The use of radiomics and artificial intelligence applied for the diagnosis and monitoring of Alzheimer’s disease has developed in recent years. However, this approach is not yet completely applicable in clinical practice. The aim of this paper is to provide a systematic analysis of the studies that have included the use of radiomics from different imaging techniques and artificial intelligence for the diagnosis and monitoring of Alzheimer’s disease in order to improve the clinical outcomes and quality of life of older patients. A systematic review of the literature was conducted in February 2023, analyzing manuscripts and articles of the last 5 years from the PubMed, Scopus and Embase databases. All studies concerning discrimination among Alzheimer’s disease, Mild Cognitive Impairment and healthy older people performing radiomics analysis through machine and deep learning were included. A total of 15 papers were included. The results showed a very good performance of this approach in the differentiating Alzheimer’s disease patients—both at the dementia and pre-dementia phases of the disease—from healthy older people. In summary, radiomics and AI can be valuable tools for diagnosing and monitoring the progression of Alzheimer’s disease, potentially leading to earlier and more accurate diagnosis and treatment. However, the results reported by this review should be read with great caution, keeping in mind that imaging alone is not enough to identify dementia due to Alzheimer’s.

(1) Background: Parkinson’s Disease (PD) is one of the most common causes of disability among older individuals. The advanced stages of PD are usually characterized by postural instability and, as a consequence, falls. Those are among the main factors that determine the quality of life, as well as the morbidity and mortality of a person with PD. In the field of PD rehabilitation, robotics is also rapidly gaining ground. As a primary aim, we evaluate the acceptability of the technology integrated intervention, using the Psychosocial Impact of Assistive Devices Scale (PIADS), in order to analyze the attitude of the participants towards the Tymo^® system. As a secondary outcome, we assess the result of the rehabilitation treatment integrated with the Tymo^® system on several patient’s features. (2) Methods: We studied a population of 16 patients with Parkinson’s Disease. Each recruited subject completed 10 treatment sessions, organized as two training sessions per week, for 5 weeks. The intervention included 30 min of traditional therapy and 20 min of technological treatment with a robotic system. PIADS is composed of three subscales (Competence subscale, Adaptability subscale, Self-esteem subscale) ranging from −3 to +3, reflecting, respectively, a negative or positive feeling towards the device. (3) Results: The Competence subscale, measuring feelings of competence and usefulness, obtained a score of 1.24 (SD = 0.78). The score of Adaptability subscale, indicating a willingness to try out new things and to take risks, was 1.83 (SD = 0.65). Finally, the Self-esteem subscale, indicating feelings of emotional health and happiness, reached a score of 1.31 (SD = 0.72). Moreover, statistical analysis reveals a significant effect on balance performance after intervention. (4) Conclusions: This feasibility study represents a starting point in the use of technology in the rehabilitation pathway of patients affected by Parkinson’s Disease. In fact, our results suggest that a standard therapy combined with an innovative treatment using Tymo^® may be accepted by PD patients, which may benefit especially from preserving balance.

Background: Distinguishing between Charcot Neuroarthropathy (CN), osteomyelitis (OM), and CN complicated with superimposed OM in diabetic patients is crucial for the treatment choice. Given that current diagnostic methods lack specificity, advanced techniques, e.g., magnetic resonance imaging (MRI) and 99mTc-HMPAO–WBC Single Photon Emission Computed Tomography (SPECT/CT), are needed. This study addresses the challenges in distinguishing OM and CN. Methods: We included diabetic patients with CN and soft tissue ulceration. MRI and 99mTc-HMPAO–WBC SPECT/CT were used for the diagnosis. The patients were classified into three probability levels for OM (i.e., Definite, Probable, and Unlikely) according to the Consensus Criteria for Diabetic Foot Osteomyelitis (CC-DFO). Results: Eight patients met the eligibility criteria. MRI, supported by SPECT-CT and CC-DFO, showed consistency with the OM diagnosis in three cases. The key diagnostic features included the location of signal abnormalities and secondary features such as skin ulcers, sinus tracts, and abscesses. Notably, cases with inconclusive MRI were clarified by SPECT/CT, emphasizing its efficacy in challenging scenarios. Conclusions: The primary objective of this study was to compare the results of MRI and 99mTc-HMPAO–WBC SPECT/CT with the CC-DFO score in the diabetic foot with CN and suspected OM. Advanced imaging offers a complementary approach to distinguish between CN and OM. This can help delineate the limits of the disease for presurgical planning. While MRI is valuable, 99mTc-HMPAO–WBC SPECT/CT provides additional clarity, especially in challenging cases or when metallic implants affect MRI accuracy.

(1) Background: Predicting hospitalization length for COVID-19 patients is crucial for optimizing resource allocation and patient management. Radiomics, combined with machine learning (ML), offers a promising approach by extracting quantitative imaging features from CT scans. The aim of the present study is to use and adapt machine learning (ML) architectures, exploiting CT radiomics information, and analyze algorithms’ capability to predict hospitalization at the time of patient admission. (2) Methods: The original CT lung images of 168 COVID-19 patients underwent two segmentations, isolating the ground glass area of the lung parenchyma. After an isotropic voxel resampling and wavelet and Laplacian of Gaussian filtering, 92 intensity and texture radiomics features were extracted. Feature reduction was conducted by applying a last absolute shrinkage and selection operator (LASSO) to the radiomic features set. Three ML classification algorithms, linear support vector machine (LSVM), medium neural network (MNN), and ensemble subspace discriminant (ESD), were trained and validated through a 5-fold cross-validation technique. Model performance was assessed using accuracy, sensitivity, specificity, precision, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). (3) Results: The LSVM classifier achieved the highest predictive performance, with an accuracy of 86.0% and an AUC of 0.93. However, reliable outcomes are also registered when MNN and ESD architecture are used. (4) Conclusions: The study shows that radiomic features can be used to build a machine learning framework for predicting patient hospitalization duration. The findings suggest that radiomics-based ML models can accurately predict COVID-19 hospitalization length.