RESULTS: The oocyte AI model demonstrated area under the curve (AUC) up to 0.65 on two blind test datasets. High sensitivity for predicting competent oocytes (83-88%) was offset by lower specificity (26-36%). Exclusion of confounding biological variables (male factor infertility and maternal age ≥35 years) improved AUC up to 14%, primarily due to increased specificity. AI score correlated with size of the zona pellucida and perivitelline space, and ooplasm appearance. AI score also correlated with blastocyst expansion grade and morphological quality. The sum of AI scores from oocytes in group culture images predicted the formation of two or more usable blastocysts (AUC 0.77).
CONCLUSION: An AI model to evaluate oocyte competence was developed using federated learning, representing an essential step in protecting patient data. The AI model was significantly predictive of oocyte competence, as defined by usable blastocyst formation, which is a critical factor for IVF success. Potential clinical utility ranges from selective oocyte fertilization to guiding treatment decisions regarding additional rounds of oocyte retrieval.
DESIGN: In total, 10,677 oocyte images with associated metadata were collected prospectively by eight IVF clinics across six countries. AI training used federated learning, where data were retained on regional servers to comply with data privacy laws. The final AI model required a single image as input to evaluate oocyte competence, which was defined by the formation of a usable blastocyst (≥expansion grade 3 by day 5 or 6 post ICSI).
DESIGN/METHODOLOGY/APPROACH: Using healthcare as a case, a stratified random sample comprising 600 patients from 40 hospitals across eight metropolitan cities in an emerging economy was acquired and analyzed using co-variance-based structural equation modeling (CB-SEM).
FINDINGS: Customers' co-creation experience has a positive impact on their co-creation self-efficacy, co-creation engagement, and value co-creation behavior. While co-creation self-efficacy and engagement have no direct influence on value co-creation behavior, they do serve as mediators between co-creation experience and value co-creation behavior, suggesting that when customers are provided with a co-creation experience, it enhances their co-creation self-efficacy and engagement, ultimately fostering value co-creation behavior.
ORIGINALITY/VALUE: A theory of customer value co-creation behavior is established.
PURPOSE: To examine the accuracy of AI-based radiomics in diagnosis, prognosis assessment and predicting the diagnostic value of radiomics for pelvic LN metastasis in cervical cancer patients.
MATERIAL AND METHODS: The study included 118 female patients with 660 LNs and 118 merged LNs. Four imaging histology models-decision tree, random forest, logistic regression, and support vector machine (SVM)-were created in this study. The imaging histology features were extracted from both the independent and merged LN groups. The AUC values for the test sets and the training sets of the four imaging histology models were compared for the independent LN group and the merged LN group. The DeLong test was used to compare the models.
RESULT: The imaging histology prediction model developed in the merged LN group outperformed the independent LN group in terms of test set AUC (0.668 vs. 0.535 for decision tree, 0.841 vs. 0.627 for logistic regression, 0.785 vs. 0.637 for random forest, 0.85 vs. 0.648 for SVM) and accuracy (0.754 vs. 0.676 for decision tree, 0.780 vs. 0.671 for random forest, 0.848 vs. 0.685 for logistic regression, 0.822 vs. 0.657 for SVM).
CONCLUSION: The constructed SVM imaging histology model for the merged LN group might be advantageous in predicting pelvic LN metastasis in cervical cancer.
OBJECTIVE: The aim of this study therefore is to determine if improving sleep quality could improve executive functions in medical students with poor sleep quality by comparing cognitive behavioural therapy for insomnia (CBT-I) with sleep hygiene education (SHE) in a randomized controlled trial (RCT).
METHODS: A parallel group, RCT with a target sample of 120 medical students recruited from government-based medical universities in Malaysia. Eligible participants will be randomized to internet group CBT-I or internet group SHE in a 1:1 ratio. Assessments will be performed at baseline, post-intervention, 1 month, 3-months, and 6-months. The primary outcome is between-group differences in sleep quality and executive function post-baseline. The secondary outcomes include pre-sleep worry, attitude about sleep, sleep hygiene and sleep parameters.
RESULTS: This study received approval from the Research Ethics Committee in Universiti Putra Malaysia (JKEUPM-2023-1446) and Universiti Kebangsaan Malaysia (JEP-2024-669). The clinical trial was also registered in Australian New Zealand Clinical Trial Registry (ACTRN1264000243516). As of June 2024, the recruitment process is ongoing and a total of 48 and 49 students have been enrolled from the universities into the CBT-I and ISHE groups, respectively. All the participants provided signed and informed consent to participate in the study. Data collection has been completed for the baseline (pre-treatment assessment), and follow-up assessments for T1 and T2 for all the participants in both groups, while T3 and T4 assessments will be completed by July 2025. Data analysis will be performed by August 2025 and the research will be completed by December 2025.
CONCLUSIONS: This study is the first attempt to design a CBT intervention to ameliorate poor sleep quality and its related negative effects among medical students. This research is also the first large-scale exploring the relationship between health status and CBT-mediated sleep improvement among medical students.
TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry ACTRN12624000243516; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=387030.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/59288.
METHODS: From July 2020 to August 2021, we surveyed 16 461 adults across 29 countries who self-reported changes in 18 lifestyle factors and 13 health outcomes due to the pandemic. Three networks were generated by network analysis for each country: lifestyle, health outcome, and bridge networks. We identified the variables with the highest bridge expected influence as central or bridge variables. Network validation included nonparametric and case-dropping subset bootstrapping, and centrality difference tests confirmed that the central or bridge variables had significantly higher expected influence than other variables within the same network.
RESULTS: Among 87 networks, 75 were validated with correlation-stability coefficients above 0.25. Nine central lifestyle types were identified in 28 countries: cooking at home (in 11 countries), food types in daily meals (in one country), less smoking tobacco (in two countries), less alcohol consumption (in two countries), less duration of sitting (in three countries), less consumption of snacks (in five countries), less sugary drinks (in five countries), having a meal at home (in two countries), taking alternative medicine or natural health products (in one country). Six central health outcomes were noted among 28 countries: social support received (in three countries), physical health (in one country), sleep quality (in four countries), quality of life (in seven countries), less mental burden (in three countries), less emotional distress (in 13 countries). Three bridge lifestyles were identified in 19 countries: food types in daily meals (in one country), cooking at home (in one country), overall amount of exercise (in 17 countries). The centrality difference test showed the central and bridge variables had significantly higher centrality indices than others in their networks (P