An ML prediction model based on clinical parameters and automated CT scan features for COVID-19 patients.

Outcome prediction for individual patient groups is of paramount importance in terms of selection of appropriate therapeutic options, risk communication to patients and families, and allocating resource through optimum triage. This has become even more necessary in the context of the current COVID-19 pandemic. Widening the spectrum of predictor variables by including radiological parameters alongside the usually utilized demographic, clinical and biochemical ones can facilitate building a comprehensive prediction model. Automation has the potential to build such models with applications to time-critical environments so that a clinician will be able to utilize the model outcomes in real-time decision making at bedside. We show that amalgamation of computed tomogram (CT) data with clinical parameters (CP) in generating a Machine Learning model from 302 COVID-19 patients presenting to an acute care hospital in India could prognosticate the need for invasive mechanical ventilation. Models developed from CP alone, CP and radiologist derived CT severity score and CP with automated lesion-to-lung ratio had AUC of 0.87 (95% CI 0.85-0.88), 0.89 (95% CI 0.87-0.91), and 0.91 (95% CI 0.89-0.93), respectively. We show that an operating point on the ROC can be chosen to aid clinicians in risk characterization according to the resource availability and ethical considerations. This approach can be deployed in more general settings, with appropriate calibrations, to predict outcomes of severe COVID-19 patients effectively.

Safety and efficacy of polymyxin B in multidrug resistant Gram-negative severe sepsis and septic shock.

BACKGROUND AND AIMS: The emergence of multidrug resistant strains of Gram-negative bacteria, especially the lactose nonfermenters like Pseudomonas and Acinetobacter, in the intensive care units have prompted renewed worldwide interest in the polymyxins. However, perceived nephrotoxicity has been a major vexation limiting their early and regular use in severe sepsis. This study was conducted to assess the safety and efficacy of polymyxin B in patients with severe sepsis and septic shock. MATERIALS AND METHODS: Forty-five patients with sepsis admitted in our medical-surgical intensive care units were identified from pharmacy records to have received polymyxin B. We retrospectively reviewed the clinical and microbiologic outcomes as well as occurrence of renal failure temporally related to the use of intravenous polymyxin B. RESULTS: polymyxin B was used in severe sepsis and septic shock with the isolated organism being resistant to other available antimicrobials or clinical deterioration despite carbapenem use. Overall mortality was 52% and among patients who received at least eight days of intravenous polymyxin B, 67% patients with initial septic shock and 62% with severe sepsis survived. The target multidrug resistant organism was cleared in 88% of subjects evaluated by repeat microbiologic testing. Acute renal failure developed in only two patients (4%). CONCLUSIONS: Polymyxin B has acceptable effectiveness against nosocomial multidrug resistant Gram-negative sepsis. The associated nephrotoxicity has been found to be significantly lower than previously reported even in patients with background renal impairment and established risk factors of renal failure.