Assessing mobility in daily life can provide significant insights into several clinical conditions, such as Chronic Obstructive Pulmonary Disease (COPD). In this paper, we present a comprehensive analysis of wearable devices’ performance in gait speed estimation and explore optimal device combinations for everyday use. Using data collected from smartphones, smartwatches, and smart shoes, we evaluated the individual capabilities of each device and explored their synergistic effects when combined, thereby accommodating the preferences and possibilities of individuals for wearing different types of devices. Our study involved 20 healthy subjects performing a modified Six-Minute Walking Test (6MWT) under various conditions. The results revealed only little performance differences among devices, with the combination of smartwatches and smart shoes exhibiting superior estimation accuracy. Particularly, smartwatches captured additional health-related information and demonstrated enhanced accuracy when paired with other devices. Surprisingly, wearing all devices concurrently did not yield optimal results, suggesting a potential redundancy in feature extraction. Feature importance analysis highlighted key variables contributing to gait speed estimation, providing valuable insights for model refinement.

Dielectric elastomer generators (DEGs) are electrostatic transducers capable of harvesting electrical energy from oscillating mechanical parts and storing it in a battery or supercapacitor. The energy conversion element typically consists of a flexible capacitor with a variable capacitance that depends on the applied stress cycle and requires an external voltage source (bias voltage). In designing an energy harvesting device from human gait, we propose integrating two components: a dielectric elastomer fabricated using a nanocomposite polyurethane (TPU-CaCu₃Ti₄O₁₂) and an electret serving as a bias voltage source. In this work, we report on the electret fabrication and long-term charge retention properties using corona charging. The manufactured electrets are tested in coupling with the dielectric elastomer and allowed us to harvest an energy amount of 62 µJ/cycle (3.1 µJ/cm²) on a resistive load of 450 MΩ during motion cycles at a frequency of 0.5 Hz. Given the materials used, this approach is well suited to harvesting energy from human gait and holds promise for powering wearable devices.

Background: Lung cancer (LC) is the leading cause of cancer death worldwide. Non‐small cell lung cancer is the most frequent and includes adenocarcinoma and squamous cell carcinoma. Currently, LC treatment is based on tumor molecular profiling. LC may display Epidermal Growth Factor Receptor (EGFR) gene mutation. Detecting mutations in the EGFR gene is crucial for the tyrosine kinase inhibitory therapy. Methods: This study used a computer‐based methodology with two Convolutional Neural Networks (CNNs) based on InceptionResNet‐V2, applied to Whole Slide Images, to distinguish healthy from cancerous tissue and then EGFR mutated tumor tissue samples. We also integrated an Explainable AI technique (Grad‐CAM) to clearly visualize insights into the model's decision‐making process. The analysis was conducted on 259 LC cases collected from three different centers (Florence, Rome, and Sassari). Results: This methodology achieved an accuracy of 96.17% in distinguishing healthy from cancerous tissue, with specificity of 87.89%, sensitivity of 98.43%, an F1 score of 97.59% and an AUC of 0.99. Additionally, Cohen's Kappa indicated a consistency of 0.7982, and the confusion matrix showed a correct classification rate of 96.2%. For EGFR mutation detection in cancer tissue, slide‐level performance after aggregation reached an accuracy of 76.67% with specificity of 80.77%, sensitivity of 73.53%, an F1 score of 78.12%, a consistency of 0.5583 of Cohen's Kappa and an AUC of 0.77. The confusion matrix showed 76.7% as a correct classification rate. Conclusion: The two tested CNNs showed potential for assisting LC diagnosis, especially in distinguishing healthy from tumor tissue. While the direct detection of EGFR mutational status remains challenging, the results suggest that relevant predictive signals can still be extracted from routine H&E slides.

Real-world gait speed assessment, has recently gained recognition as an important health indicator particularly in patients with chronic conditions such as Chronic Obstructive Pulmonary Disease (COPD). This study proposes an AI-based method for estimating gait speed in the real-world context in COPD patients using different combinations of three wearable devices: a smartphone, a smartwatch, and a pair of sensorized shoes. An analysis pipeline is developed and trained using laboratory datasets, then validated on an independent dataset acquired under free-walking conditions, demonstrating strong performance in both walking detection and gait speed estimation with mean accuracies across different device combinations of 0.81, 0.93, and 0.90 for resting, walking, and stair climbing activities, respectively, as well as a mean RMSE of 0.118 m/s and an ICC of 0.80. The estimated speed, obtained by applying the developed pipeline to daily life data of COPD patients, showed a strong and significant correlation with the clinical standard of functional capacity, the six-minutes walking distance (6MWD) across 34 patients (Spearman coefficient = 0.854, p-value = 1.38e-10). These findings highlight the feasibility of unobtrusive, continuous gait speed monitoring in real-life conditions, offering a promising integrative tool to traditional clinical assessments. The results suggest that wearable-based mobility monitoring could enhance remote patient management and personalized care strategies for COPD and other chronic conditions.

Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality worldwide, with progressive lung function decline severely affecting patients' quality of life. Spirometric assessment, particularly Forced Expiratory Volume in one second as a percentage of predicted (FEV1% predicted), is central to monitoring disease progression but is often impractical for regular use due to its invasive and burdensome nature. This study explores an alternative approach for predicting longitudinal changes in FEV1% predicted using passive data collected via wearable sensors and demographic variables. Utilizing data from 423 patients in the COSYCONET cohort, physical activity metrics - such as accelerometer readings, step counts, and energy expenditure - were processed from one-week recordings. After constructing paired observations to reflect FEV1 changes between clinical visits, the problem was reformulated as a binary classification task (improvement vs. worsening). Principal Component Analysis was used for dimensionality reduction, followed by training six classification models. Naive Bayes and Quadratic Discriminant Analysis (QDA) achieved the highest overall accuracy, with k-Nearest Neighbors (k-NN) offering the best sensitivity. Results suggest that non-linear and non-parametric models are more suitable for capturing the complexity of COPD progression. However, performance remains modest, likely due to the simplistic binary threshold applied to FEV1 changes. Future research should focus on refining thresholds to better reflect clinically meaningful variations and improve model precision.

Real-world gait speed assessment, has recently gained recognition as an important health indicator particularly in patients with chronic conditions such as Chronic Obstructive Pulmonary Disease (COPD). This study proposes an AI-based method for estimating gait speed in the real-world context in COPD patients using different combinations of three wearable devices: a smartphone, a smartwatch, and a pair of sensorized shoes. An analysis pipeline is developed and trained using laboratory datasets, then validated on an independent dataset acquired under free-walking conditions, demonstrating strong performance in both walking detection and gait speed estimation. The estimated speed, obtained by applying the developed pipeline to daily life data of COPD patients, showed a strong and significant correlation with the clinical measures of six-minutes-walking-distance (6MWD) across 34 patients (Spearman coefficient = 0.854, p-value = 1.38e-10). These findings highlight the feasibility of unobtrusive, continuous gait speed monitoring in real-life conditions, offering a promising integrative tool to traditional clinical assessments. The results suggest that wearablebased mobility monitoring could enhance remote patient management and personalized care strategies for COPD and other chronic conditions.