Osteoporosis constitutes a significant public health concern necessitating proactive prevention, treatment, and monitoring efforts. Timely identification holds paramount importance in averting fractures and alleviating the overall disease burden. The realm of osteoporosis diagnosis has witnessed a surge in interest in machine learning applications. This burgeoning technology excels at recognizing patterns and forecasting the onset of osteoporosis, paving the way for more efficacious preventive and therapeutic interventions. Smart walkers emerge as valuable tools in this context, serving as data acquisition platforms for datasets tailored to machine learning techniques. These datasets, trained to discern patterns indicative of osteoporosis, play a pivotal role in enhancing diagnostic accuracy. In this study, encompassing 40 participants—20 exhibiting robust health and 20 diagnosed with osteoporosis—data from force sensors embedded in the handlebars of conventional walkers were gathered. A windowing action was used to increase the size of the dataset. The data were normalized, and k-fold cross-validation was applied to assess how well our model performs on untrained data. We used multiple machine learning algorithms to create an accurate model for automatic monitoring of users’ gait, with the Random Forest classifier performing the best with 95.40% accuracy. To achieve the best classification accuracy on the validation dataset, the hyperparameters of the Random Forest classifier were further adjusted on the training data. The results suggest that machine learning-based automatic monitoring of gait parameters could lead to accurate, non-laborious, cost-effective, and efficient diagnostic tools for osteoporosis and other musculoskeletal disorders. Further research is needed to validate these findings.

Fragility fractures, caused by low-energy trauma, are a significant global health concern, with 158 million people aged 50 and over at risk. Hip fractures, a common issue in elderly patients, are often linked to underlying conditions such as osteoporosis. This study proposed a cost-effective solution using a non-wheeled smart walker with load sensors to measure gait parameters, addressing the high cost of traditional gait analysis equipment, the prototype used PASCO load cells PS2200 for force measurement, eliminating the need for Arduino UNO or microcontroller-based hardware. A lightweight amplifier PS2198 amplified the signal, which was transmitted via USB to a personal computer. PASCO capstone software was used for data recording and visualization. The smart walker was tested on forty volunteers divided into two equal groups: those with osteoporosis and those without, by performing a 10 m walk test three times. ANOVA comparing spatiotemporal parameters (TSPs) of the two participant groups (α = 0.05) showed that significant differences lay in terms of time taken to complete the walk test (p < 0.01), left step length (p = 0.03), walking speed (p = 0.02), and stride length (p < 0.02). The results indicate that this smart walker is a reliable tool for assessing gait patterns in individuals with osteoporosis. The proposed system can be an alternative for time consuming and costly methods such as motion capture, and for socially stigmatizing devices such as exoskeletons. It can also be used further to identify risk factors of osteoporosis.

Peptic ulcer (PU) has been recognized as an utmost gastrointestinal problem that affects the lining of the stomach and duodenum, specifically triggering soreness. It is a life-threatening condition, while roots of the infection are not identified yet. There are various risk factors for the cause of peptic ulcer disease, but the most significant is “Helicobacter pylori” (H. pylori). The detection of this disease involves different invasive procedures which are painful and not feasible for everyone. The aim of this device is to identify the peptic ulcer non-invasively by unmasking the presence of H. Pylori bacterium by monitoring crucial parameters of the disease which include respiration rate, heart rate, ECG, pH of Saliva, and temperature. Multiple investigations related to PU authenticate the alteration in these physicochemical aspects of the body. The increase in the level of stomach acid in PU is responsible for belching and bloating. Heart rate, temperature, and respiratory rate are also elevated during peptic ulcers while the pH of Saliva is decreased toward the acidic side. The disturbance in the QRS complex of the ECG wave is also observed. These biosignals are examined as analog input from the body, sent into MCP3008, and converted into digital input signals. Then these digital inputs are directed toward Raspberry pi 3 which processes, received inputs, and shows output on the LCD. The values of parameters obtained are then compared with standard values and a conclusion is made that whether a patient has a peptic ulcer or not.

Membrane proteins constitute essential biomolecules attached to or integrated into cellular and organelle membranes, playing diverse roles in cellular processes. Their precise localization is crucial for understanding their functions. Existing protein subcellular localization predictors are predominantly trained on globular proteins; their performance diminishes for membrane proteins, explicitly via deep learning models. To address this challenge, the proposed study segregates membrane proteins into three distinct locations, including the plasma membrane, internal membrane, and membrane of the organelle, using deep learning algorithms including recurrent neural networks (RNN) and Long Short-Term Memory (LSTM). A redundancy-curtailed dataset of 3000 proteins from the MemLoci approach is selected for the investigation, along with incorporating pseudo amino acid composition (PseAAC). PseAAC is an exemplary technique for extracting protein information hidden in the amino acid sequences. After extensive testing, the results show that the accuracy for LSTM and RNN is 83.4% and 80.5%, respectively. The results show that the LSTM model outperforms the RNN and is most commonly employed in proteomics.