Application of natural language processing to predict final recommendation of Brazilian health technology assessment reports.

INTRODUCTION: Health technology assessment (HTA) plays a vital role in healthcare decision-making globally, necessitating the identification of key factors impacting evaluation outcomes due to the significant workload faced by HTA agencies. OBJECTIVES: The aim of this study was to predict the approval status of evaluations conducted by the Brazilian Committee for Health Technology Incorporation (CONITEC) using natural language processing (NLP). METHODS: Data encompassing CONITEC's official report summaries from 2012 to 2022. Textual data was tokenized for NLP analysis. Least Absolute Shrinkage and Selection Operator, logistic regression, support vector machine, random forest, neural network, and extreme gradient boosting (XGBoost), were evaluated for accuracy, area under the receiver operating characteristic curve (ROC AUC) score, precision, and recall. Cluster analysis using the k-modes algorithm categorized entries into two clusters (approved, rejected). RESULTS: The neural network model exhibited the highest accuracy metrics (precision at 0.815, accuracy at 0.769, ROC AUC at 0.871, and recall at 0.746), followed by XGBoost model. The lexical analysis uncovered linguistic markers, like references to international HTA agencies' experiences and government as demandant, potentially influencing CONITEC's decisions. Cluster and XGBoost analyses emphasized that approved evaluations mainly concerned drug assessments, often government-initiated, while non-approved ones frequently evaluated drugs, with the industry as the requester. CONCLUSIONS: NLP model can predict health technology incorporation outcomes, opening avenues for future research using HTA reports from other agencies. This model has the potential to enhance HTA system efficiency by offering initial insights and decision-making criteria, thereby benefiting healthcare experts.

A comprehensive model for assessing and classifying patients with thrombotic microangiopathy: the TMA-INSIGHT score.

BACKGROUND: Thrombotic Microangiopathy (TMA) is a syndrome characterized by the presence of anemia, thrombocytopenia and organ damage and has multiple etiologies. The primary aim is to develop an algorithm to classify TMA (TMA-INSIGHT score). METHODS: This was a single-center retrospective cohort study including hospitalized patients with TMA at a single center. We included all consecutive patients diagnosed with TMA between 2012 and 2021. TMA was defined based on the presence of anemia (hemoglobin level < 10 g/dL) and thrombocytopenia (platelet count < 150,000/µL), signs of hemolysis, and organ damage. We classified patients in eight categories: infections; Malignant Hypertension; Transplant; Malignancy; Pregnancy; Thrombotic Thrombocytopenic Purpura (TTP); Shiga toxin-mediated hemolytic uremic syndrome (STEC-SHU) and Complement Mediated TMA (aHUS). We fitted a model to classify patients using clinical characteristics, biochemical exams, and mean arterial pressure at presentation. RESULTS: We retrospectively retrieved TMA phenotypes using automatic strategies in electronic health records in almost 10 years (n = 2407). Secondary TMA was found in 97.5% of the patients. Primary TMA was found in 2.47% of the patients (TTP and aHUS). The best model was LightGBM with accuracy of 0.979, and multiclass ROC-AUC of 0.966. The predictions had higher accuracy in most TMA classes, although the confidence was lower in aHUS and STEC-HUS cases. CONCLUSION: Secondary conditions were the most common etiologies of TMA. We retrieved comorbidities, associated conditions, and mean arterial pressure to fit a model to predict TMA and define TMA phenotypic characteristics. This is the first multiclass model to predict TMA including primary and secondary conditions.

Machine Learning Model to Predict Graft Rejection After Kidney Transplantation.

BACKGROUND: There are few predictive studies about early posttransplant outcomes taking into account baseline and posttransplant variables. The objective of this study was to create a predictive model for 30-day graft rejection using machine learning techniques. METHODS: Retrospective study with 1255 patients undergoing transplant from living and deceased donors at a tertiary health service in Brazil. Recipient, donor, transplantation, and postoperative period data were collected from physical and electronic records. We split the data into derivation (training) and validation (test) datasets. Five supervised machine learning algorithms were developed with this subset of variables in the training set: Simple Logistic Regression, Lasso, Multilayer Perceptron, XGBoost, and Light GBM. RESULTS: There were 147 (12.48%) cases of graft rejection within 30 days of transplantation. The best model was XGBoost (accuracy, 0.839; receiver operating characteristic area under the curve, 0.715; precision, 0.900). The model showed that deceased donor transplantation, glomerulopathy as an underlying disease, and donor's use of vasoactive drugs had more than 20% importance as rejection risk factors. The variables with the greatest predictive values were thymoglobulin induction and delayed graft function. CONCLUSIONS: We fitted a machine learning model to predict 30-day graft rejection after kidney transplantation that reaches a higher accuracy and precision. Machine learning models could contribute to predicting kidney survival using nontraditional approaches.

Impact of the COVID-19 Pandemic on Solid Organ Transplant and Rejection Episodes in Brazil's Unified Healthcare System.

BACKGROUND: Brazil has the world's largest public organ transplant program, which was severely affected by the COVID-19 pandemic. The primary aim of the study was to evaluate differences in solid organ transplants and rejection episodes during the COVID-19 pandemic compared to the five years before the pandemic in the country. METHODS: A seven-year database was built by downloading data from the DATASUS server. The pandemic period was defined as March 2020 to December 2021. The pre-pandemic period was from January 2015 to March 2020. RESULTS: During the pandemic, the number of solid organ transplants decreased by 19.3% in 2020 and 22.6% in 2021 compared to 2019. We found a decrease for each evaluated organ, which was more pronounced for lung, pancreas, and kidney transplants. The seasonal plot of rejection data indicated a high rejection rate between 2018 and 2021. There was also an 18% (IRR 1.18 (95% CI 1.01 to 1.37), p = 0.04) increase in the rejection rate during the COVID-19 pandemic. CONCLUSIONS: The total number of organ transplants performed in 2021 represents a setback of six years. Transplant procedures were concentrated in the Southeast region of the country, and a higher proportion of rejections occurred during the pandemic. Together, these findings could have an impact on transplant procedures and outcomes in Brazil.