Artificial intelligence (AI) can potentially enhance cognitive assessment practices in maternal and child health nursing education. Objectives: To evaluate the reliability, accuracy and precision, and external validity of an AI-assisted answer assessment (4A) program for cognitive assessments in nursing education. Methods: This study is a validation study. Initially, 170 nursing students from northern Thailand participated, with 52 randomly selected for detailed testing. Agreement testing between the 4A program and human experts was conducted using the intraclass correlation coefficient (ICC). Accuracy and precision testing compared 4A scores with human expert assessments via the McNemar test. External validation involved 138 participants to compare the 4A program’s assessments against national examination outcomes using logistic regression. Results: Results indicated a high level of consistency between the 4A program and human experts (ICC = 0.886). With an accuracy of 0.808 and a precision of 0.913, compared to the human expert’s accuracy of 0.923 and precision of 1.000. The McNemar test (χ2 = 0.4, p = 0.527) showed no significant difference in evaluation performance between AI and human experts. Higher scores on the 4A program significantly predicted success in the national nursing examination (OR: 1.124, p = 0.031). Conclusions: The 4A program demonstrates potential in reliably assessing nursing students’ cognitive abilities and predicting exam success. This study advocates for the continued integration of AI in educational assessments and the importance of refining AI systems to better align with traditional assessment methods.
Objectives: Prospective anthropometric data on how women above and below the Asian-specific BMI ≥ 23 kg/m2 cut-off differ across the maternal continuum remain limited. Because these data were collected in 2017–2018, before Thailand’s 2022 adoption of the threshold in antenatal care, this study describes central adiposity indicators in two independent cohorts of Thai women as a pre-implementation baseline. Methods: In this descriptive longitudinal dual-cohort study at a tertiary centre in Northern Thailand, 192 women formed two independent cohorts: Cohort A (pregnancy, from 12 weeks’ gestation; n = 110) and Cohort B (delivery to 24 weeks postpartum; n = 82), with no woman in both. Women were stratified by pre-pregnancy BMI (<23 vs. ≥23 kg/m2). Waist-to-height ratio (WHtR, primary) and mid-upper arm circumference (MUAC, secondary) were measured at seven timepoints and validated against 3D body scanning (r = 0.92–0.99). Results: At 12 weeks’ gestation, the ≥23 kg/m2 stratum had higher WHtR (0.58 vs. 0.49; d = 1.56) and MUAC (32.52 vs. 26.19 cm; d = 1.98; both p < 0.001). Postpartum, the <23 kg/m2 stratum returned to WHtR < 0.50 by Week 8, whereas the ≥23 kg/m2 stratum remained above 0.50 through 24 weeks (0.56 vs. 0.48; p < 0.001). Conclusions: The ≥23 kg/m2 stratum showed higher central adiposity indicators from early pregnancy and, in the separate postpartum cohort, values that remained above 0.50 through 24 weeks. Because the cohorts comprised different women, these patterns are descriptive and cannot demonstrate within-woman retention. They nonetheless suggest the cut-off may identify women who could benefit from earlier antenatal and extended postpartum nursing assessment, pending confirmation in within-woman studies.
Background: Nursing education faces challenges in developing critical thinking and digital literacy among Generation Z students, particularly in maternal–newborn care contexts where evidence-based practice is essential. Objectives: To evaluate the effectiveness of an AI-assisted podcasting intervention on critical thinking and digital literacy among nursing students and explore their experiences. Methods: A convergent mixed-methods design included 48 third-year nursing students who created educational podcasts using AI tools (Sci Space for literature search, Notebook LM for synthesis). Quantitative data were analyzed using paired t-tests; qualitative data from three focus groups (n = 15) underwent thematic analysis. Results: Critical thinking scores increased significantly from 89.71 (SD = 13.43) to 117.29 (SD = 9.94), (t = −13.332, p < 0.001). Digital literacy scores improved from 37.98 (SD = 5.84) to 46.94 (SD = 4.11), (t = −9.407, p < 0.001). Four themes emerged: transformation from anxiety to empowerment, AI as scaffold, distinct tool utility, and future clinical application. Conclusions: These findings suggest that AI-assisted podcasting has the potential to significantly enhance critical thinking and digital literacy among nursing students; however, results should be interpreted with caution given the pre–post design, single-institution sample, and use of researcher-developed instruments.
Background: The appropriateness of the World Health Organization (WHO) body mass index (BMI) cut-off (≥25 kg/m2) for gestational diabetes mellitus (GDM) screening in Asian populations remains controversial due to the “Asian phenotype,” characterized by higher body fat percentage and visceral adiposity at lower BMI values. This systematic review evaluated the screening and prognostic performance of pre-pregnancy BMI thresholds (≥23, ≥24, ≥25 kg/m2) for predicting GDM in Asian women. Methods: A systematic review and meta-analysis were conducted following the JBI Manual for Evidence Synthesis and PRISMA-DTA guidelines. A comprehensive search was performed in PubMed, Scopus, Embase, CINAHL, Cochrane Library, and Google Scholar from January 2015 to August 2024. Studies reporting screening and prognostic performance of pre-pregnancy BMI for GDM prediction in Asian populations were assessed using the QUADAS-2 tool. Data were synthesized using MetaBayesDTA for univariate random-effects meta-analysis of sensitivity and specificity. A supplementary DerSimonian-Laird random-effects meta-analysis of odds ratios (ORs) was conducted to assess the prognostic association between BMI thresholds and GDM risk. Results: A total of 13 studies were included in the review, comprising a total of 427,159 Asian pregnant women. Most included studies were conducted in East Asian populations, predominantly Chinese, and findings may not generalize to South or Southeast Asian subgroups. For the Asian-standard threshold (≥23 kg/m2; n = 3 studies), pooled sensitivity was 0.47 (95% CrI 0.45–0.49) and specificity was 0.71 (95% CrI 0.56–0.83). For the intermediate threshold (≥24 kg/m2; n = 7 studies), sensitivity was 0.31 (95% CrI 0.25–0.37) and specificity 0.84 (95% CrI 0.80–0.88). For the WHO standard (≥25 kg/m2; n = 3 studies), sensitivity was 0.31 (95% CrI 0.11–0.61) and specificity 0.80 (95% CrI 0.45–0.95). Heterogeneity was extremely high for BMI ≥ 25 kg/m2 (I2 = 92% for sensitivity), substantially limiting the interpretability of pooled estimates for this threshold. Conclusions: Based on low-certainty evidence from three studies with very high heterogeneity, the WHO BMI criterion (≥25 kg/m2) appears to have clinically insufficient sensitivity for GDM detection in East Asian populations. The Asian-standard threshold (≥23 kg/m2) shows improved prediction (moderate-certainty evidence) but still misses approximately 53% of true positives. Supplementary OR meta-analysis confirms that all three thresholds are significantly associated with GDM risk (pooled ORs 1.80–2.38), though effect sizes are modest. BMI alone is insufficient for GDM screening and should be integrated into multifactorial risk assessment strategies. These findings apply primarily to East Asian populations and may not generalize to South or Southeast Asian subgroups.