Artificial intelligence model on chest imaging to diagnose COVID-19 and other pneumonias: A systematic review and meta-analysis

Artificial neural network based prediction of the lung tissue involvement as an independent in‐hospital mortality and mechanical ventilation risk factor in COVID‐19

“…AI‐based radiological support tools have been rapidly developed as apart of the COVID‐19 pandemic response 33 . Several such tools have been developed and validated and are being applied in clinical practice, 34 achieving high accuracy, sensitivity, and specificity 35 . Our tool was implemented across emergency and other clinical departments of a large regional hospital involved in the primary COVID‐19 response in the West Pomeranian region of Poland.…”

“…Continuous data were fitted into categorical variables and proportional hazard models, allowing examination of the significance of every variable to construct the final model, which was also reanalyzed for the subgroups observed until and beyond 15 days of in-hospital treatment, as almost 70% of the group either died or was discharged within 2 weeks from admission.AI-based radiological support tools have been rapidly developed as apart of the COVID-19 pandemic response 33. Several such tools have been developed and validated and are being applied in clinical practice,34 achieving high accuracy, sensitivity, and specificity 35. Our tool was implemented across emergency and other clinical departments of a large regional hospital involved in the primary COVID-19 response in the West Pomeranian region of Poland.…”

Keeping global focus on the many challenges of respiratory tract infections

“…In this issue of COPM, Antonietta Barbieri et al [8] explore the integration of AI into the management of community-acquired pneumonia emphasizing its relevance in predicting the risk of hospitalization. Artificial-intelligence models on chest imaging to diagnose pneumonia from any cause are being developed and assessed [9]. The use of AI-assisted automated accurate diagnostics, management protocols and prognostics have the potential to help improve and transform efficiency of patient management, clinical workflow, and could optimize resource allocation for the whole spectrum of respiratory tract infections [9][10][11].…”

“…Artificial-intelligence models on chest imaging to diagnose pneumonia from any cause are being developed and assessed [9]. The use of AI-assisted automated accurate diagnostics, management protocols and prognostics have the potential to help improve and transform efficiency of patient management, clinical workflow, and could optimize resource allocation for the whole spectrum of respiratory tract infections [9][10][11]. Many ethical and operational questions regarding AI remain and whether it will deliver its promising potential in transforming healthcare and disease surveillance remains to be seen.…”

Is artificial intelligence for medical professionals serving the patients? Protocol for a mixed method systematic review on patient-relevant benefits and harms of algorithmic decision-making.

“…By searching PubMed for the term “artificial intelligence”, we found over 2,000 systematic reviews and meta-analyses published in the last 10 years, with a yearly increasing trend. These include several reviews conducted in the area of AI in healthcare that provide an overview of the current state of AI technologies in specific clinical areas, including AI systems for breast cancer diagnosis in screening programmes (Freeman et al 2021), ovarian cancer (Xu et al 2022), early detection of skin cancer (Jones et al 2022), COVID-19 and other pneumonia (Jia et al 2022), prediction of preterm birth (Akazawa & Hashimoto 2022), or diabetes management (Kamel et al 2022). Other reviews have focused on comparing clinicians and AI systems in terms of their performance to show their capabilities in a clinical setting (Shen et al 2019, Nagendran et al 2020, Liu et al 2019).…”