Assessment of potential transthyretin amyloid cardiomyopathy cases in the Brazilian public health system using a machine learning mode

OBJECTIVES: To identify and describe the profile of potential transthyretin cardiac amyloidosis (ATTR-CM) cases in the Brazilian public health system (SUS), using a predictive machine learning (ML) model. METHODS: This was a retrospective descriptive database study that aimed to estimate the frequency of potential ATTR-CM cases in the Brazilian public health system using a supervised ML model, from January 2015 to December 2021. To build the model, a list of ICD-10 codes and procedures potentially related with ATTR-CM was created based on literature review and validated by experts. RESULTS: From 2015 to 2021, the ML model classified 262 hereditary ATTR-CM (hATTR-CM) and 1,581 wild-type ATTR-CM (wtATTR-CM) potential cases. Overall, the median age of hATTR-CM and wtATTR-CM patients was 66.8 and 59.9 years, respectively. The ICD-10 codes most presented as hATTR-CM and wtATTR-CM were related to heart failure and arrythmias. Regarding the therapeutic itinerary, 13% and 5% of hATTR-CM and wtATTR-CM received treatment with tafamidis meglumine, respectively, while 0% and 29% of hATTR-CM and wtATTR-CM were referred to heart transplant. CONCLUSION: Our findings may be useful to support the development of health guidelines and policies to improve diagnosis, treatment, and to cover unmet medical needs of patients with ATTR-CM in Brazil.

Assessment of potential transthyretin amyloid cardiomyopathy cases in the Brazilian public health system using a machine learning model.

OBJECTIVES: To identify and describe the profile of potential transthyretin cardiac amyloidosis (ATTR-CM) cases in the Brazilian public health system (SUS), using a predictive machine learning (ML) model. METHODS: This was a retrospective descriptive database study that aimed to estimate the frequency of potential ATTR-CM cases in the Brazilian public health system using a supervised ML model, from January 2015 to December 2021. To build the model, a list of ICD-10 codes and procedures potentially related with ATTR-CM was created based on literature review and validated by experts. RESULTS: From 2015 to 2021, the ML model classified 262 hereditary ATTR-CM (hATTR-CM) and 1,581 wild-type ATTR-CM (wtATTR-CM) potential cases. Overall, the median age of hATTR-CM and wtATTR-CM patients was 66.8 and 59.9 years, respectively. The ICD-10 codes most presented as hATTR-CM and wtATTR-CM were related to heart failure and arrythmias. Regarding the therapeutic itinerary, 13% and 5% of hATTR-CM and wtATTR-CM received treatment with tafamidis meglumine, respectively, while 0% and 29% of hATTR-CM and wtATTR-CM were referred to heart transplant. CONCLUSION: Our findings may be useful to support the development of health guidelines and policies to improve diagnosis, treatment, and to cover unmet medical needs of patients with ATTR-CM in Brazil.

A machine learning model to assess potential misdiagnosed dengue hospitalization.

Dengue, like other arboviruses with broad clinical spectra, can easily be misdiagnosed as other infectious diseases due to the overlap of signs and symptoms. During large outbreaks, severe dengue cases have the potential to overwhelm the health care system and understanding the burden of dengue hospitalizations is therefore important to better allocate medical care and public health resources. A machine learning model that used data from the Brazilian public healthcare system database and the National Institute of Meteorology (INMET) was developed to estimate potential misdiagnosed dengue hospitalizations in Brazil. The data was modeled into a hospitalization level linked dataset. Then, Random Forest, Logistic Regression and Support Vector Machine algorithms were assessed. The algorithms were trained by dividing the dataset in training/test set and performing a cross validation to select the best hyperparameters in each algorithm tested. The evaluation was done based on accuracy, precision, recall, F1 score, sensitivity, and specificity. The best model developed was Random Forest with an accuracy of 85% on the final reviewed test. This model shows that 3.4% (13,608) of all hospitalizations in the public healthcare system from 2014 to 2020 could have been dengue misdiagnosed as other diseases. The model was helpful in finding potentially misdiagnosed dengue and might be a useful tool to help public health decision makers in planning resource allocation.

Adverse events of COVID-19 vaccines in pregnant and postpartum women in Brazil: A cross-sectional study.

BACKGROUND: By the fact that pregnant and postpartum women are currently using COVID-19 vaccines, ensure their safety is critical. So, more safety evidence is crucial to include this new technology to their vaccine's calendar and to develop public policies regarding the support and training of Health Care Personnel. This study aims to describe the adverse events (AE) of COVID-19 vaccines in pregnant and postpartum women in the early stage of vaccination campaign in Brazil. METHODS: An observational cross-sectional study using data from the Brazilian surveillance information system to characterize the AE of COVID-19 vaccines (Sinovac/Butantan, Pfizer/BioNTech, AstraZeneca and Janssen) in Brazilian pregnant and postpartum women from April to August 2021. Frequency and incidence rate of AE for COVID-19 vaccines were assessed. RESULTS: 3,333 AE following immunization were reported for the study population. AE incidence was 309.4/100,000 doses (95% CI 297.23, 321.51). Within the vaccines available, Sinovac/Butantan had the lowest incidence (74.08/100,000 doses; 95% CI 63.47, 84.69). Systemic events were the most frequent notified (82.07%), followed by local (11.93%) and maternal (4.74%), being most of them classified as non-severe (90.65%). CONCLUSION: Our results corroborate the recommendation of vaccination for these groups. Even though, further studies appraising a longer observation time are still needed to provide a broader safety aspect for the vaccines currently under use for this population.

Yellow fever vaccine safety in immunocompromised individuals: a systematic review and meta-analysis.

BACKGROUND: Yellow fever (YF) is an arbovirus with variable severity, including severe forms with high mortality. The vaccination is the most effective measure to protect against the disease. Non-serious and serious adverse events have been described in immunocompromised individuals, but previous studies have failed to demonstrate this association. This systematic review assessed the risk of adverse events after YF vaccination in immunocompromised individuals compared with its use in non-immunocompromised individuals. METHODS: A search was conducted in the MEDLINE, LILACS, EMBASE, SCOPUS, DARE, Toxiline, Web of Science and grey literature databases for publications until February 2021. Randomized and quasi-randomized clinical trials and observational studies that included immunocompromised participants (individuals with HIV infection, organ transplants, with cancer, who used immunosuppressive drugs for rheumatologic diseases and those on immunosuppressive therapy for other diseases) were selected. The methodological quality of observational or non-randomized studies was assessed by the ROBINS-I tool. Two meta-analyses were performed, proportion and risk factor analyses, to identify the summary measure of relative risk (RR) in the studies that had variables suitable for combination. RESULTS: Twenty-five studies were included, most with risk of bias classified as critical. Thirteen studies had enough data to carry out the proposed meta-analyses. Seven studies without a comparator group had their results aggregated in the proportion meta-analysis, identifying an 8.5% [95% confidence interval (CI) 0.07-21.8] risk of immunocompromised individuals presenting adverse events after vaccination. Six cohort studies were combined, with an RR of 1.00 (95% CI 0.78-1.29). Subgroup analysis was performed according to the aetiology of immunosuppression and was also unable to identify an increased risk of adverse events following vaccination. CONCLUSIONS: It is not possible to affirm that immunocompromised individuals, regardless of aetiology, have a higher risk of adverse events after receiving the YF vaccine.

Meningococcal disease epidemiology in Brazil (2005-2018) and impact of MenC vaccination.

BACKGROUND: Meningococcal disease (MD) presents a substantial public health problem in Brazil. Meningococcal C conjugate (MenC) vaccination was introduced into the routine infant immunization program in 2010, followed by adolescent vaccination in 2017. We evaluated changes in national and regional MD incidence and mortality between 2005 and 2018, serogroup distribution and vaccine coverage. METHODS: Data were obtained from national surveillance systems from 2005 to 2018. Age-stratified incidence and mortality rates were calculated and a descriptive time-series analysis was performed comparing rates in the pre-(2005-2009) and post-vaccination (2011-2018) periods; MD due to specific meningococcal serogroups were analyzed in the pre-(2007-2009) and post-vaccination (2011-2018) periods. RESULTS: From 2005 to 2018, 31,108 MD cases were reported with 6496 deaths; 35% of cases and deaths occurred in children < 5 years. Incidence and mortality rates declined steadily since 2012 in all age-strata, with significantly lower incidence and mortality in the post-vaccine introduction period in children aged < 1-year, 1-4 years, 5-9 years and 10-14 years. A significant decline in MenC disease in children < 5 years was observed following MenC vaccine introduction; infants < 1 year, from 3.30/100,000 (2007-2009) to 1.08/100,000 (2011-2018) and from 1.44/100,000 to 0.42/100,000 in 1-4-year-olds for these periods. Reductions in MenB disease was also observed. MenW remains an important cause of MD with 748 cases reported across 2005-2018. While initial infant vaccination coverage was high (>95% nationwide), this has since declined (to 83% in 2018); adolescent uptake was < 20% in 2017/18). Regional variations in outcomes and vaccine coverage were observed. CONCLUSION: A substantial decline in incidence and mortality rates due to MD was seen following MenC vaccine introduction in Brazil, especially among children < 5 years chiefly driven by reductions in MenC serogroup. While these benefits are considerable, the prevalence of MD due to other serogroups such as MenW and MenB remains a concern. A video summary linked to this article can be found on Figshare: https://doi.org/10.6084/m9.figshare.13379612.v1.