% compared to 6.2% in the symmetry group ( p < 0.0001). Conclusions In patients with diabetes, plantar temperature downshifts are associated with thromboembolic risk constellation.

Background:Detecting peripheral neuropathy (PNP) is crucial in preventing complications such as foot ulceration. Clinical examinations for PNP are infrequently provided to patients at high risk due to restrictions on facilities, care providers, or time. A gamified health assessment approach combining wearable sensors holds the potential to address these challenges and provide individuals with instantaneous feedback on their health status. Objective:We aimed to develop and evaluate an application that assesses PNP through video games controlled by pressure sensor-equipped insoles. Methods:In the proof-of-concept exploratory cohort study, a complete game-based framework that allowed the study participant to play 4 video games solely by modulating plantar pressure values was established in an outpatient clinic setting. Foot plantar pressures were measured by the sensor-equipped insole and transferred via Bluetooth to an Android tablet for game control in real time. Game results and sensor data were delivered to the study server for visualization and analysis. Each session lasted about 15 minutes. In total, 299 patients with diabetes mellitus and 30 with metabolic syndrome were tested using the game application. Patients' game performance was initially assessed by hypothesis-driven key capabilities that consisted of reaction time, sensation, skillfulness, balance, endurance, and muscle strength. Subsequently, specific game features were extracted from gaming data sets and compared with nerve conduction study findings, neuropathy symptoms, or disability scores. Multiple machine learning algorithms were applied to 70% (n=122) of acquired data to train predictive models for PNP, while the remaining data were held out for final model evaluation. Results:Overall, clinically evident PNP was present in 247 of 329 (75.1%) participants, with 88 (26.7%) individuals showing asymmetric nerve deficits. In a subcohort (n=37) undergoing nerve conduction study as the gold standard, sensory and motor nerve conduction velocities and nerve amplitudes in lower extremities significantly correlated with 79 game features (|R|>0.4, highest R value +0.65; P<.001; adjusted R-2=0.36). Within another subcohort (n=173) with normal cognition and matched covariates (age, sex, BMI, etc), hypothesis-driven key capabilities and specific game features were significantly correlated with the presence of PNP. Predictive models using selected game features achieved 76.1% (left) and 81.7% (right foot) accuracy for PNP detection. Multiclass models yielded an area under the receiver operating characteristic curve of 0.76 (left foot) and 0.72 (right foot) for assessing nerve damage patterns (small, large, or mixed nerve fiber damage). Conclusions:The game-based application presents a promising avenue for PNP screening and classification. Evaluation in expanded cohorts may iteratively optimize artificial intelligence model efficacy. The integration of engaging motivational elements and automated data interpretation will support acceptance as a telemedical application.

BackgroundDetecting peripheral neuropathy (PNP) is crucial in preventing complications such as foot ulceration. Clinical examinations for PNP are infrequently provided to patients at high risk due to restrictions on facilities, care providers, or time. A gamified health assessment approach combining wearable sensors holds the potential to address these challenges and provide individuals with instantaneous feedback on their health status. ObjectiveWe aimed to develop and evaluate an application that assesses PNP through video games controlled by pressure sensor–equipped insoles. MethodsIn the proof-of-concept exploratory cohort study, a complete game-based framework that allowed the study participant to play 4 video games solely by modulating plantar pressure values was established in an outpatient clinic setting. Foot plantar pressures were measured by the sensor-equipped insole and transferred via Bluetooth to an Android tablet for game control in real time. Game results and sensor data were delivered to the study server for visualization and analysis. Each session lasted about 15 minutes. In total, 299 patients with diabetes mellitus and 30 with metabolic syndrome were tested using the game application. Patients’ game performance was initially assessed by hypothesis-driven key capabilities that consisted of reaction time, sensation, skillfulness, balance, endurance, and muscle strength. Subsequently, specific game features were extracted from gaming data sets and compared with nerve conduction study findings, neuropathy symptoms, or disability scores. Multiple machine learning algorithms were applied to 70% (n=122) of acquired data to train predictive models for PNP, while the remaining data were held out for final model evaluation. ResultsOverall, clinically evident PNP was present in 247 of 329 (75.1%) participants, with 88 (26.7%) individuals showing asymmetric nerve deficits. In a subcohort (n=37) undergoing nerve conduction study as the gold standard, sensory and motor nerve conduction velocities and nerve amplitudes in lower extremities significantly correlated with 79 game features (|R|>0.4, highest R value +0.65; P<.001; adjusted R2=0.36). Within another subcohort (n=173) with normal cognition and matched covariates (age, sex, BMI, etc), hypothesis-driven key capabilities and specific game features were significantly correlated with the presence of PNP. Predictive models using selected game features achieved 76.1% (left) and 81.7% (right foot) accuracy for PNP detection. Multiclass models yielded an area under the receiver operating characteristic curve of 0.76 (left foot) and 0.72 (right foot) for assessing nerve damage patterns (small, large, or mixed nerve fiber damage). ConclusionsThe game-based application presents a promising avenue for PNP screening and classification. Evaluation in expanded cohorts may iteratively optimize artificial intelligence model efficacy. The integration of engaging motivational elements and automated data interpretation will support acceptance as a telemedical application.

Background Fall(s) are a significant cause of morbidity and mortality especially amongst elderly with polyneuropathy and cognitive decline. Conventional fall risk assessment tools are prone to low predictive values and do not address specific vulnerabilities. This study seeks to advance the development of an innovative, engaging fall prediction tool for a high-risk cohort diagnosed with diabetes. Methods In this proof-of-concept cohort study, between July 01, 2020, and May 31, 2022, 152 participants with diabetes performed clinical examinations to estimate individual risks of fall (timed " up and go" (TUG) test, dynamic gait index (DGI), Berg-Balance-Scale (BBS)) and participated in a video game-based fall risk assessment with sensor-equipped insoles as steering units. The participants engaged in four distinct video games, each designed to address capabilities pertinent to prevent fall(s): skillfulness, reaction time, sensation, endurance, balance, and muscle strength. Data were collected during both, seated and standing gaming sessions. By data analyses using binary machine learning models a classification of participants was achieved and compared with actual fall events reported for the past 24 months. Findings Overall 22 out of 152 participants (14.5%) underwent at least one episode of fall during the past 24 months. Adjusted risk classification accuracies of TUG, DGI, and BBS reached 58.7%, 58.3%, and 47.5%, respectively. Data analyses from gaming sessions in seated and standing positions yielded two models with six predictors from the four games with accuracies of 82.8% and 88.6% (area under the receiver-operating-characteristic curve 0.84 (95% confidence interval (CI): 0.77-0.91) and 0.91 (95% CI: 0.85-0.97), respectively). Key capabilities that were distinctly different between the groups related to endurance (0.6 +/- 0.1 vs. 0.5 +/- 0.2; p = 0.03) and balance (0.7 +/- 0.2 vs. 0.6 +/- 0.2; p = 0.05). The AI-driven analysis allowed to extract a list of game features that showed highly significant predictive values, e.g., reaction times in specific task, deviation from ideal steering routes in parcours and pressure-related parameters. Interpretation Thus, video game-based assessment of fall risk surpasses traditional clinical assessment tools and scores (e.g., TUG, DGI, and BBS) and may open a novel resource for patient evaluation in the future. Further research with larger, heterogeneous cohorts is needed to validate these fi ndings and especially predict future fall risk probabilities in clinical as well as outpatient settings.

BackgroundProactive screening for cognitive dysfunction (CD) and peripheral neuropathy (PNP) in elderly patients with diabetes mellitus is essential for early intervention, yet clinical examination is time-consuming and prone to bias.ObjectiveWe aimed to investigate PNP and CD in a diabetes cohort and explore the possibility of identifying key features linked with the respective conditions by machine learning algorithms applied to data sets obtained in playful games controlled by sensor-equipped insoles.MethodsIn a cohort of patients diagnosed with diabetes (n=261) aged over 50 years PNP and CD were diagnosed based on complete physical examination (neuropathy symptom and disability scores, and Montreal Cognitive Assessment). In an observational and proof-of-concept study patients performed a 15 min lasting gaming session encompassing tutorials and four video games with 5,244 predefined features. The steering of video games was solely achieved by modulating plantar pressure values, which were measured by sensor-equipped insoles in real-time. Data sets were used to identify key features indicating game performance with correlation regarding CD and PNP findings. Thereby, machine learning models (e.g. gradient boosting and lasso and elastic-net regularized generalized linear models) were set up to distinguish patients in the different groups.ResultsPNP was diagnosed in 59% (n=153), CD in 34% (n=89) of participants, and 23% (n=61) suffered from both conditions. Multivariable regression analyses suggested that PNP was positively associated with CD in patients with diabetes (adjusted odds ratio = 1.95; 95% confidence interval: 1.03-3.76; P=0.04). Predictive game features were identified that significantly correlated with CD (n=59), PNP (n=40), or both (n=59). These features allowed to set up classification models that were enriched by individual risk profiles (i.e. gender, age, weight, BMI, diabetes type, and diabetes duration). The obtained models yielded good predictive performance with the area under the receiver-operating-characteristic curves reaching 0.95 for CD without PNP, 0.83 for PNP without CD, and 0.84 for CD and PNP combined.ConclusionsThe video game-based assessment was able to categorize patients with CD and/or PNP with high accuracy. Future studies with larger cohorts are needed to validate these results and potentially enhance the discriminative power of video games.

Background: The worldwide prevalence of diabetic foot ulcers (DFUs) among persons with diabetes is estimated at 6.3%, with an annual incidence of 9.1 to 26.1 million persons. The early detection of asymmetrical plantar temperature elevation, followed by reduction of weight -bearing on the affected foot, may be an effective mode of prevention. Methods: Patients with diabetes and peripheral neuropathy (DFU risk groups 2/3) were monitored for plantar abnormalities with a telemedical system consisting of sole inserts with temperature sensors and photographic documentation. An open, prospective, randomized controlled trial was performed to determine whether this system prevented DFUs. The intervention and control groups were also trained in ulcer prevention and observed in follow-up at 6 -month intervals for 24 months. Results: 283 patients were recruited. In 85 137 observation days, DFUs arose in five patients in the control group (n = 143) and in no patient in the intervention group (n = 140). The primary outcome measure was the hazard ratio, which was calculated to be 0.015 (95% confidence interval [0; 19,717]; p = 0.25) after adjustment for age, sex, severity of neuropathy, and risk class. There were 239 alarms and 75 instructions to reduce weight -bearing on the foot. The subjects carried out the telemedical application on about 70% of the days of observation. Quality of life improved in both groups. Conclusion: The tele -health system used in this trial is practical and enables the early detection of morbidity. Likely explanations for the unexpectedly low ulceration rate in this trial (and, in turn, for the lack of statistical significance) include the availability of a training program and regular follow-up examinations to patients in both arms of the trial, along with lower mobility levels due to the COVID pandemic.

The worldwide prevalence of diabetic foot ulcers (DFUs) among persons with diabetes is estimated at 6.3%, with an annual incidence of 9.1 to 26.1 million persons. The early detection of asymmetrical plantar temperature elevation, followed by reduction of weight-bearing on the affected foot, may be an effective mode of prevention.

Clinical trials are essential for advancements in the medical field. The study subjects of clinical trials agree that the data may be used within the scope of the clinical trial and they trust the study center to not misuse the data. Limiting access and anonymizing the data is usually the only way of offering privacy to the subjects. Currently, the collected data may only be used within the scope of the respective study, and in the case of external entities evaluating the data, potential privacy risks occur. To improve the situation, we investigated the applicability of Differential Privacy approaches for clinical trials by looking into differentially private queries as well as differentially private Machine-Learning approaches. Different configurations have been tested for two Differential Privacy mechanisms. The Laplacian Mechanism is much more influenced by the chosen epsilon compared to the Functional Mechanism implemented in this study. However, both mechanisms trade accuracy for privacy. In summary, both queries and Machine Learning can be made secure by applying differential privacy approaches, but the implementation and configuration overhead is still likely to exceed the capacity of clinical trials, especially the smaller ones. Keywords-Differential Privacy; Clinical Trial; Sensor Data; Machine Learning; Privacy Preservation; Data Security.

Background: Microcirculatory defects in diabetes are linked with neuropathy and the onset of diabetic foot syndrome. In this study we quantify pressure- and posture-dependent changes of plantar temperatures as a surrogate of tissue perfusion in healthy volunteers versus diabetes patients diagnosed with neuropathy in the absence of macroangiopathy. Methods: Healthy volunteers (n = 31) as well as patients with diabetes diagnosed with severe polyneuropathy (n = 30) were enrolled in a clinical study to test for plantar temperature changes in the feet during extended episodes of standing. These lasted between 5 and 20 min each over 95 min, in between the participants were asked to take a seated position for 5 min and release the pressure from the feet. Major macroangiopathy was excluded before study enrolment. Custom-made insoles harbored temperature and pressure sensors positioned at eight preselected positions for recording. Findings: In both subgroups a significant plantar temperature downshift occurred within 10 min of standing, which was especially detected during the initial 45 min of the study protocol. Comparisons between healthy volunteers and patients with diabetes revealed no differences in the magnitude of temperature downshifts during stance episodes. Pressure sensor recordings revealed that healthy volunteers intermittently released pressure during the longer stance episodes due to discomfort, whereas the patients with diabetes and polyneuropathy did not. Interpretation: Our findings demonstrate a tight plantar temperature regulation following pressure exposure. In patients with diabetes and peripheral sensoric neuropathy the temperature drop is similar to healthy volunteers. Potentially, prolonged stance periods resulting in less perfused plantar tissue may remain unrecognized with polyneuropathy, whereas discomfort develops in healthy controls. (C) 2020 The Author( s). Published by Elsevier B.V.

•The overall peripheral neuropathy prevalence among patients with diabetes is high (40.3%) and patients with type 2 diabetes (42.2%) are more often affected than those with type 1 diabetes (29.1%).•DPN prevalence increases with age and diabetes duration and is already high (35.0%) following type 2 diabetes diagnosis.•major DPN risk factors are “older age” and loss of consciousness due to severe hypoglycemia episodes among patients with type 1 diabetes as well as “older age” and an adverse cardiovascular-metabolic profile (obesity, hypertension, low HDL-c levels, elevated triglycerides, low physical activity and limited range of motion) among patients with type 2 diabetes.•diabetes micro- and macrovascular co-morbidities (diabetic nephropathy, retinopathy and peripheral artery disease) are strongly associated with the incidence of neuropathy.

Early detection of diabetic foot ulcerations (DFUs) can avoid or delay any progression into more severe stages, which may require limb amputation or lead to infectious sequelae and death. However, frequent clinical screening would be too intrusive and costly, and self-examination may be hampered by concomitant diseases and social disabilities. In addition, it requires professional knowledge and experience using specialized devices. Researchers reported that skin temperature monitoring could reduce the risk of DFUs in high-risk patients. The main research objects in this field are effective and convenient means of temperature measurement, accurate and reasonable early warning mechanisms, and timely and appropriate interventions. This trial aims to investigate the effectiveness of daily home-based foot temperature measurements in the prevention of DFUs with the aid of intelligent sensor-equipped insoles combined with photo documentation. In this open-label, prospective, randomized, 24-month trial, 300 patients with diabetes mellitus (type 1 or 2) and severe diabetic peripheral neuropathy (vibration sensation ≤ 4/8), aged 18–85 years, will be recruited and assigned to control and intervention groups in a ratio of 1:1. Main inclusion criteria to be eligible for study participation encompass in particular risk group 2 or 3 for the development of DFUs using the diabetic foot risk classification system (as specified by the International Working Group on the Diabetic Feet [IWGDF]) and the ability to use a mobile phone. Participants in both groups will receive education about regular foot care at the beginning of the study (visit 0). In the intervention group, every patient will receive a pair of slippers with the inserted sensor-equipped insole as well as a smartphone with the corresponding smartphone application (Smart Prevent Diabetic Feet Application). The insole is a tool that records the temperature variabilities of the plantar foot. Patients will measure their foot temperature twice a day at home with a time interval > 4 h during the entire course of the study (24 months). The measured data will be initially analyzed and visualized, and further transferred to a remote server that allows the physician to perform specific interpretations. In case of temperature differences > 1.5 °C between left and right corresponding sites lasting > 32 h (assigned alarm level 4), the physician will start an intervention phase, which requires the patient to reduce daily activities and relax his feet for five days. At the same time, photo documentation is encouraged to be performed by the patient. Possibly, additional visits to a private doctor or clinical examinations will be arranged for the patient during this intervention period. Outcomes: The primary outcome is foot ulceration, evaluated by a physician, and occurring at any point during the study. This study addresses principal aspects in the prevention of DFUs. First, the sensor-equipped insole will be evaluated for daily performance in home-based measurements of foot temperatures. Second, a telemedicine structure is tested that evaluates sensor data automatically and proposes suitable intervention measures under the supervision of a physician. Third, predictive models for DFUs will be built using the collected sensor data allowing for interpretations, which in the future may support medical care providers. German Clinical Trials Register (DRKS), DRKS00013798 . Registered on 18 January 2018.

Diabetic foot syndrome is a frequent and serious complication occurring among patients with diabetes. In this study, we investigate the potential of intelligent wearables that monitor temperature changes of the foot surface through temperature sensors. In particular, we are interested in identifying differences between the temperature variations recorded on patients with the disorder and healthy people during an experiment. To this purpose, we propose a method that encompasses shapelet-based timeseries classification and shapelet ranking on predictiveness. We report on our results for an experiment consisting of stance and rest periods of increasing duration.

The diabetic foot syndrome (DFS) is linked to loss of neuron functions, implying that the patients do not feel their feet and may unknowingly injure themselves or apply excessive plantar pressure. Such patients are at 17-40 times higher risk of foot amputation than non-diabetics. Sensor-equipped insoles are being developed to warn diabetics against inadverted excessive pressure. For the successful use of such technology, it is essential to understand how patients distribute plantar pressure load and to identify common pressure patterns, to be later used as basis for recognizing abnormalities. In this study, we propose a mining workflow for the discovery of pressure patterns among DFS patients. Our approach encompasses different ways of modeling pressure distribution among foot regions, and workpaths for the computation of similarity between patients and the construction of clusters of patients who apply pressure on their feet the same way. We report on our findings from a dataset of experiment participants who wore sensor-equipped insoles and were asked to apply and release pressure repeatedly over a time period of several minutes. We elaborate on the pressure patterns thus identified and juxtapose them to findings from the literature.

In diabetic patients, excessive peak plantar pressure has been identified as major risk factor for ulceration. Analyzing plantar pressure distributions potentially improves the identification of patients with a high risk for foot ulceration development. The goal of this study was to classify regional plantar pressure distributions. By means of a sensor-equipped insole, pressure recordings of healthy controls (n = 18) and diabetics with severe polyneuropathy (n = 25) were captured across eight foot regions. The study involved a controlled experimental protocol with multiple sessions, where a session contained several cycles of pressure exposure. Clustering was used to identify subgroups of study participants that are characterized by similar pressure distributions. For both analyzed groups, the number of clusters to best describe the pressure profiles was four. When both groups were combined, analysis again led to four distinct clusters. While three clusters did not separate between healthy and diabetic volunteers the fourth cluster was only represented by diabetics. Here the pressure distribution pattern is characterized by a focal point of pressure application on the forefoot and low pressure on the lateral region. Our data suggest that pressure clustering is a feasible means to identify inappropriate biomechanical plantar stress.

Message from General Chairs ...................................................................................................................xi Message from Program Chairs.................................................................................................................xii Conference Organization..........................................................................................................................xiii Program Committee..................................................................................................................................xiv Keynotes....................................................................................................................................................xvi