Digital health technologies (DHTs), including digital therapeutics (DTx), are revolutionizing patient care by enabling the prevention, management, and trea
Background/Objectives: Prevalence and burden of chronic obstructive pulmonary disease (COPD) are projected to increase in the coming decades. Although prognostic models for disease progression and exacerbation risk have proliferated, especially with the advent of machine learning (ML), their methodological rigor, generalizability, and predictive performance remain inconsistent. This study aimed to systematically review prognostic models for disease progression in adults with COPD, including traditional regression-based methods and ML techniques, evaluating model performance, sources of heterogeneity and methodological issues. Methods: PubMed and Embase were searched for all studies that developed and/or validated prognostic models for mortality (overall and cause-specific), exacerbations, or hospitalizations in adults with COPD over a time window of 1–5 years. Methodological quality was appraised using PROBAST. Model performance was summarized descriptively, and discrimination (c-statistic) was meta-analyzed for externally validated models with sufficient homogeneity. Results: Eighty-seven studies presenting 193 prognostic models across 96 unique cohorts were included. Only 7% of models were based on ML. Thirty-eight percent of records were validations of multidimensional indices. All-cause mortality (n = 85), severe exacerbations (n = 38) and moderate/severe exacerbations (n = 16) were the most frequently studied outcomes. Meta-analysis of exacerbation models was hampered by insufficient homogeneity (median c 0.74). As for mortality, BODE outperformed other indices (pooled c 0.75). Over 40% of studies were flawed by a high risk of bias. Conclusions: Despite a comprehensive literature search and thorough data extraction, we were able to provide a meaningful quantitative synthesis only for externally validated mortality models, as pooling results for other individual outcomes was precluded by substantial heterogeneity. Our findings highlight the predominance of regression approaches, the limited use of ML, the presence of persistent methodological limitations and the need for more robust, validated models capable of handling complex, multimodal patient data.
26 May 2026 in Journal of Evaluation in Clinical Practice
Background: Artificial intelligence (AI) is rapidly transforming medicine through advanced diagnostic, prognostic, and decision‐support systems. Objective: To summarize the fundamental concepts, clinical applications, ethical issues, and future perspectives of AI in healthcare. Methods: A narrative review of current evidence on machine learning, deep learning, neural networks, and AI applications across major medical specialties was conducted. Results: AI demonstrated high performance in diagnostic support, prognostic prediction, medical imaging, and personalized medicine. However, limitations related to data quality, generalizability, transparency, and ethical concerns remain significant challenges. Conclusions: AI has strong potential to improve healthcare delivery and precision medicine, although robust validation, ethical oversight, and appropriate regulation are essential for safe clinical implementation.
During the two years of the COVID-19 pandemic, more than 400 million cases all over the world have been identified. Health care workers were among the first to deal with this virus and consequently a high incidence of infection was reported in this population. The aim of the survey was to investigate health care workers’ (HCWs) clinical characteristics and potential risk factors associated with the SARS-CoV-2 infection in a referral hospital in Northern Italy after the first and second waves of the pandemic. We administered a questionnaire during the flu vaccination campaign that took place at the end of 2020; among 1386 vaccinated HCWs, data was collected and analyzed for 1065 subjects. 182 HCWs (17%) declared that they had tested positive on at least a molecular or a serological test since the beginning of the pandemic. Comparing the infected vs. not infected HCWs, median age, BMI, smoking habit, presence of hypertension or other comorbidities were not significantly different, while having worked in a COVID ward was associated with the infection (ORadj = 1.54, 95% CI: 1.07–2.20). Respondents declared that more than 70% of contacts occurred in the hospital with patients or colleagues, while about 15% in domestic environments. Among the infected, the most reported symptoms were fever (62.1%), asthenia (60.3%), anosmia/ageusia (53.5%), arthralgia/myalgia (48.3%), headache or other neurological symptoms (46.6%), cough (43.1%) and flu-like syndrome (41.4%). The percentage of subjects who have been infected with SARS-CoV-2 seems to be higher in HCWs than in the general population; hence, in hospitals, protective measures and preventive strategies to avoid the spreading of the contagion remain crucial.
Digital health technologies (DHTs), including digital therapeutics (DTx), are revolutionizing patient care by enabling the prevention, management, and treatment of medical conditions. These tools comprise care delivery mobile applications, wearable devices, and cloud platforms for capturing real-time data and enabling remote monitoring. DTx also encompasses artificial intelligence (AI) and machine learning algorithms, as well as AI agents and digital twins (DTs) for clinical decision-making and predictive analytics. Evidence supports the effectiveness of DHT strategies across different clinical fields. For example, wearable and remote patient monitoring technologies enable continuous assessment and personalized feedback in cardiology and neurology. Additionally, AI-enabled devices are mostly implemented for continuous monitoring of glucose levels. However, several key challenges remain. Persistent gender and social biases in datasets and algorithms raise ethical concerns, particularly for underrepresented groups and pediatric populations. Mitigation strategies include regulatory frameworks, explainable AI, and trustworthy AI ecosystems. This narrative review synthesizes current evidence, highlights implementation barriers, and proposes recommendations to enhance inclusivity, interoperability, and real-world evaluation of these technologies. Applications of DHT in animals within the one digital health framework are also discussed.