ABSTRACT
BACKGROUND: The complex nature and heterogeneity involving pituitary surgery results have increased interest in machine learning (ML) applications for prediction of outcomes over the last decade. This study aims to systematically review the characteristics of ML models involving pituitary surgery outcome prediction and assess their reporting quality. METHODS: We searched the PubMed, Scopus, and Web of Knowledge databases for publications on the use of ML to predict pituitary surgery outcomes. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to assess report quality. Our search strategy was based on the terms "artificial intelligence", "machine learning", and "pituitary". RESULTS: 20 studies were included in this review. The principal models reported in each article were post-surgical endocrine outcomes (n = 10), tumor management (n = 3), and intra- and postoperative complications (n = 7). Overall, the included studies adhered to a median of 65% (IQR = 60-72%) of TRIPOD criteria, ranging from 43% to 83%. The median reported AUC was 0.84 (IQR = 0.80-0.91). The most popular algorithms were support vector machine (n = 5) and random forest (n = 5). Only two studies reported external validation and adherence to any reporting guideline. Calibration methods were not reported in 15 studies. No model achieved the phase of actual clinical applicability. CONCLUSION: Applications of ML in the prediction of pituitary outcomes are still nascent, as evidenced by the lack of any model validated for clinical practice. Although studies have demonstrated promising results, greater transparency in model development and reporting is needed to enable their use in clinical practice. Further adherence to reporting guidelines can help increase AI's real-world utility and improve clinical practice.
ABSTRACT
INTRODUCTION: The present study aims to investigate whether mothers from Culturally and Linguistically Diverse (CALD) backgrounds present with higher levels of demoralization in comparison with their non-minority counterparts, and to explore potential correlations between demoralization and anxiety as well as depression in the same sample of mothers. METHODS: Women admitted to a public tertiary care teaching hospital were invited to participate in the study within 24-48 hours following delivery. The study compared women who did not regard English as their main spoken language to native English-speaking women. Women were asked to complete the demographic Kissane Demoralization Scale (KDS) and Being a Mother Scale (BaM-13) questionnaires. Participants were contacted by phone, 6 to 8 weeks after they had completed the KDS and the BaM-13 questionnaires, to complete an Edinburgh Postnatal Depression Scale (EPDS) and State Trait Anxiety Scale (STAI) questionnaires. RESULTS: Mothers of CALD background presented with significantly higher scores on the KDS (p<0.001), STAI (p<0.001) and EPDS (p<0.001) scales in comparison with their non-CALD counterparts. Furthermore, when mothers were reassessed after 6 to 8 weeks, higher KDS scores in the postnatal period predicted significantly higher anxiety and depression scores, according to STAI (p<0.001) and the EPDS (p<0.001), respectively. CONCLUSIONS: The results of this study reveal that, mothers of CALD background manifest higher levels of demoralization as well as anxiety and depression in the postpartum period when compared with their non-CALD counterparts.
