Search

Background: The severity of laboratory and imaging finding was found to be inconsistent with clinical symptoms in COVID‑19 patients, thereby increasing casualties. As compared to conventional biomarkers, machine learning algorithms can learn nonlinear and complex interactions and thus improve prediction accuracy. This study aimed at evaluating role of biochemical and immunological parameters–based machine learning algorithms for severity indexing in COVID‑19. Methods: Laboratory biochemical results of 5715 COVID‑19 patients were mined from electronic records including 509 admitted in COVID‑19 ICU. Random Forest Classifier (RFC), Support Vector Machine (SVM), Naive Bayesian Classifier (NBC) and K‑Nearest Neighbours (KNN) classifier models were used. Lasso regression helped in identifying the most influential parameter. A decision tree was made for subdivided data set, based on randomization. Results: Accuracy of SVM was highest with 94.18% and RFC with 94.04%. SVM had highest PPV (1.00), and NBC had highest NPV (0.95). QUEST modelling ignored age, urea and total protein, and only C‑reactive protein and lactate dehydrogenase were considered to be a part of decision‑tree algorithm. The overall percentage of correct classification was 78.31% in the overall algorithm with a sensitivity of 87.95% and an AUC of 0.747. Conclusion: C‑reactive protein and lactate dehydrogenase being routinely performed tests in clinical laboratories in peripheral setups, this algorithm could be an effective predictive tool. SVM and RFC models showed significant accuracy in predicting COVID‑19 severity and could be useful for future pandemics. [ABSTRACT FROM AUTHOR]

How to cite this article: Ramakrishnan N, Abraham BK, Barokar R, Chanchalani G, Jagathkar G, Shetty RM, et al . Post-ICU Care: Why, What, When and How? ISCCM Position Statement. Indian J Crit Care Med 2024;28(S2):S279-S287., Competing Interests: Source of support: Nil Conflict of interest: None, (Copyright © 2024; The Author(s).)

Patients' experiences in the intensive care unit (ICU) can enhance or impair their subsequent recovery. Improving patient and family experiences on the ICU is an important part of providing high quality care. There is little evidence to guide how to do this in a South Asian critical care context. This study addresses this gap by exploring the experiences of critically ill patients and their families in ICUs in Bangladesh and India. We elicit suggestions for improvements from patients, families and staff and highlight examples of practices that support person-centred care. This multi-site hospital ethnography was carried out in five ICUs in government hospitals in Bangladesh and India, selected using purposive sampling. Qualitative data were collected using non-participant observation and semi-structured interviews and analysed using reflexive thematic analysis. A total of 108 interviews were conducted with patients, families, and ICU staff. Over 1000 hours of observation were carried out across the five study sites. We identified important mediators of patient and family experience that span many different aspects of care. Factors that promote person-centred care include access to ICU for families, support for family involvement in care delivery, clear communication with patients and families, good symptom management for patients, support for rehabilitation, and measures to address the physical, environmental and financial needs of the family. This study has generated a list of recommendations that can be used by policy makers and practitioners who wish to implement person-centred principles in the ICU., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Inglis et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Background: The optimal way to hold an endotracheal tube (ETT) during intubation has not been studied. In this randomised clinical trial, we examined the effect of site-holding the ETT in two different positions on time and ease of intubation by anaesthesia trainees., Methods: A single-centre, randomised trial of intubations of stable patients with uncomplicated airways was conducted from 15 September 2019 to 31 May 2021 in the All India Institute of Medical Sciences, Bhubaneswar, India. A previous pilot study performed in the unit determined the comparator positions for the ETT and the sample size for a 20% difference for the primary outcome of mean time to intubation (TTI). Patients were randomised at the time of the intubation; anaesthesia trainees held the ETT at 19 or 24 cm according to the patient's assignment. Video recordings of intubations were independently reviewed by two assessors blinded to the assignment. Secondary outcomes were intubation success, ease of intubation and complications. Intention-to-treat and per-protocol analyses were performed., Results: 360 adults were randomised (180/arm) and intubated by 19 trainees. In intention-to-treat analysis, there was no significant difference in TTI. Sixteen times, trainees assigned to hold the ETT at 24 cm moved their grip distally (closer to the cuff) during the procedure. In a per-protocol analysis, TTI for those whose grip remained at 24 cm was shorter than those holding at 19 cm: 6.6 (SD 3.0) vs 7.6 (SD 4.2) s (95% CI for the difference 0.2 to 1.7 s), p=0.01. In both intention-to-treat and per-protocol analyses, there was no difference in first-pass success or ease of intubation between techniques. Eight patients assigned to 19 cm group and four assigned to 24 cm developed sore throats., Conclusion: In stable patients with uncomplicated airways, there was no significant difference in TTI based on the site at which trainees were assigned to hold the ETT. However, the shorter TTI at 24 cm in per-protocol analysis and fewer sore throat observed suggest this practice change warrants further investigation., Trial Registration Number: CTRI/ 2019/09/021201., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. No commercial re-use. See rights and permissions. Published by BMJ.)