Development and evaluation of standardized pregnancy identification and trimester distribution algorithms in U.S. IBM MarketScan® Commercial and Medicaid data

Antenatal care inequalities in South Korea: An analysis of health insurance claims data (2013-2022) in a high-resource, high-use country

OBJECTIVE

The aim of the present study was to explore inequalities in antenatal care (ANC) in South Korea. Based on the guidelines of the WHO, we categorized less than eight visits to an obstetrical facility as insufficient ANC. We examined ANC inequalities associated with age, disability, nationality, income, and geographic accessibility.

METHODS

We extracted delivery event claimed from 2013 to 2022 from the National Health Insurance Service database. By tracing back 270 days from the delivery date, we counted the number of antenatal visits for each childbirth and calculated the proportion of women with insufficient ANC and assessed both absolute and relative inequalities for each population group. The logistic regression analysis for both underuse and overuse of ANC were conducted.

RESULTS

Out of 3 416 517 childbirths, 104 109 women (3.0%) had fewer than eight ANC visits. Although the average number of ANC visits reached 18.7 in 2022, significant inequalities persisted across different population groups. The insufficient ANC rate was 28.1% for teenage women, 6.4% for disabled women, 10.7% for non-Korean women, and 15.2% for dependents of medical aid households. Women with low income and those living in obstetric care underserved areas also exhibited higher ANC insufficiency. From 2021 to 2022, sufficiency in ANC decreased for teenage, disabled, and non-Korean women, highlighting the effects of the COVID-19 pandemic.

CONCLUSION

Antenatal care inequalities are evident in South Korea's well-resourced health system. There is a need for further investigation into these disparities and the qualitative aspects of maternity care services.

Patients with autoimmune skin diseases are at increased risk of adverse pregnancy outcomes

BACKGROUND

Increased rates of adverse pregnancy outcomes have been reported in association with rheumatologic diseases such as systemic lupus erythematosus, rheumatoid arthritis, dermatomyositis. However, little is known about pregnancy outcomes in patients with autoimmune skin diseases.

OBJECTIVE

This study aimed to determine the frequency of adverse pregnancy outcomes in patients with autoimmune skin diseases. We hypothesized that similar to rheumatic diseases, the rate of adverse pregnancy outcomes in patients with autoimmune skin diseases would be higher than the general population.

STUDY DESIGN

This is a case control study using the TriNetX US Collaborative Network, which is a database of electronic medical records of >95 million patients seen at 57 healthcare organizations in the United States. All pregnant women between the ages of 15 and 44 years who were seen at a healthcare organization between January 1, 2016 and December 31, 2021 were included. Participants with autoimmune skin disease were matched to healthy controls and controls with systemic rheumatologic conditions (systemic lupus erythematosus or rheumatoid arthritis). For both the autoimmune skin disease and healthy control groups, those with systemic rheumatologic condition or hidradenitis suppurativa were excluded. The primary outcomes were adverse pregnancy outcomes defined as spontaneous abortion, gestational hypertension, preeclampsia or eclampsia, gestational diabetes mellitus, intrauterine growth restriction, preterm premature rupture of membranes, preterm birth, and stillbirth. Patients with autoimmune skin diseases and controls were 1:1 propensity score-matched by age, race, ethnicity, comorbidities, obesity, and substance use. For each outcome, odds ratio with a 95% confidence interval was calculated.

RESULTS

A total of 2788 patients with autoimmune skin diseases were matched to 2788 healthy controls. Patients with autoimmune skin diseases were at a higher risk of spontaneous abortions than controls (odds ratio, 1.54; 95% confidence interval, 1.36-1.75; P<.001). Compared with patients with systemic lupus erythematosus, patients with autoimmune skin diseases were at lower risk of having infants with intrauterine growth restriction (odds ratio, 0.59; 95% confidence interval, 0.4-0.87; P=.01), preterm birth (odds ratio, 0.68; 95% confidence interval, 0.47-0.98; P=.04), and stillbirth (odds ratio, 0.50; 95% confidence interval, 0.25-0.97; P=.04). The differences in adverse pregnancy outcomes between patients with autoimmune skin diseases and those with rheumatoid arthritis were not statistically significant.

CONCLUSION

Patients with autoimmune skin diseases are at a higher risk of spontaneous abortions than patients without autoimmune skin diseases. When analyzed by each autoimmune skin disease, patients with cutaneous lupus erythematosus or vitiligo remained at increased risk of spontaneous abortions compared with patients without autoimmune skin diseases. Patients with autoimmune skin diseases have similar risks of adverse pregnancy outcomes as patients with rheumatoid arthritis, but lower risks than patients with systemic lupus erythematosus.

Exploring patient medication adherence and data mining methods in clinical big data: A contemporary review

BACKGROUND

Increasingly, patient medication adherence data are being consolidated from claims databases and electronic health records (EHRs). Such databases offer an indirect avenue to gauge medication adherence in our data-rich healthcare milieu. The surge in data accessibility, coupled with the pressing need for its conversion to actionable insights, has spotlighted data mining, with machine learning (ML) emerging as a pivotal technique. Nonadherence poses heightened health risks and escalates medical costs. This paper elucidates the synergistic interaction between medical database mining for medication adherence and the role of ML in fostering knowledge discovery.

METHODS

We conducted a comprehensive review of EHR applications in the realm of medication adherence, leveraging ML techniques. We expounded on the evolution and structure of medical databases pertinent to medication adherence and harnessed both supervised and unsupervised ML paradigms to delve into adherence and its ramifications.

RESULTS

Our study underscores the applications of medical databases and ML, encompassing both supervised and unsupervised learning, for medication adherence in clinical big data. Databases like SEER and NHANES, often underutilized due to their intricacies, have gained prominence. Employing ML to excavate patient medication logs from these databases facilitates adherence analysis. Such findings are pivotal for clinical decision-making, risk stratification, and scholarly pursuits, aiming to elevate healthcare quality.

CONCLUSION

Advanced data mining in the era of big data has revolutionized medication adherence research, thereby enhancing patient care. Emphasizing bespoke interventions and research could herald transformative shifts in therapeutic modalities.