Health Services Optimization, Improvement, and Management: Worldwide Experiences

Background: Artificial intelligence (AI) and machine learning (ML) have been reshaping maternal, fetal, neonatal, and reproductive healthcare by enhancing risk prediction, diagnostic accuracy, and operational efficiency across the perinatal continuum. However, no comprehensive synthesis has yet been published. Objective: To conduct a scoping review of reviews of AI/ML applications spanning reproductive, prenatal, postpartum, neonatal, and early child-development care. Methods: We searched PubMed, Embase, the Cochrane Library, Web of Science, and Scopus through April 2025. Two reviewers independently screened records, extracted data, and assessed methodological quality using AMSTAR 2 for systematic reviews, ROBIS for bias assessment, SANRA for narrative reviews, and JBI guidance for scoping reviews. Results: Thirty-nine reviews met our inclusion criteria. In preconception and fertility treatment, convolutional neural network-based platforms can identify viable embryos and key sperm parameters with over 90 percent accuracy, and machine-learning models can personalize follicle-stimulating hormone regimens to boost mature oocyte yield while reducing overall medication use. Digital sexual-health chatbots have enhanced patient education, pre-exposure prophylaxis adherence, and safer sexual behaviors, although data-privacy safeguards and bias mitigation remain priorities. During pregnancy, advanced deep-learning models can segment fetal anatomy on ultrasound images with more than 90 percent overlap compared to expert annotations and can detect anomalies with sensitivity exceeding 93 percent. Predictive biometric tools can estimate gestational age within one week with accuracy and fetal weight within approximately 190 g. In the postpartum period, AI-driven decision-support systems and conversational agents can facilitate early screening for depression and can guide follow-up care. Wearable sensors enable remote monitoring of maternal blood pressure and heart rate to support timely clinical intervention. Within neonatal care, the Heart Rate Observation (HeRO) system has reduced mortality among very low-birth-weight infants by roughly 20 percent, and additional AI models can predict neonatal sepsis, retinopathy of prematurity, and necrotizing enterocolitis with area-under-the-curve values above 0.80. From an operational standpoint, automated ultrasound workflows deliver biometric measurements at about 14 milliseconds per frame, and dynamic scheduling in IVF laboratories lowers staff workload and per-cycle costs. Home-monitoring platforms for pregnant women are associated with 7–11 percent reductions in maternal mortality and preeclampsia incidence. Despite these advances, most evidence derives from retrospective, single-center studies with limited external validation. Low-resource settings, especially in Sub-Saharan Africa, remain under-represented, and few AI solutions are fully embedded in electronic health records. Conclusions: AI holds transformative promise for perinatal care but will require prospective multicenter validation, equity-centered design, robust governance, transparent fairness audits, and seamless electronic health record integration to translate these innovations into routine practice and improve maternal and neonatal outcomes. Full article

Background/Objectives: Generating real-world data on the efficacy of multidisciplinary care in cardiometabolic risk management is essential to ensure that guidelines are both applicable and effective, especially in public healthcare settings, where organizational structures may impede healthcare professionals’ agility. This study aimed to generate data on patient follow-up and cardiometabolic risk management during the early years of a public university family medicine group in Québec (Canada) that provides multidisciplinary care to adults with cardiometabolic conditions, in order to evaluate the implementation and effectiveness of its care model. Methods: This was a retrospective longitudinal study. Patients treated at the clinic from 31 January 2020 (clinic opening) to 8 May 2024 (n = 96) were invited to consent to the use of their medical data for research. Results: A total of 52 patients consented and were included in the study. Upon entry at the clinic, >90% of patients had anthropometry and blood pressure (BP) measured, but plasma glucose and lipids were assessed among 50% and 79% of patients, respectively. A total of 36 patients completed the personalized multidisciplinary care program. No evidence of associations between the total number of appointments or appointments with the registered dietitian specifically with changes in BMI, waist circumference, and BP was found. However, each pharmaceutical intervention was associated with a −0.51 cm (95%CI: −1.03, 0.02; p = 0.06) change in waist circumference and a −1.49 mm Hg (95%CI: −2.56, −0.43, p = 0.01) change in diastolic BP. Conclusions: These data highlight the challenges of implementing a research-oriented clinic within Québec’s public healthcare system. Full article

Background and Objectives: Healthcare payment systems face challenges such as fraud and overbilling, which often require costly and resource-intensive detection tools. In response, the utility of simple statistical tests was explored in this study as a practical alternative for identifying irregularities in dermatology service payments within the Health Insurance Institute of Slovenia (HIIS). Materials and Methods: Ten-year-old anonymized billing data from 30 dermatology providers in Slovenia (with a population of 2 million) were analyzed to evaluate the effectiveness of the proposed methodology while aiming to avoid reputational harm to current providers. The dataset from 2014 included variables such as the “number of services charged”, “total number of points charged” (under Slovenia’s point-based tariff system at the time), “number of points per examination”, “average examination values (EUR)”, “number of first examinations”, and “total number of first/follow-up examinations”. Data credibility was assessed using Benford’s Law (for calculating χ² values and testing null hypothesis rejection at the 95% level), and Grubbs’ test, Hampel’s test, and T-test were used to identify outliers. Results: An analysis using Benford’s Law revealed significant deviations for the “number of services charged” (p < 0.005), “total number of points charged” (p < 0.01), “number of points per examination” (p < 0.0005), and “average examination values (EUR)” (p < 0.005), suggesting anomalies. Conversely, data on the numbers of “first” (p < 0.7) and “total first/follow-up examinations” (p < 0.3) were found to align with Benford’s Law, indicating authenticity. Outlier detection consistently identified two institutions with unusually high values for points per examination and average examination monetary value. Conclusions: Simple statistical tests can effectively identify potential irregularities in healthcare payment data, providing a cost-effective screening method for further investigation. Identifying outlier providers highlights areas needing detailed scrutiny to understand anomaly causes. Full article