Parkinson's disease (PD) is a progressive neurodegenerative disorder that impacts motor functions and speech characteristics This study focuses on differentiating individuals with Parkinson's disease from healthy controls through the extraction and classification of speech features. Patients were further divided into 2 groups. Med On represents the patient with medication, while Med Off represents the patient without medication. The dataset consisted of patients and healthy individuals who read a predefined text using the H1N Zoom microphone in a suitable recording environment at F{\i}rat University Neurology Department. Speech recordings from PD patients and healthy controls were analyzed, and 19 key features were extracted, including jitter, luminance, zero-crossing rate (ZCR), root mean square (RMS) energy, entropy, skewness, and kurtosis.These features were visualized in graphs and statistically evaluated to identify distinctive patterns in PD patients. Using MATLAB's Classification Learner toolbox, several machine learning classification algorithm models were applied to classify groups and significant accuracy rates were achieved. The accuracy of our 3-layer artificial neural network architecture was also compared with classical machine learning algorithms. This study highlights the potential of noninvasive voice analysis combined with machine learning for early detection and monitoring of PD patients. Future research can improve diagnostic accuracy by optimizing feature selection and exploring advanced classification techniques.

Wearable medical sensors (WMSs) are revolutionizing smart healthcare by enabling continuous, real-time monitoring of user physiological signals, especially in the field of consumer healthcare. The integration of WMSs and modern machine learning (ML) enables unprecedented solutions to efficient early-stage disease detection. Despite the success of Transformers in various fields, their application to sensitive domains, such as smart healthcare, remains underexplored due to limited data accessibility and privacy concerns. To bridge the gap between Transformer-based foundation models and WMS-based disease detection, we propose COMFORT, a continual fine-tuning framework for foundation models targeted at consumer healthcare. COMFORT introduces a novel approach for pre-training a Transformer-based foundation model on a large dataset of physiological signals exclusively collected from healthy individuals with commercially available WMSs. We adopt a masked data modeling (MDM) objective to pre-train this health foundation model. We then fine-tune the model using various parameter-efficient fine-tuning (PEFT) methods, such as low-rank adaptation (LoRA) and its variants, to adapt it to various downstream disease detection tasks that rely on WMS data. In addition, COMFORT continually stores the low-rank decomposition matrices obtained from the PEFT algorithms to construct a library for multi-disease detection. The COMFORT library enables scalable and memory-efficient disease detection on edge devices. Our experimental results demonstrate that COMFORT achieves highly competitive performance while reducing memory overhead by up to 52% relative to conventional methods. Thus, COMFORT paves the way for personalized and proactive solutions to efficient and effective early-stage disease detection for consumer healthcare.

Assessing the quality of movements for post-stroke patients during the rehabilitation phase is vital given that there is no standard stroke rehabilitation plan for all the patients. In fact, it depends basically on the patient's functional independence and its progress along the rehabilitation sessions. To tackle this challenge and make neurorehabilitation more agile, we propose an automatic assessment pipeline that starts by recognising patients' movements by means of a shallow deep learning architecture, then measuring the movement quality using jerk measure and related measures. A particularity of this work is that the dataset used is clinically relevant, since it represents movements inspired from Fugl-Meyer a well common upper-limb clinical stroke assessment scale for stroke patients. We show that it is possible to detect the contrast between healthy and patients movements in terms of smoothness, besides achieving conclusions about the patients' progress during the rehabilitation sessions that correspond to the clinicians' findings about each case.

Why do some people live longer, healthier, and more active lives while others their same age struggle with lifelong chronic pain and suffer maladies up to their dying day--which comes much earlier than others? This basic longevity question has been nagging physicians for ages. The importance of lifestyle factors such as diet, exercise, stress, and epigenetic processes like lifestyle and exposure to environmental hazards have been called into account to explain this divergence, and now a team of researchers from Stanford's Cardiovascular Institute Division of Vascular Surgery and the Buck Institute for Research on Aging believes they found the answer. Rather than the biological age, they say a better predictor of health and longevity is a person's inflammation age. Aided by artificial intelligence and machine learning, the researchers have concluded that epigenetic effects of inflammation processes, particularly on the cardiovascular and neurological level, are connected with much of the morbidity and mortality associated with aging.

Massachusetts Institute of Technology researchers have found that people who are asymptomatic for Covid-19 may differ from healthy individuals in the way that they cough, which can be captured by artificial intelligence. Massachusetts Institute of Technology (MIT) researchers have developed an artificial intelligence model that differentiates between asymptomatic people infected with Covid-19 and healthy individuals via forced-cough recordings submitted through Web browsers, cellphones, and laptops. The MIT team trained the model on cough samples and spoken words; it accurately identified 98.5% of coughs from people confirmed to have the virus (100% from those who are asymptomatic) when fed new cough recordings. The researchers are incorporating the model into a user-friendly application which could potentially be a free, convenient, noninvasive prescreening tool to identify asymptomatic people infected with the virus. Users could log in daily, cough into their handset, and instantly receive information on whether they might be infected and confirm with a formal test.

For years scientists have sought to create the ultimate cancer-screening test--one that can reliably detect a malignancy early, before tumor cells spread and when treatments are more effective. A new method reported today in Nature Communications brings researchers a step closer to that goal. By using a blood test, the international team was able to diagnose cancer long before symptoms appeared in nearly all the people it tested who went on to develop cancer. "What we showed is: up to four years before these people walk into the hospital, there are already signatures in their blood that show they have cancer," says Kun Zhang, a bioengineer at the University of California, San Diego, and a co-author of the study. "That's never been done before."

Dyspnoea, shortness of breath and coughing are just a few of the potential symptoms of asthma. Those affected suffer sudden attacks of bronchial constriction. Identifying the disease quickly is crucial, as that is the only way as to lower the threat of asthma attacks, which can even be fatal. It is particularly important to identify the disease early in children in order to quickly intervene and alleviate the symptoms. However, diagnosing children is more complicated and tedious than diagnosing adults.

Here we apply machine learning techniques over magnetic resonance images (MRIs) of the brain of healthy individuals to predict who is harboring abnormal amyloid levels. The method has been trained and tested on two independent cohorts using cerebrospinal fluid levels of amyloid as gold-standard. Predictive capacity is modest (AUC 0.76), but used as a pre-screening tool, it has a notable impact since can cut down to half the burden to detect healthy individuals at risk of Alzheimer's. Healthy individuals harboring amyloid protein in the brain are at increased risk of developping Alzheimer's and could benefit from secondary preventive interventions. However, gold-standard techniques for amyloid are not suitable for screening the general population.