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.

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.

Unsupervised type III polygraphy in children undergoing adenotonsillectomy: a technical and economic report.

OBJECTIVE: To evaluate the economic and technical viability of the sleep study (type III) in children with adenotonsilar hypertrophy. METHODS: 141 children were submitted to sleep study (type III), aged between three and 11, all with symptoms of OSA. The frequency of failed examinations and a comparison of cost analysis between complete polysomnography were described. RESULTS: 41 exams lost at least one sensor. The sensor with the highest number of losses was the oximetry, observed in 14.28%. The 100 valid sleep studies allowed the diagnosis of severe OSA in 36 children. Sleep study accounts for approximately 63% of the value of the PSG type I, thus, it showed to be cost effective even with the repetition of the failed one. CONCLUSION: Sleep study (type III) may have high failure rates and it was a reliable exam for the identification of severe OSA. The cost analysis showed economic feasibility, even with a high failure rate and necessity of repetition.

The short evaluation of orofacial myofunctional protocol (ShOM) and the sleep clinical record in pediatric obstructive sleep apnea.

INTRODUCTION: Multiple anatomic and functional risk factors contribute to Obstructive Sleep Apnea (OSA) in children, most of the screening tools only evaluate clinical symptoms. The aim was to describe the evaluation of the short orofacial myofunctional protocol (ShOM) in OSA children, and to analyze if the inclusion of orofacial myofunctional aspects would influence the screening sensitivity/specificity of the Sleep Clinical Record (SCR). METHODS: Children from Brazil and Italy with sleep disordered breathing were evaluated by full night polygraphy, the SCR and the ShOM. For the analysis of the correlations, we normalized the distribution of the children based on the percentiles of the Apnea and Hypopnea Index (AHI). The children were divided in: Group1: first percentile AHI up to25% (cut-off value: AHI≤1.9); Group 2: second percentile from 25% to 75% (cut-off values: 1.9˂AHI≤7.9); Group3: third percentile AHI˃75% (cut = off value: AHI˃7.9). The findings of SCR and ShOM were compared for each group. ROC curve of the sensitivity and specificity of OSA diagnosis were compared for SCR alone and the combined results of SCR plus ShOM. RESULTS: 86 children, 47 girls, 4-11 years, were included, 34 children were obese and 20 overweight. OSA severity and obesity showed a positive correlation (p = 0.04). Mean ShOM score was 5.64 ± 2.27, with a positive correlation to the SCR (p = 0.002). In Group1, the SCR showed more nasal obstruction, arched palate and OSAS score/positive Brouilette questionnaire and the ShOM scored more alterations to breathing mode, breathing type (p = 0.01) and lip competence. In Group 3, we found more tonsillar hypertrophy, Friedman tongue position alteration (p < 0.001), malocclusion and obesity at SCR and more alterations in tongue resting position, tongue deglutition position and malocclusion at ShOM. CONCLUSIONS: The myofuntional evaluation contributed to the screening of OSA in children, while alterations of the tongue (resting and deglutition position) were observed in children with the highest AHI percentile. The combination of SCR and ShOM improved the sensitivity and specificity for the identification of pediatric OSA when compared to SCR alone.