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.

COVID-19 in Kidney Transplant Recipients With Diabetes Mellitus: A Propensity Score Matching Analysis.

Kidney transplant recipients present higher rates of pre-existing comorbidities, in particular diabetes mellitus (DM), hypertension, and cardiac disease. We aimed to verify the main risk factors related to DM that contribute to COVID-19 progression and mortality in a kidney transplant setting. From March to August 2020, we evaluated 300 kidney transplant recipients affected by COVID-19. We used propensity score matching (PSM) to estimate the impact of DM on COVID-19. After matching, all baseline characteristics were well balanced between those with and without DM (n = 100 in each group). Case fatality rate, the requirement of invasive mechanical ventilation (IMV), and acute kidney injury (AKI) were associated with previous fasting blood glucose, and C-reactive protein (CRP), and lactate dehydrogenase (LDH) levels on admission. These findings were similar in kidney transplant patients with and without DM. Glycemia on admission and estimated glomerular filtration rate (eGFR) either on admission or basal correlated to the need of IMV and development of AKI, respectively. Poor glycaemic control, eGFR, markers of inflammation (CRP) and tissue damage (LDH) were indicative of COVID-19 burden in kidney transplant recipients and may be useful tools for risk-stratifying this population, independently of the DM status, during the pandemic.

Association between urinary sodium excretion and hard outcomes in non-dialysis chronic kidney disease patients.

BACKGROUND: Restriction of sodium intake is routinely recommended for patients with chronic kidney disease (CKD). Whether or not sodium intake is associated with the progression of CKD and mortality remains uncertain. We evaluated the association between urinary sodium excretion (as a surrogate for sodium intake) with the occurrence of renal failure and mortality in patients with non-dialytic CKD. METHODS: We conducted a retrospective study of patients followed at a CKD clinic care hospital from October 2006 to March 2017. Adult patients with non-dialytic CKD were included. Using a time-to-event analysis, we examined the association of urinary sodium excretion as a categorical variable (categorized as quintiles: 1st quintile: 0.54-2.51 g; 2nd quintile: 2.52-3.11 g, 3rd quintile: 3.12-3.97 g, 4th quintile: 3.98-5.24 g and 5th quintile: 5.26-13.80 g) and the outcomes of interest. The primary outcome was defined as progression to end-stage renal disease requiring any type of renal replacement therapy. The secondary outcome was mortality. RESULTS: Two hundred five patients were included in the study (mean follow up of 2.6 years) with a mean eGFR of 26 (19-41) ml/min/1.73m2. 37 patients (18%) required renal replacement therapy and 52 (25,3%) died. There was association between urinary sodium excretion and need for renal replacement therapy (adjusted HR 0.245; 95%CI 0.660-0.912). There was no association between urinary sodium excretion and mortality in adjusted models. CONCLUSION: Moderate sodium intake was associated with a lower risk of renal failure.

Exploring the causes of the high incidence of delayed graft function after kidney transplantation in Brazil: a multicenter study.

This retrospective multicenter (n = 18) cohort study evaluated the incidence, risk factors, and the impact of delayed graft function (DGF) on 1-year kidney transplant (KT) outcomes. Of 3992 deceased donor KT performed in 2014-2015, the incidence of DGF was 54%, ranging from 29.9% to 87.7% among centers. Risk factors (lower-bound-95%CI OR upper-bound-95%CI ) were male gender (1.066 1.2491.463 ), diabetic kidney disease (1.053 1.2961.595 ), time on dialysis (1.005 1.0071.009 ), retransplantation (1.035 1.3971.885 ), preformed anti-HLA antibodies (1.011 1.3831.892 ), HLA mismatches (1.006 1.0661.130 ), donor age (1.011 1.0171.023 ), donor final serum creatinine (sCr) (1.239 1.3171.399 ), cold ischemia time (CIT) (1.031 1.0431.056 ), machine perfusion (0.401 0.5420.733 ), and induction therapy with rabbit antithymocyte globulin (rATG) (0.658 0.8000.973 ). Duration of DGF > 4 days was associated with inferior renal function and DGF > 14 days with the higher incidences of acute rejection, graft loss, and death. In conclusion, the incidence and duration of DGF were high and associated with inferior graft outcomes. While late referral and poor donor maintenance account for the high overall incidence of DGF, variability in donor and recipient selection, organ preservation method, and type of induction agent may account for the wide variation observed among transplant centers.

Kidney transplantation is associated with reduced myocardial fibrosis. A cardiovascular magnetic resonance study with native T1 mapping.

BACKGROUND: The measurement of native T1 through cardiovascular magnetic resonance (CMR) is a noninvasive method of assessing myocardial fibrosis without gadolinium contrast. No studies so far have evaluated native T1 after renal transplantation. The primary aim of the current study is to assess changes in the myocardium native T1 6 months after renal transplantation. METHODS: We prospectively evaluated 44 renal transplant patients with 3 T CMR exams: baseline at the beginning of transplantation and at 6 months after transplantation. RESULTS: The native T1 time was measured in the midventricular septum and decreased significantly from 1331 ± 52 ms at the baseline to 1298 ± 42 ms 6 months after transplantation (p = 0.001). The patients were split into two groups through a two-step cluster algorithm: In cluster-1 (n = 30) the left ventricular (LV) mass index and the prevalence of diabetes were lower. In cluster-2 (n = 14) the LV mass index and diabetes prevalence were higher. Decrease in native T1 values was significant only in the patients in cluster-1 (p = 0.001). CONCLUSIONS: The native myocardial T1 time decreased significantly 6 months after renal transplant, which may be associated with the regression of the reactive fibrosis. The patients with greater baseline LV mass index and the diabetic group did not reach a significant decrease in T1.

The role of renin-angiotensin system in the chronic allograft nephropathy: an immunohistochemical study.

BACKGROUND: Evidences suggest a role of renin-angiotensin system (RAS) in the development of chronic allograft injury. METHODS: We correlated intrarenal angiotensin-converting enzyme, angiotensin II (Angio II) and transforming growth factor ß1 (TGFß1) expression in 58 biopsies-proven chronic allograft nephropathy (CAN) with tissue injury and allograft survival. RESULTS: The biopsies with CAN were graded according to Banff classification as I (22 cases), II (17) and III (19); 27 biopsies also showed a mononuclear inflammatory infiltrate in scarred areas. There were increased expression of angiotensin converting-enzyme (ACE), Angio II and TGFß1 mainly in tubulointerstitial compartment in the group with CAN; there was no association of Angio II and TGFß1 expression with interstitial fibrosis. There were no significant differences of ACE, Angio II and TGFß1 expression between the patients treated and untreated with RAS blockade, and with the graft outcome. Interstitial inflammatory infiltrate had positive correlation with interstitial fibrosis and significant impact on graft survival at 8 years. CONCLUSIONS: Our study showed in a group of cases with CAN a high percentage of inflammatory infiltrate that correlated with interstitial fibrosis and graft outcome. The chronic inflammatory changes in these cases did not show significant association with local RAS expression.

Safety of cinacalcet in children and adolescents with chronic kidney disease-mineral bone disorder: systematic review and proportional meta-analysis of case series.

BACKGROUND: Mineral and bone disease in children with chronic kidney disease can cause abnormalities in calcium, phosphorus, parathyroid hormone, and vitamin D and when left untreated can result in impaired growth, bone deformities, fractures, and vascular calcification. Cinacalcet is a calcimimetic widely used as a therapy to reduce parathyroid hormone levels in the adult population, with hypocalcemia among its side effects. The analysis of safety in the pediatric population is questioned due to the scarcity of randomized clinical trials in this group. OBJECTIVE: To assess the onset of symptomatic hypocalcemia or other adverse events (serious or non-serious) with the use of cinacalcet in children and adolescents with mineral and bone disorder in chronic kidney disease. DATA SOURCES AND STUDY ELIGIBILITY CRITERIA: The bibliographic search identified 2699 references from 1927 to August/2023 (57 LILACS, 44 Web of Science, 686 PubMed, 131 Cochrane, 1246 Scopus, 535 Embase). Four references were added from the bibliography of articles found and 12 references from the gray literature (Clinical Trials). Of the 77 studies analyzed in full, 68 were excluded because they did not meet the following criteria: population, types of studies, medication, publication types and 1 article that did not present results (gray literature). PARTICIPANTS AND INTERVENTIONS: There were 149 patients aged 0-18 years old with Chronic Kidney Disease and mineral bone disorder who received cinacalcet. STUDY APPRAISAL AND SYNTHESIS METHODS: Nine eligible studies were examined for study type, size, intervention, and reported outcomes. RESULTS: There was an incidence of 0.2% of fatal adverse events and 16% of serious adverse events (p < 0.01 and I2 = 69%), in addition to 10.7% of hypocalcemia, totaling 45.7% of total adverse events. LIMITATIONS: There was a bias in demographic information and clinical characteristics of patients in about 50% of the studies and the majority of the studies were case series. CONCLUSIONS AND IMPLICATIONS OF KEY FINDINGS: If used in the pediatric population, the calcimimetic cinacalcet should be carefully monitored for serum calcium levels and attention to possible adverse events, especially in children under 50 months. SYSTEMATIC REVIEW REGISTRATION NUMBER (PROSPERO REGISTER): CRD42019132809.

Radiological presentation of active pulmonary tuberculosis in kidney transplant recipients: a retrospective study of four cases and a review of the literature.

Although kidney transplantation is the best therapeutic option for patients with chronic kidney disease, the immunosuppression required greatly increases susceptibility to infections that are responsible for high post-transplant mortality. Pulmonary tuberculosis (TB) represents a major cause of such infections, and its early diagnosis is therefore quite important. In view of that, we researched the manifestations of active pulmonary TB in kidney transplant recipients, through chest X-ray and computed tomography (CT), as well as determining the number of cases of active pulmonary TB occurring over a 3.5-year period at our institution. We identified four cases of active pulmonary TB in kidney transplant recipients. The CT scans provided information complementary to the chest X-ray findings in all four of those cases. We compared our CT findings with those reported in the literature. We analyzed our experience in conjunction with an extensive review of the literature that was nevertheless limited because few studies have been carried out in lowand middle-income countries, where the incidence of TB is higher.

Apesar de o transplante renal ser a melhor opção terapêutica para pacientes com doença renal crônica, a imunodepressão decorrente desse tratamento eleva muito a suscetibilidade desses pacientes a infecções, responsáveis por altas taxas de mortalidade pós-operatórias. A tuberculose (TB) pulmonar é uma significativa causa dessas infecções, sendo muito importante o seu diagnóstico precoce. Assim, nós pesquisamos as manifestações da TB pulmonar ativa nessa população de transplantados renais por meio de radiografias simples e tomografia computadorizada (TC) do tórax, também para estabelecer o número de casos de TB pulmonar ativa em nossa instituição após levantamento de 3,5 anos. Encontramos quatro casos de TB pulmonar ativa em pacientes transplantados renais. A TC forneceu informações adicionais em relação às radiografias de tórax em 100% dos casos analisados. Comparamos os nossos achados de TC com os relatados na literatura. Somamos a experiência obtida com extensa revisão da literatura, ainda limitada nessa questão, com poucos estudos realizados em países em desenvolvimento onde a incidência de TB é maior.

Body fat predicts urinary tract infection in kidney transplant recipients: a prospective cohort study.

BACKGROUND: The association between obesity and infectious diseases is increasingly reported in the literature. There are scarce studies on the association between obesity and urinary tract infection after kidney transplantation (KTx). These studies defined obesity based on body mass index, and their results were conflicting. The present study aimed to evaluate this association using bioelectrical impedance analysis for body composition evaluation, and obesity definition. METHODS: A single-center cohort study was conducted. Demographic, clinical, anthropometric, and laboratory data were collected at KTx admission, and bioelectrical impedance analysis was performed to measure the visceral fat area, waist circumference, and total fat mass. The occurrence of urinary tract infection (symptomatic bacteriuria and/or histological evidence of pyelonephritis) was evaluated within three months after KTx. RESULTS: Seventy-seven patients were included in the cohort, and 67 were included in the final analysis. Urinary tract infection was diagnosed in 23.9% of the transplanted patients. Waist circumference (HR: 1.053; 95% CI 1.005-1.104; p = 0.032), visceral fat area (HR: 1.015; 95% CI 1.003-1.027; p = 0.014), and total fat mass (HR: 1.075; 95% CI 1.008-1.146; p = 0.028) were associated with urinary tract infection occurrence after KTx, using Cox regression models. Patients with high waist circumference (above 102 cm for men and above 88 cm for women) had a 4.7 times higher risk of a urinary tract infection than those with normal waist circumference (HR: 4.726; 95% CI 1.267-17.630; p = 0.021). Kaplan-Meier curves showed that patients with high waist circumference, high visceral fat area, and high total fat mass had more urinary tract infections (Log-rank test p = 0.014, p = 0.020, and p = 0.018, respectively). Body mass index was not able to predict urinary tract infection in the study sample. CONCLUSIONS: Waist circumference, visceral fat area, and total fat mass, assessed by bioelectrical impedance analysis, were predictors of urinary tract infection risk within the first three months after KTx.

Use of Machine Perfusion to Increase the Number of Expanded Criteria Deceased Donor Kidney Transplants: A Pharmacoeconomic Analysis.

Background: The discard of expanded criteria donor (ECD) kidneys is unacceptably high, considering the growing demand for transplantation. Using machine perfusion may reduce the discard rate, increase the number of transplants, and reduce mortality on the waiting list. Methods: We developed a 5-y Markov model to simulate incorporating the pulsatile perfusion machine into the current government-funded healthcare system. The model compared the universal use of static cold storage for all kidneys with the selective use of machine perfusion for ECD kidneys. Real-life data were used to compose the cohort characteristics in this model. This pharmacoeconomic analysis aimed to determine the cost-effectiveness and budgetary impact of using machine perfusion to preserve ECD kidneys. Results: Compared with the universal use of static cold storage, the use of machine perfusion for ECD kidneys was associated with an increase in the number of kidney transplants (n = 1123), a decrease in the number of patients on the waiting list (n = 815), and decrease in mortality (n = 120), with a cost difference of US dollar 4 486 009 in the period. The budget impact analysis revealed an additional cost of US dollar 4 453 749 >5 y. The budget impact analysis demonstrated a progressive reduction in costs, becoming cost-saving during the last year of the analysis. Conclusions: This stochastic model showed that incorporating machine perfusion for ECD kidneys is most often a dominant or cost-effective technology associated with an increase in the number of transplants and a reduction in the number of patients on the waiting list, reducing mortality on the waiting list.

Mononuclear inflammatory infiltrate and microcirculation injury in acute rejection: role in renal allograft survival.

This study aimed at investigating associations between monocytes/macrophages (Mo) infiltration and three important criteria associated with acute antibody-mediated rejection: C4d staining, microcirculation injury, and graft survival time. By quantitative analysis, Mo were counted in peritubular capillaries and in the interstitial compartment (peritubular/interstitial Mo), and they were also identified in glomeruli (glomerular Mo). The study included 47 patients who received renal allograft between 1991 and 2009. Capillaritis and glomerulitis were classified by the Banff scoring system, and C4d and Mo were analyzed by immunohistochemistry. In the quantitative analysis, the mean values of 50 Mo per 10 high-power fields (HPF) and 4 Mo per glomerulus were used as cut-off points for the peritubular/interstitial and glomerular compartments, respectively. Positive C4d cases were associated with the groups of biopsies with a mean value ≥50 Mo per 10 HPF (p = 0.01) and ≥4 Mo per glomerulus (p = 0.02). The group with a mean value ≥4 Mo per glomerulus also showed association with the presence of glomerulitis (p = 0.02). Peritubular/interstitial Mo did not associate with glomerulitis. Capillaritis did not show association with peritubular/interstitial or glomerular Mo. As regards graft survival, the infiltration of Mo in glomeruli interfered with allograft survival (p = 0.01). The group with a mean value of ≥4 glomerular Mo presented worse survival at the time of the 1-year follow-up. According to the literature, our data showed that infiltration of mononuclear cells was associated with C4d staining, microcirculation injury, and glomerulitis, in particular, and that glomerular macrophages could influence renal allograft survival.

Genetic and phenotypic profile of Fabry disease in the population of Vale do Paraiba and Eastern São Paulo.

INTRODUCTION: Fabry disease (FD) is an inborn error of metabolism characterized by α-galactosidase A deficiency. The primary objective was to evaluate the genetic and phenotypic profile of Fabry disease in hemodialysis. METHODS: Observational cohort study to determine the incidence of genetic variations and phenotypic changes for FD in hemodialysis patients in the Paraiba Valley and Eastern São Paulo. Genetic testing for the GLA gene was performed for men and women over 12 years of age at the hemodialysis clinics between January 2016 and December 2019 as a screening protocol. RESULTS: The cases came from screening exams of the index case among patients with chronic kidney disease, resulting in 17 families and totaling 82 patients under study. The classification of the most prevalent variant was that of uncertain significance (54%), followed by the pathogenic variant (46%). Five patients in two families were described with two types of variants not previously described in the literature, with pathogenic behavior. Comparing the types of variants, the presence of a pathogenic variant was associated with higher levels of lysoGB3, lower values for alpha-GAL activity and higher frequency of symptoms related to FD. CONCLUSION: We characterized an extensive population of patients with FD variants with rich genetic, clinical and biomarker details. We believe that this study can help to better characterize the Brazilian population with FD and the most frequent types of variants.

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.

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.

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.

Development and validation of a simple machine learning tool to predict mortality in leptospirosis.

Predicting risk factors for death in leptospirosis is challenging, and identifying high-risk patients is crucial as it might expedite the start of life-saving supportive care. Admission data of 295 leptospirosis patients were enrolled, and a machine-learning approach was used to fit models in a derivation cohort. The comparison of accuracy metrics was performed with two previous models-SPIRO score and quick SOFA score. A Lasso regression analysis was the selected model, demonstrating the best accuracy to predict mortality in leptospirosis [area under the curve (AUC-ROC) = 0.776]. A score-based prediction was carried out with the coefficients of this model and named LeptoScore. Then, to simplify the predictive tool, a new score was built by attributing points to the predictors with importance values higher than 1. The simplified score, named QuickLepto, has five variables (age > 40 years; lethargy; pulmonary symptom; mean arterial pressure < 80 mmHg and hematocrit < 30%) and good predictive accuracy (AUC-ROC = 0.788). LeptoScore and QuickLepto had better accuracy to predict mortality in patients with leptospirosis when compared to SPIRO score (AUC-ROC = 0.500) and quick SOFA score (AUC-ROC = 0.782). The main result is a new scoring system, the QuickLepto, that is a simple and useful tool to predict death in leptospirosis patients at hospital admission.

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.

Renal function at 12 months of kidney transplantation comparing tacrolimus and mycophenolate with tacrolimus and mTORi in donors with different KDPI ranges. A multicenter cohort study using propensity scoring.

Introduction: The combination of tacrolimus/mTORi compared to tacrolimus/mycophenolate (MMF) was shown to be safe in the TRANSFORM trial. For donors with a high KDPI (Kidney Donor Profile Index), however, there are no data to support the effectiveness of this regimen. The main objective of this study was to explore the influence of the KDPI on 12-month renal function (eGFR) in patients receiving mTORi or MMF. Methods: Multicenter cohort study of four Brazilian services that use the tacrolimus with mTORi as a protocol. Data from 2008 to 2018 of the tacrolimus/mycophenolate (MMF) and tacrolimus/mTORi (mTORi) regimens in renal transplant recipients over 18 years old were collected. For better homogeneity, the propensity score was used. Afterward, the method used for group selection ("match") was the K-nearest neighbor (KNN) method. New analyses were performed on this new balanced sample, and two different subsamples were constituted based on the median KDPI. Results: The global analysis (n = 870) showed that the major determinant of worse kidney function was high KDPI. Afterward, the three strata were analyzed. In the first stratum (KDPI up to 50), 242 patients were evaluated, with 121 in each group. The eGFR was 64 ml/min/1.73 m2 in the mTORi group compared to 63 in the MMF group, p = 0.4, and when imputed eGFR was evaluated, 61 in the mTORi and 53 in the MMF, p = 0.065. In the second stratum (KDPI from 50 to 85), 282 patients were evaluated, with 141 in each group. eGFR was 46 ml/min/1.73 m2 in mTORi compared to 48 in MMF, p = 0.4, and when imputed eGFR was evaluated, 40 mTORi and 41 MMF, p = 0.8. In the last stratum (KDPI higher than 85) with n = 126 and 63 cases per group, eGFR was 36 ml/min/1.73 m2 in mTORi compared to 39 in MMF, p = 0.2, and when imputed eGFR was evaluated, 30 mTORi and 34 MMF, p = 0.2. Discussion: The regimen using mTOR inhibitor is an effective and safe regimen when compared to the standard regimen. In addition, the scheme seems to offer additional protection against infections and may be an important ally in cases of high risk for these pathologies.

Brazilian consensus recommendations for the diagnosis, screening, and treatment of individuals with fabry disease: Committee for Rare Diseases - Brazilian Society of Nephrology/2021.

Fabry disease (FD) is an X-linked inherited disorder caused by mutations in the GLA gene encoding enzyme alpha-galactosidase A (α-Gal A). The purpose of this study was to produce a consensus statement to standardize the recommendations concerning kidney involvement in FD and provide advice on the diagnosis, screening, and treatment of adult and pediatric patients. This consensus document was organized from an initiative led by the Committee for Rare Diseases (Comdora) of the Brazilian Society of Nephrology (SBN). The review considered randomized clinical trials, real-world data studies, and the expertise of its authors. The purpose of this consensus statement is to help manage patient and physician expectations concerning the outcomes of treatment. Our recommendations must be interpreted within the context of available evidence. The decisions pertaining to each individual case must be made with the involvement of patients and their families and take into account not only the potential cost of treatment, but also concurrent conditions and personal preferences. The Comdora intends to update these recommendations regularly so as to reflect recent literature evidence, real-world data, and appreciate the professional experience of those involved. This consensus document establishes clear criteria for the diagnosis of FD and for when to start or stop specific therapies or adjuvant measures, to thus advise the medical community and standardize clinical practice.