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.

Economic evaluation of non-invasive liver tests for the diagnosis of liver fibrosis in chronic liver diseases: a systematic review protocol

OBJECTIVE

The objective of this review is to determine the costs and benefits of non-invasive liver tests vs liver biopsy in patients with chronic liver diseases.

INTRODUCTION

Hepatic diseases can lead to liver fibrosis, cirrhosis, and hepatocellular carcinoma. In the past, liver biopsy was the only option for diagnosing fibrosis degree. Liver biopsy is an invasive procedure that depends on the sample size to be able to deliver an accurate diagnosis. In recent years, non-invasive liver tests have been increasingly used to estimate liver fibrosis degree; however, there is a lack of economic assessments of technology implementation outcomes.

INCLUSION CRITERIA

This review will include partial (cost studies) and complete economic evaluation studies on hepatitis B, hepatitis C, alcoholic liver disease, and non-alcoholic fatty liver disease that compare non-invasive liver tests with liver biopsies. Studies published in English, French, Spanish, German, Italian, or Portuguese will be included. No date limits will be applied to the search.

METHODS

This review will identify published and unpublished studies. Published studies will be identified using MEDLINE (PubMed), Cochrane Library (CENTRAL), Embase, Web of Science, Scopus, and LILACS. Sources of unpublished studies and gray literature will include sources from health technology assessment agencies, clinical practice guidelines, regulatory approvals, advisories and warnings, and clinical trial registries, as well as Google Scholar. Two independent reviewers will screen and assess studies, and extract and critically appraise the data. Data extracted from the included studies will be analyzed and summarized to address the review objective using narrative text, and the JBI dominance ranking matrix.

REVIEW REGISTRATION

PROSPERO CRD42023404278.

Nursing experiences in specialized services in child and adolescent mental health: a systematic review of qualitative studies

OBJECTIVE

to synthesize evidence from qualitative studies on nursing experiences regarding child and adolescent mental health care in specialized services.

METHOD

a systematic review with meta-synthesis of qualitative studies according to JBI guidelines. CINAHL, EMBASE, MEDLINE, LILACS, PSYCinfo, Scopus and Web of Science databases were used. The findings were classified according to the level of reliability and credibility and categorized by similarity between contents.

RESULTS

229 articles were identified, and five were included in the final sample and organized into the categories: Emotional impact; and Understanding nursing role. The level of evidence found was moderate.

FINAL CONSIDERATIONS

nursing experiences are permeated by emotional exhaustion, feelings of frustration and difficulty in understanding their professional role. The need for training spaces that qualify this care is highlighted.

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.

Exploring the COVID-19 Pandemic's Impact on the Health Technology Assessment Process of the National Commission for the Incorporation of Technologies Into the Brazilian Health System

OBJECTIVES

This study aimed to evaluate the impact of the COVID-19 pandemic on Brazilian health technology assessment processes based on public reports from the National Committee for Health Technology Incorporation (CONITEC).

METHODS

This descriptive study analyzed CONITEC's official reports on Brazil available on its website between 2018 and 2021 that aimed to propose recommendations for technologies to be incorporated into its public healthcare system. We used descriptive statistics covering the number of technologies and number of reports about drugs per year, objective, type of technology, demanding sector, and outcome before 2018 to 2019 and during the COVID-19 pandemic (2020-2021). Furthermore, we used logistic regression to explore any association between the final decision labeled as "incorporated" and the emergence of the COVID-19 pandemic.

RESULTS

A total of 278 reports were analyzed. Approximately 85% (136 of 278), 79% (220 of 278), and 45% of the reports (125 of 278) were about drugs, for incorporation, and requested by the government, respectively. Moreover, 74 of 130 (57%) and 56 of 148 decisions (38%) were "incorporated" before and during the pandemic, respectively. No significant association was noted between incorporated decisions and the arrival of the COVID-19 pandemic for all technologies (odds ratio 1.43; 95% CI 0.84-2.46; P = .192) and for drugs (odds ratio 1.43; 95% confidence interval 0.81-2.53; P = .223) while adjusting for the type of technology and demandant.

CONCLUSIONS

The COVID-19 pandemic has brought many challenges, but it does not seem to have had a significant impact on the health technology assessment approval decisions of CONITEC in Brazil.

Cost-effectiveness analysis of cinacalcet vs. paricalcitol in the treatment of hyperparathyroidism secondary to chronic kidney disease

INTRODUCTION

For the reduction of PTH levels, two classes of drugs are available in the Brazilian market: non-selective and selective vitamin D receptor activators and calcimimetics. Among the mentioned drugs, the SUS provides oral calcitriol, paricalcitol and cinacalcet.

OBJECTIVES

Develop cost-effectiveness (CE) and budgetary impact (BI) analysis of cinacalcet versus paricalcitol for patients on dialysis with SHPT, from the perspective of SUS.

METHODOLOGY

A decision tree model was constructed for CE analysis, which considered the outcome of avoided parathyroidectomy and a time horizon of 1 year. As for the BI analysis, two scenarios were considered, one of which was measured demand and other epidemiological, based on data from the Brazilian Society of Nephrology (BSN).

RESULTS

The CE analysis showed that the use of cinacalcet results in one-off savings of R$1,394.64 per year and an incremental effectiveness of 0.08, in relation to avoided parathyroidectomy. The incremental CE ratio (ICER) was - R$ 17,653.67 per avoided parathyroidectomy for cinacalcet, as it was more effective and cheaper compared to paricalcitol. As for the BI analysis, it was estimated that the incremental BI with the expansion of the use of cinacalcet in the SUS will be between - R$ 1,640,864.62 and R$ 166,368.50 in the first year, considering the main and the epidemiological scenarios. At the end of 5 years after the expansion of use, an BI was estimated between - R$ 10,740,743.86 and - R$ 1,191,339.37; considering the same scenarios.

CONCLUSION

Cinacalcet was dominant to avoid parathyroidectomies, being cost-effective.

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.

Hospital characteristics associated with COVID-19 mortality: data from the multicenter cohort Brazilian Registry

The COVID-19 pandemic caused unprecedented pressure over health care systems worldwide. Hospital-level data that may influence the prognosis in COVID-19 patients still needs to be better investigated. Therefore, this study analyzed regional socioeconomic, hospital, and intensive care units (ICU) characteristics associated with in-hospital mortality in COVID-19 patients admitted to Brazilian institutions. This multicenter retrospective cohort study is part of the Brazilian COVID-19 Registry. We enrolled patients ≥ 18 years old with laboratory-confirmed COVID-19 admitted to the participating hospitals from March to September 2020. Patients' data were obtained through hospital records. Hospitals' data were collected through forms filled in loco and through open national databases. Generalized linear mixed models with logit link function were used for pooling mortality and to assess the association between hospital characteristics and mortality estimates. We built two models, one tested general hospital characteristics while the other tested ICU characteristics. All analyses were adjusted for the proportion of high-risk patients at admission. Thirty-one hospitals were included. The mean number of beds was 320.4 ± 186.6. These hospitals had eligible 6556 COVID-19 admissions during the study period. Estimated in-hospital mortality ranged from 9.0 to 48.0%. The first model included all 31 hospitals and showed that a private source of funding (β = - 0.37; 95% CI - 0.71 to - 0.04; p = 0.029) and location in areas with a high gross domestic product (GDP) per capita (β = - 0.40; 95% CI - 0.72 to - 0.08; p = 0.014) were independently associated with a lower mortality. The second model included 23 hospitals and showed that hospitals with an ICU work shift composed of more than 50% of intensivists (β = - 0.59; 95% CI - 0.98 to - 0.20; p = 0.003) had lower mortality while hospitals with a higher proportion of less experienced medical professionals had higher mortality (β = 0.40; 95% CI 0.11-0.68; p = 0.006). The impact of those association increased according to the proportion of high-risk patients at admission. In-hospital mortality varied significantly among Brazilian hospitals. Private-funded hospitals and those located in municipalities with a high GDP had a lower mortality. When analyzing ICU-specific characteristics, hospitals with more experienced ICU teams had a reduced mortality.

Cost-effectiveness analysis of intravenous paricalcitol vs. oral calcitriol in the treatment of hyperparathyroidism secondary to chronic kidney disease

INTRODUCTION

Hyperparathyroidism (SHPT) secondary to chronic kidney disease (CKD) is characterized by high levels of parathyroid hormone (PTH), hyperplasia of the parathyroid glands and cardiovascular disease. Selective and non-selective and selective vitamin D-receptor activators, calcimimetics, are available in the Brazilian market to reduce PTH levels.

OBJECTIVES

To develop a cost-effectiveness (C/E) and budgetary impact (BI) analysis of intravenous paricalcitol vs. oral calcitriol for patients on dialysis with SHPT, from the perspective of the Brazilian Public Health Care System (SUS).

METHODOLOGY

We built a decision-tree model to analyze C/E, which considered the outcome of avoided death and a time horizon of 1 year. As for the BI analysis, two scenarios were considered, one of demand and one of epidemiological approach, based on data from the Brazilian Society of Nephrology.

RESULTS

The analysis showed that the C/E ratio was R$ 1,213.68 per year, and an incremental effectiveness of 0.032, referring to avoided death. The incremental C/E ratio was R$37,927.50 per death averted by paricalcitol. It was estimated that the incremental BI with the expansion of paricalcitol use will be between R$1,600,202.28 and R$4,128,565.65 in the first year, considering the main and epidemiological scenarios. At the end of 5 years after the expansion of its use, an incremental BI was estimated between R$ 48,596,855.50 and R$ 62,90,555.73.

CONCLUSION

Intravenous paricalcitol has superior efficacy and similar safety to oral calcitriol, reducing the overall mortality of dialysis patients, although it implies a higher cost.

Análise de custo-efetividade do paricalcitol intravenoso vs. calcitriol oral no tratamento do hiperparatireoidismo secundário à doença renal crônica

Resumo Introdução: O hiperparatireoidismo secundário (HPTS) à doença crônica renal (DRC) é caracterizado por elevados níveis de paratormônio (PTH), hiperplasia das glândulas paratireoides e doença cardiovascular. Para a redução dos níveis do PTH, estão disponíveis no mercado brasileiro os ativadores não seletivos e seletivos do receptor da vitamina D e os calcimiméticos. Objetivos: Desenvolver análise de custo-efetividade (C/E) e de impacto orçamentário (IO) do paricalcitol intravenoso vs. calcitriol oral para pacientes em diálise com HPTS, na perspectiva do Sistema Único de Saúde. Metodologia: Foi construído um modelo de árvore de decisão para a análise de C/E, que considerou o desfecho morte evitada e um horizonte temporal de 1 ano. Quanto à análise de IO, foram considerados dois cenários, sendo um de demanda aferida e um de abordagem epidemiológica, baseado nos dados da Sociedade Brasileira de Nefrologia. Resultados: A análise mostrou que a relação de C/E foi de R$ 1.213,68 ao ano, e uma efetividade incremental de 0,032, referente à morte evitada. A razão de C/E incremental foi de R$ 37.927,50 por morte evitada para o paricalcitol. Estimou-se que o IO incremental com a ampliação do uso do paricalcitol estará entre R$ 1.600.202,28 e R$ 4.128.565,65 no primeiro ano, considerando os cenários principal e o epidemiológico. Já no fim de 5 anos após a ampliação do uso, estimou-se IO incremental entre R$ 48.596.855,50 e R$ 62.90.555,73. Conclusão: O paricalcitol intravenoso tem eficácia superior e segurança semelhante ao comparador calcitriol oral, diminuindo a mortalidade geral dos pacientes em diálise, embora implique maior custo.