Machine learning in perioperative medicine: a systematic review.

BACKGROUND: Risk stratification plays a central role in anesthetic evaluation. The use of Big Data and machine learning (ML) offers considerable advantages for collection and evaluation of large amounts of complex health-care data. We conducted a systematic review to understand the role of ML in the development of predictive post-surgical outcome models and risk stratification. METHODS: Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines, we selected the period of the research for studies from 1 January 2015 up to 30 March 2021. A systematic search in Scopus, CINAHL, the Cochrane Library, PubMed, and MeSH databases was performed; the strings of research included different combinations of keywords: "risk prediction," "surgery," "machine learning," "intensive care unit (ICU)," and "anesthesia" "perioperative." We identified 36 eligible studies. This study evaluates the quality of reporting of prediction models using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklist. RESULTS: The most considered outcomes were mortality risk, systemic complications (pulmonary, cardiovascular, acute kidney injury (AKI), etc.), ICU admission, anesthesiologic risk and prolonged length of hospital stay. Not all the study completely followed the TRIPOD checklist, but the quality was overall acceptable with 75% of studies (Rev #2, comm #minor issue) showing an adherence rate to TRIPOD more than 60%. The most frequently used algorithms were gradient boosting (n = 13), random forest (n = 10), logistic regression (LR; n = 7), artificial neural networks (ANNs; n = 6), and support vector machines (SVM; n = 6). Models with best performance were random forest and gradient boosting, with AUC > 0.90. CONCLUSIONS: The application of ML in medicine appears to have a great potential. From our analysis, depending on the input features considered and on the specific prediction task, ML algorithms seem effective in outcomes prediction more accurately than validated prognostic scores and traditional statistics. Thus, our review encourages the healthcare domain and artificial intelligence (AI) developers to adopt an interdisciplinary and systemic approach to evaluate the overall impact of AI on perioperative risk assessment and on further health care settings as well.

COVID-19 respiratory support outside the ICU's doors. An observational study for a new operative strategy.

BACKGROUND AND AIM: During the first wave of the Severe Acute Respiratory Syndrome CoronaVirus 2 (SARS-CoV-2) pandemic, we faced a massive clinical and organizational challenge having to manage critically ill patients outside the Intensive Care Unit (ICU). This was due to the significant imbalance between ICU bed availability and the number of patients presenting Acute Hypoxemic Respiratory Failure caused by SARS-CoV-2-related interstitial pneumonia. We therefore needed to perform Non-Invasive Ventilation (NIV) in non-intensive wards to assist these patients and relieve pressure on the ICUs and subsequently implemented a new organizational and clinical model. This study was aimed at evaluating its effectiveness and feasibility. METHODS: We recorded the anamnestic, clinical and biochemical data of patients undergoing non-invasive mechanical ventilation while hospitalized in non-intensive CoronaVirus Disease 19 (COVID-19) wards. Data were registered on admission, during anesthesiologist counseling, and when NIV was started and suspended. We retrospectively registered the available results from routine arterial blood gas and laboratory analyses for each time point. RESULTS: We retrospectively enrolled 231 patients. Based on our criteria, we identified 46 patients as NIV responders, representing 19.9% ​​of the general study population and 29.3% of the patients that spent their entire hospital stay in non-ICU wards. Overall mortality was 56.2%, with no significant differences between patients in non-intensive wards (57.3%) and those later admitted to the ICU (54%) Conclusions: NIV is safe and manageable in an emergency situation and could become part of an integrated clinical and organizational model.

Surgery in COVID-19 patients: operational directives.

The current COVID-19 pandemic underlines the importance of a mindful utilization of financial and human resources. Preserving resources and manpower is paramount in healthcare. It is important to ensure the ability of surgeons and specialized professionals to function through the pandemic. A conscious effort should be made to minimize infection in this sector. A high mortality rate within this group would be detrimental.This manuscript is the result of a collaboration between the major Italian surgical and anesthesiologic societies: ACOI, SIC, SICUT, SICO, SICG, SIFIPAC, SICE, and SIAARTI. We aim to describe recommended clinical pathways for COVID-19-positive patients requiring acute non-deferrable surgical care. All hospitals should organize dedicated protocols and workforce training as part of the effort to face the current pandemic.