Objective: Compare the reporting of 16 mental health symptoms (MHS) through AI-based virtual triage (VT) in three European countries/language user groups, including Ukrainians, Poles, and Italians, before and following the onset of the Russian invasion of Ukraine in February 2022.
Methods: Frequencies of 16 MHS reported through VT were compared for 12 months prior to and after the onset of the 2022 Russia-Ukraine conflict (i.e., February 24, 2021 to February 23, 2022 pre-war and from February 24, 2022 through February 23, 2023 post-war, respectively). Italian patient-users served as a quasi-control group relative to Ukrainian and Polish language users, given the lower perception of national risk from Russian military aggression.
Results: In 93,877 VT encounters, at least one MHS was reported. MHS reporting among Ukrainians and Poles increased 11.6% and 3.7%, respectively, after the first onset of the conflict (p<.05). Italian MHS reporting decreased 1.6%. Among Ukrainians, MHS reporting increased for 10 of 16 symptoms, the largest being suicidal thoughts/intent (158.7%), sleep disorder (45.7%), insomnia (32.9%), and irritability (20.7%) (all p<.05). Among Poles, reporting increased for 10 symptoms, including sleep disorder (52.2%), fear of dying (27.9%), insomnia (25.3%), and suicidal thoughts/intent (13.6%) (all p<.05).
Conclusions: Individuals in nations more directly exposed to and potentially impacted by the war reported higher levels of MHS to AI-based automated VT. Virtual triage offers a new vehicle for enhancing detection of MHS, and for potentially accelerating referral to in-person or virtual/telemedical mental healthcare services among displaced populations needing care in conflict areas.

Background: It is anticipated that closing the quality gap through provision of effective antenatal, intrapartum and postnatal care for mothers and newborns in facilities will reduce morbidity and mortality. Mothers’ and health care providers’ experiences play a vital role in achieving quality care during the perinatal periods.Purpose:To assess the health care providers’ (HCPs) and clients’ experiences on quality of perinatal care at three district hospitals in Bunyoro region, Western Uganda.
Methods: A convergent parallel mixed methods study design was utilized to explore experiences of 1) mothers as they sought antenatal, intrapartum, and postnatal care; and 2) care providers. Consecutive sampling was used to select 872 postnatal women at discharge, while purposive sampling was employed to select 54 care providers to participate in the study using structured questionnaires and interview guides. Quantitative data was analyzed descriptively, and qualitative data analyzed using inductive thematic analysis.
Results: Most women rated their interactions with the HCPs as trustworthy (80.5%), respectful (74.5%), and devoted (77.4%). All women were examined during antenatal, and 94% examined during childbirth. Most received medications during antenatal (99.5%) and childbirth (82.6%). Medical histories and care were recorded for 94.4% of women using standardized tools (98.2%). However, only 26.4% felt fully supported in transitioning care, while 37.4% faced difficulties. Additionally, over half of the HCPs were dissatisfied with the available physical infrastructure (75.9%) and resources (61.1%). Three themes emerged: good care provision, receiving information about care, and provider and client satisfaction.
Conclusions: Women had a positive experience contrary to that of the health care providers, which was influenced by a lack of an enabling environment. The limited environment also impacted women’s ability to transition in care. The presence of an enabling environment may enhance the quality of care provided to pregnant women.

Objective: To assess whether automated AI-based virtual triage and care referral (VTCR) improves appropriate acuity-based care by aligning patient healthcare seeking intent and potential care seeking behavior with triage output in a leading multinational healthcare plan based in the Middle East.
Methods: Data were derived from an AI-based symptom checker application and analyzed the pre- and post-VTCR care intentions of eligible health plan patients (N = 4,985) to examine how VTCR influenced potential care seeking behavior across five levels of care acuity. Pre- and post-triage care intentions were compared, and changes as a result of triage, including acuity level escalation and de-escalation, were assessed for statistical significance using Z-tests.
Results: Overall alignment with VTCR clinical guidance was 37.6% following virtual triage, improved from a 22.2% level of acuity alignment prior to VTCR. VTCR significantly decreased the number of patients with uncertain healthcare intention (62.9% or - 22.1 PP; p =.05), the largest group of whom decided to engage self-care after VTCR (13.9% of all patients). The largest changes in care intent occurred where patients altered their care plan to engage self-care (an increase of 128.2% or +18.8 PP; p =.05), reducing avoidable use of higher acuity services. Post-triage intent to access emergency care increased 138.8% (+ 1.9 PP; p =.05). The largest de-escalation of care acuity was observed among patients who before VTCR intended to engage a non-urgent outpatient consultation, but instead chose self-care after VTCR (9.3% of patients; p =.05).
Conclusions: Virtual triage reduced potential clinically inappropriate utilization of both higher and lower acuity care services by patients, and post-VTCR care seeking was better aligned with patients’ actual clinical needs. VTCR improved early detection of and care referral for emergent conditions, and simultaneously reduced inappropriate ED and outpatient care utilization for symptoms that could be managed by patients through self-care. VTCR was able to reduce care acuity-level misalignment and potentially unnecessary and avoidable healthcare utilization.

Background: This study seeks to provide insights into the factors that influence hospital performance during health crises to propose strategies for improving operational efficiency in future public health emergencies. It measures efficiency in national hospitals in Japan using a stochastic distance function approach on data from before and after the COVID-19 pandemic.
Methods: We collected data for financial years 2017, 2018, 2020, and 2021 (before and after the COVID-19 pandemic) related to the National Hospital Organization. The number of physicians, nurses, and others (including co-medical staff); the sum of costs; and the number of beds were used as input variables. The total numbers of inpatients and outpatients per year were used as output variables. The dataset comprised 140 national hospitals and spanned four years, resulting in 280 hospital observations pre- and post-COVID-19.
Results: The average number of inpatients at each hospital during the observation period was 109,141.5 (standard deviation [SD] = 37077.7), and the average number of outpatients was 84,324.5 (SD = 75050.4). The average numbers of physicians, nurses, others, beds, and costs were 46.9 (SD = 41.5), 62.6 (SD = 38.1), 278.7 (SD = 143.9), 363.5 (SD = 124.2), and 249,409,614.3 (SD = 2366015803.0), respectively. In the pre- and post-pandemic periods, the outpatient/inpatient coefficients were significant and positive, suggesting that the progression of COVID-19 led to a decrease in hospital efficiency.
Conclusions: While this study cannot definitively explain the efficiency decline, it provides important evidence indicating that the COVID-19 pandemic adversely affected hospital operations and revenue in Japan.