ROBSON LUIS OLIVEIRA DE AMORIM
Projetos de Pesquisa
Unidades Organizacionais
LIM/62 - Laboratório de Fisiopatologia Cirúrgica, Hospital das Clínicas, Faculdade de Medicina
4 resultados
Resultados de Busca
Agora exibindo 1 - 4 de 4
- Prediction of Early TBI Mortality Using a Machine Learning Approach in a LMIC Population(2020) AMORIM, Robson Luis; OLIVEIRA, Louise Makarem; MALBOUISSON, Luis Marcelo; NAGUMO, Marcia Mitie; SIMOES, Marcela; MIRANDA, Leandro; BOR-SENG-SHU, Edson; BEER-FURLAN, Andre; ANDRADE, Almir Ferreira De; RUBIANO, Andres M.; TEIXEIRA, Manoel Jacobsen; KOLIAS, Angelos G.; PAIVA, Wellingson SilvaBackground: In a time when the incidence of severe traumatic brain injury (TBI) is increasing in low- to middle-income countries (LMICs), it is important to understand the behavior of predictive variables in an LMIC's population. There are few previous attempts to generate prediction models for TBI outcomes from local data in LMICs. Our study aim is to design and compare a series of predictive models for mortality on a new cohort in TBI patients in Brazil using Machine Learning. Methods: A prospective registry was set in Sao Paulo, Brazil, enrolling all patients with a diagnosis of TBI that require admission to the intensive care unit. We evaluated the following predictors: gender, age, pupil reactivity at admission, Glasgow Coma Scale (GCS), presence of hypoxia and hypotension, computed tomography findings, trauma severity score, and laboratory results. Results: Overall mortality at 14 days was 22.8%. Models had a high prediction performance, with the best prediction for overall mortality achieved through Naive Bayes (area under the curve = 0.906). The most significant predictors were the GCS at admission and prehospital GCS, age, and pupil reaction. When predicting the length of stay at the intensive care unit, the Conditional Inference Tree model had the best performance (root mean square error = 1.011), with the most important variable across all models being the GCS at scene. Conclusions: Models for early mortality and hospital length of stay using Machine Learning can achieve high performance when based on registry data even in LMICs. These models have the potential to inform treatment decisions and counsel family members.
- Consensus statement from the international consensus meeting on post-traumatic cranioplasty(2021) IACCARINO, C.; KOLIAS, A.; ADELSON, P. D.; RUBIANO, A. M.; VIAROLI, E.; BUKI, A.; CINALLI, G.; FOUNTAS, K.; KHAN, T.; SIGNORETTI, S.; WARAN, V.; ADELEYE, A. O.; AMORIM, R.; BERTUCCIO, A.; CAMA, A.; CHESNUT, R. M.; BONIS, P. De; ESTRANEO, A.; FIGAJI, A.; FLORIAN, S. I.; FORMISANO, R.; FRASSANITO, P.; GATOS, C.; GERMANO, A.; GIUSSANI, C.; HOSSAIN, I.; KASPRZAK, P.; PORTA, F. La; LINDNER, D.; MAAS, A. I. R.; PAIVA, W.; PALMA, P.; PARK, K. B.; PERETTA, P.; POMPUCCI, A.; POSTI, J.; SENGUPTA, S. K.; SINHA, A.; SINHA, V.; STEFINI, R.; TALAMONTI, G.; TASIOU, A.; ZONA, G.; ZUCCHELLI, M.; HUTCHINSON, P. J.; SERVADEI, F.Background Due to the lack of high-quality evidence which has hindered the development of evidence-based guidelines, there is a need to provide general guidance on cranioplasty (CP) following traumatic brain injury (TBI), as well as identify areas of ongoing uncertainty via a consensus-based approach. Methods The international consensus meeting on post-traumatic CP was held during the International Conference on Recent Advances in Neurotraumatology (ICRAN), in Naples, Italy, in June 2018. This meeting was endorsed by the Neurotrauma Committee of the World Federation of Neurosurgical Societies (WFNS), the NIHR Global Health Research Group on Neurotrauma, and several other neurotrauma organizations. Discussions and voting were organized around 5 pre-specified themes: (1) indications and technique, (2) materials, (3) timing, (4) hydrocephalus, and (5) paediatric CP. Results The participants discussed published evidence on each topic and proposed consensus statements, which were subject to ratification using anonymous real-time voting. Statements required an agreement threshold of more than 70% for inclusion in the final recommendations. Conclusions This document is the first set of practical consensus-based clinical recommendations on post-traumatic CP, focusing on timing, materials, complications, and surgical procedures. Future research directions are also presented.
- The Evolving Concept of Damage Control in Neurotrauma: Application of Military Protocols in Civilian Settings with Limited Resources(2019) RUBIANO, Andres M.; MALDONADO, Miguel; MONTENEGRO, Jorge; RESTREPO, Claudia M.; KHAN, Ahsan Ali; MONTEIRO, Ruy; FALEIRO, Rodrigo M.; CARRENO, Jose N.; AMORIM, Robson; PAIVA, Wellingson; MUNOZ, Erick; PARANHOS, Jorge; SOTO, Alvaro; ARMONDA, Rocco; ROSENFELD, Jeffrey V.OBJECTIVE: The aim of the present review was to describe the evolution of the damage control concept in neurotrauma, including the surgical technique and medical postoperative care, from the lessons learned from civilian and military neurosurgeons who have applied the concept regularly in practice at military hospitals and civilian institutions in areas with limited resources. METHODS: The present narrative review was based on the experience of a group of neurosurgeons who participated in the development of the concept from their practice working in military theaters and low-resources settings with an important burden of blunt and penetrating cranial neurotrauma. RESULTS: Damage control surgery in neurotrauma has been described as a sequential therapeutic strategy that supports physiological restoration before anatomical repair in patients with critical injuries. The application of the concept has evolved since the early definitions in 1998. Current strategies have been supported by military neurosurgery experience, and the concept has been applied in civilian settings with limited resources. CONCLUSION: Damage control in neurotrauma is a therapeutic option for severe traumatic brain injury management in austere environments. To apply the concept while using an appropriate approach, lessons must be learned from experienced neurosurgeons who use this technique regularly.
- Evaluation of Computed Tomography Scoring Systems in the Prediction of Short-Term Mortality in Traumatic Brain Injury Patients from a Low- to Middle-Income Country(2022) SOUZA, Matheus Rodrigues de; CORTES, Mayra Aparecida; SILVA, Gustavo Carlos Lucena da; SOLLA, Davi Jorge Fontoura; MARQUES, EryanneGarcia; OLIVEIRA JUNIOR, WellithonLuz; FAGUNDES, Caroline Ferreira; TEIXEIRA, Manoel Jacobsen; AMORIM, Robson Luis Oliveira de; RUBIANO, Andres M.; KOLIAS, Angelos G.; PAIVA, Wellingson SilvaThe present study aims to evaluate the accuracy of the prognostic discrimination and prediction of the short-term mortality of the Marshall computed tomography (CT) classification and Rotterdam and Helsinki CT scores in a cohort of TBI patients from a low- to middle-income country. This is a post hoc analysis of a previously conducted prospective cohort study conducted in a university-associated, tertiary-level hospital that serves a population of >12 million in Brazil. Marshall CT class, Rotterdam and Helsinki scores, and their components were evaluated in the prediction of 14-day and in-hospital mortality using Nagelkerk's pseudo-R-2 and area under the receiver operating characteristic curve. Multi-variate regression was performed using known outcome predictors (age, Glasgow Coma Scale, pupil response, hypoxia, hypotension, and hemoglobin values) to evaluate the increase in variance explained when adding each of the CT classification systems. Four hundred forty-seven patients were included. Mean age of the patient cohort was 40 (standard deviation, 17.83) years, and 85.5% were male. Marshall CT class was the least accurate model, showing pseudo-R-2 values equal to 0.122 for 14-day mortality and 0.057 for in-hospital mortality, whereas Rotterdam CT scores were 0.245 and 0.194 and Helsinki CT scores were 0.264 and 0.229. The AUC confirms the best prediction of the Rotterdam and Helsinki CT scores regarding the Marshall CT class, which presented greater discriminative ability. When associated with known outcome predictors, Marshall CT class and Rotterdam and Helsinki CT scores showed an increase in the explained variance of 2%, 13.4%, and 21.6%, respectively. In this study, Rotterdam and Helsinki scores were more accurate models in predicting short-term mortality. The study denotes a contribution to the process of external validation of the scores and may collaborate with the best risk stratification for patients with this important pathology.