ICD-10 impact on ascertainment and accuracy of oral cleft cases as recorded by the Brazilian national live birth information system

The Latin American network for congenital malformation surveillance: ReLAMC

The early detection of congenital anomaly epidemics occurs when comparing current with previous frequencies in the same population. The success of epidemiologic surveillance depends on numerous factors, including the accuracy of the rates available in the base period, wide population coverage, and short periodicity of analysis. This study aims to describe the Latin American network of congenital malformation surveillance: ReLAMC, created to increase epidemiologic surveillance in Latin America. We describe the main steps, tasks, strategies used, and preliminary results. From 2017 to 2019, five national registries (Argentina [RENAC], Brazil [SINASC/SIM-BRS], Chile [RENACH], Costa Rica [CREC], Paraguay [RENADECOPY-PNPDC]), six regional registries (Bogotá [PVSDC-Bogota], Cali [PVSDC-Cali], Maule [RRMC SSM], Nicaragua [SVDC], Nuevo-León [ReDeCon HU], São Paulo [SINASC/SIM-MSP]) and the ECLAMC hospital network sent data to ReLAMC on a total population of 9,152,674 births, with a total of 101,749 malformed newborns (1.1%; 95% CI 1.10-1.12). Of the 9,000,651 births in countries covering both live and stillbirths, 88,881 were stillborn (0.99%; 95% CI 0.98-0.99), and among stillborns, 6,755 were malformed (7.61%; 95% CI 7.44-7.79). The microcephaly rate was 2.45 per 10,000 births (95% CI 2.35-2.55), hydrocephaly 3.03 (2.92-3.14), spina bifida 2.89 (2.78-3.00), congenital heart defects 15.53 (15.27-15.79), cleft lip 2.02 (1.93-2.11), cleft palate and lip 2.77 (2.66-2.88), talipes 2.56 (2.46-2.67), conjoined twins 0.16 (0.14-0.19), and Down syndrome 5.33 (5.18-5.48). Each congenital anomaly showed heterogeneity in prevalence rates among registries. The harmonization of data in relation to operational differences between registries is the next step in developing the common ReLAMC database.

Administrative Data Linkage in Brazil: Potentials for Health Technology Assessment

Health technology assessment (HTA) is the systematic evaluation of the properties and impacts of health technologies and interventions. In this article, we presented a discussion of HTA and its evolution in Brazil, as well as a description of secondary data sources available in Brazil with potential applications to generate evidence for HTA and policy decisions. Furthermore, we highlighted record linkage, ongoing record linkage initiatives in Brazil, and the main linkage tools developed and/or used in Brazilian data. Finally, we discussed the challenges and opportunities of using secondary data for research in the Brazilian context. In conclusion, we emphasized the availability of high quality data and an open, modern attitude toward the use of data for research and policy. This is supported by a rigorous but enabling legal framework that will allow the conduct of large-scale observational studies to evaluate clinical, economical, and social impacts of health technologies and social policies.

Projection Word Embedding Model With Hybrid Sampling Training for Classifying ICD-10-CM Codes: Longitudinal Observational Study

BACKGROUND

Most current state-of-the-art models for searching the International Classification of Diseases, Tenth Revision Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification, wherein discharge notes present only positive disease descriptions.

OBJECTIVE

We aimed to propose a projection word2vec model and a hybrid sampling method. In addition, we aimed to conduct a series of experiments to validate the effectiveness of these methods.

METHODS

We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the word2vec models and used these embeddings to identify the three-character-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan, from June 1, 2015, to June 30, 2017, were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017, to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted.

RESULTS

In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure=0.7371/0.6698).

CONCLUSIONS

The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the models could effectively handle emerging diseases. The proposed hybrid sampling method enables the model to behave like a human expert.