Predicting the Need for Blood Transfusions in Cardiac Surgery: A Comparison between Machine Learning Algorithms and Established Risk Scores in the Brazilian Population

ABSTRACT Introduction: Blood transfusion is a common practice in cardiac surgery, despite its well-known negative effects. To mitigate blood transfusion-associated risks, identifying patients who are at higher risk of needing this procedure is crucial. Widely used risk scores to predict the need for blood transfusions have yielded unsatisfactory results when validated for the Brazilian population. Methods: In this retrospective study, machine learning (ML) algorithms were compared to predict the need for blood transfusions in a cohort of 495 cardiac surgery patients treated at a Brazilian reference service between 2019 and 2021. The performance of the models was evaluated using various metrics, including the area under the curve (AUC), and compared to the commonly used Transfusion Risk and Clinical Knowledge (TRACK) and Transfusion Risk Understanding Scoring Tool (TRUST) scoring systems. Results: The study found that the model had the highest performance, achieving an AUC of 0.7350 (confidence interval [CI]: 0.7203 to 0.7497). Importantly, all ML algorithms performed significantly better than the commonly used TRACK and TRUST scoring systems. TRACK had an AUC of 0.6757 (CI: 0.6609 to 0.6906), while TRUST had an AUC of 0.6622 (CI: 0.6473 to 0.6906). Conclusion: The findings of this study suggest that ML algorithms may offer a more accurate prediction of the need for blood transfusions than the traditional scoring systems and could enhance the accuracy of predicting blood transfusion requirements in cardiac surgery patients. Further research could focus on optimizing and refining ML algorithms to improve their accuracy and make them more suitable for clinical use.

Physical rehabilitation in Brazilian pediatric intensive care units: a multicenter point prevalence study / Reabilitação física em unidades de terapia intensiva pediátrica brasileiras: um estudo multicêntrico de prevalência pontual

ABSTRACT Objective: To determine the prevalence and factors associated with the physical rehabilitation of critically ill children in Brazilian pediatric intensive care units. Methods: A 2-day, cross-sectional, multicenter point prevalence study comprising 27 pediatric intensive care units (out of 738) was conducted in Brazil in April and June 2019. This Brazilian study was part of a large multinational study called Prevalence of Acute Rehabilitation for Kids in the PICU (PARK-PICU). The primary outcome was the prevalence of mobility provided by physical therapy or occupational therapy. Clinical data on patient mobility, potential mobility safety events, and mobilization barriers were prospectively collected in patients admitted for ≥ 72 hours. Results: Children under the age of 3 years comprised 68% of the patient population. The prevalence of therapist-provided mobility was 74%, or 277 out of the 375 patient-days. Out-of-bed mobility was most positively associated with family presence (adjusted odds ratios 3.31;95%CI 1.70 - 6.43) and most negatively associated with arterial lines (adjusted odds ratios 0.16; 95%CI 0.05 - 0.57). Barriers to mobilization were reported on 27% of patient-days, the most common being lack of physician order (n = 18). Potential safety events occurred in 3% of all mobilization events. Conclusion: Therapist-provided mobility in Brazilian pediatric intensive care units is frequent. Family presence was high and positively associated with out-of-bed mobility. The presence of physiotherapists 24 hours a day in Brazilian pediatric intensive care units may have a substantial impact on the mobilization of critically ill children.

RESUMO Objetivo: Determinar a prevalência e os fatores associados à reabilitação física de crianças em estado grave em unidades de terapia intensiva pediátrica brasileiras. Métodos: Realizou-se um estudo de prevalência pontual multicêntrico, transversal, de 2 dias, abrangendo 27 unidades de terapia intensiva pediátrica (do total de 738) no Brasil em abril e junho de 2019. Este estudo brasileiro fez parte de um grande estudo multinacional chamado Prevalence of Acute Rehabilitation for Kids in the PICU (PARK-PICU). O desfecho primário foi a prevalência de mobilidade proporcionada pela fisioterapia ou pela terapia ocupacional. Foram coletados prospectivamente dados clínicos sobre a mobilidade do paciente, possíveis eventos de segurança de mobilidade e barreiras de mobilização em pacientes admitidos por ≥ 72 horas. Resultados: As crianças com idade inferior a 3 anos eram 68% da população de pacientes. A prevalência de mobilidade fornecida pelo terapeuta foi de 74%, ou 277 dos 375 pacientes-dia. A mobilidade para fora do leito foi mais positivamente associada à presença de familiares (razão de chance ajustada de 3,31; IC95% 1,70 - 6,43) e mais negativamente associada às linhas arteriais (razão de chance ajustada de 0,16; IC95% 0,05 - 0,57). Foram relatadas barreiras à mobilização em 27% dos pacientes-dia, sendo a mais comum a falta de prescrição médica (n = 18). Registaram-se eventuais eventos de segurança em 3% de todos os eventos de mobilização. Conclusão: A mobilidade proporcionada pelo terapeuta nas unidades de terapia intensiva pediátrica brasileiras é frequente. A presença de familiares foi alta e positivamente associada à mobilidade para fora do leito. A presença de fisioterapeutas 24 horas por dia nas unidades de terapia intensiva pediátrica brasileiras pode exercer papel importante na mobilização de crianças em estado grave.

Validation of Blood Transfusion Risk Scores (TRACK and TRUST) in a Cardiac Surgery Service in Brazil

ABSTRACT Introduction: Transfusion of red blood cells is recurrent in cardiac surgery despite the well-established deleterious effects. Identifying patients with higher chances of requiring blood transfusion is essential to apply strategic preventive measures to reduce such chances, considering the restricted availability of this product. The most used risk scores to predict blood transfusion are the Transfusion Risk and Clinical Knowledge (TRACK) and Transfusion Risk Understanding Scoring Tool (TRUST). However, these scores were not validated for the Brazilian population. The objective of this study was to assess the accuracy of TRACK and TRUST scores in estimating the need for postoperative transfusion of red blood cell concentrates (TRBCC) after cardiac surgery. Methods: A clinical retrospective study was conducted using the database of a Brazilian reference service composed of patients operated between November 2019 and September 2021. Scores were compared using Mann-Whitney U test. Hosmer-Lemeshow goodness of fit test assessed calibration of the scores. Accuracy was assessed using the area under the receiver operating characteristic curve (AUC). All analyses considered a level of significance of 5%. The study was approved by the research ethics committee (CAAE 55577421.4.0000.5201). Results: This study assessed 498 patients. Only the TRACK score presented good calibration (P=0.238; TRUST P=0.034). AUC of TRACK was 0.678 (95% confidence interval 0.63 to 0.73; P<0.001), showing a significant accuracy. Conclusion: Between the scores analyzed, only the TRACK score showed a good calibration, but low accuracy, to predict postoperative TRBCC after cardiac surgery.