Search for other papers by Huguette S Brink in
Google Scholar
PubMed
Search for other papers by Aart Jan van der Lely in
Google Scholar
PubMed
Search for other papers by Joke van der Linden in
Google Scholar
PubMed
GD pathogenesis. Combining biomarkers and risk factors into a predictive model may add to early prediction of GD, evoke effective prevention strategies and may ultimately reduce complications associated with GD. The aim of this review is to ( 1
Search for other papers by Hui Long in
Google Scholar
PubMed
Search for other papers by Yanhong Nie in
Google Scholar
PubMed
Search for other papers by Li Wang in
Google Scholar
PubMed
Search for other papers by Yong Lu in
Google Scholar
PubMed
Search for other papers by Yan Wang in
Google Scholar
PubMed
Search for other papers by Yijun Cai in
Google Scholar
PubMed
Search for other papers by Zhen Liu in
Google Scholar
PubMed
Search for other papers by Miaomiao Jia in
Google Scholar
PubMed
Search for other papers by Qifeng Lyu in
Google Scholar
PubMed
Search for other papers by Yanping Kuang in
Google Scholar
PubMed
Search for other papers by Qiang Sun in
Google Scholar
PubMed
FSH level ( 10 ). To date, AMH is widely used in prediction of ovarian response and clinical outcomes in humans ( 19 ) and other species, such as cow ( 20 ), sheep ( 21 ) and goats ( 22 ). However, the role of AMH in prediction of ovarian response in
Search for other papers by Ashley K Clift in
Google Scholar
PubMed
Search for other papers by Omar Faiz in
Google Scholar
PubMed
Search for other papers by Robert Goldin in
Google Scholar
PubMed
Search for other papers by John Martin in
Google Scholar
PubMed
Search for other papers by Harpreet Wasan in
Google Scholar
PubMed
Search for other papers by Marc-Olaf Liedke in
Google Scholar
PubMed
Search for other papers by Erik Schloericke in
Google Scholar
PubMed
Department of Pathophysiology and Endocrinology, Medical University of Silesia, Katowice, Poland
Search for other papers by Anna Malczewska in
Google Scholar
PubMed
Search for other papers by Guido Rindi in
Google Scholar
PubMed
Search for other papers by Mark Kidd in
Google Scholar
PubMed
Search for other papers by Irvin M Modlin in
Google Scholar
PubMed
Search for other papers by Andrea Frilling in
Google Scholar
PubMed
represent s.e.m. Data for all patients are included. The data marks in each plot from left to right represent high-, medium- and low-risk groups, respectively. Discussion NET patient prognosis prediction is limited by the paucity of
Neuroendocrine Unit, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
Search for other papers by Nidan Qiao in
Google Scholar
PubMed
). Machine learning may help to build a more reliable aided diagnostic tool for neuroradiologists and neuropathologists. Better prediction of clinical outcomes in these patients may provide better clinical decision support for either neuroendocrinologists or
Search for other papers by Thomas Reinehr in
Google Scholar
PubMed
Search for other papers by Martin Carlsson in
Google Scholar
PubMed
Search for other papers by Dionisios Chrysis in
Google Scholar
PubMed
Search for other papers by Cecilia Camacho-Hübner in
Google Scholar
PubMed
Introduction Prediction of adult height is a frequently requested procedure in pediatric endocrinology. The commonly used methods for adult height prediction are bone age determination of the wrist and fingers of the left hand by Greulich
Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia
Search for other papers by Tomaž Kocjan in
Google Scholar
PubMed
University Rehabilitation Institute, Ljubljana, Slovenia
FAMNIT, University of Primorska, Koper, Slovenia
Search for other papers by Gaj Vidmar in
Google Scholar
PubMed
Clinical Institute of Radiology, University Medical Centre Ljubljana, Ljubljana, Slovenia
Search for other papers by Peter Popović in
Google Scholar
PubMed
Clinical Institute of Radiology, University Medical Centre Ljubljana, Ljubljana, Slovenia
Search for other papers by Milenko Stanković in
Google Scholar
PubMed
prediction tools based on patient clinical and biochemical characteristics, which are obtained during the routine diagnostic work-up, might be employed to better select patients for AVS ( 13 ). These aids mainly rely on the well-known observation that LPA is
Search for other papers by Marieke S Velema in
Google Scholar
PubMed
Search for other papers by Evie J M Linssen in
Google Scholar
PubMed
Search for other papers by Ad R M M Hermus in
Google Scholar
PubMed
Search for other papers by Hans J M M Groenewoud in
Google Scholar
PubMed
Search for other papers by Gert-Jan van der Wilt in
Google Scholar
PubMed
Search for other papers by Antonius E van Herwaarden in
Google Scholar
PubMed
Department of Internal Medicine III, University Hospital Carl Gustav Carus at the TU Dresden, Dresden, Germany
Search for other papers by Jacques W M Lenders in
Google Scholar
PubMed
Search for other papers by Henri J L M Timmers in
Google Scholar
PubMed
Department of Internal Medicine III, University Hospital Carl Gustav Carus at the TU Dresden, Dresden, Germany
Search for other papers by Jaap Deinum in
Google Scholar
PubMed
development and validation of prediction models ( 5 ). Patients Our cohort consisted of adult patients who underwent an SLT for clinically suspected PA at the Radboud Adrenal Center, a tertiary center of expertise for patients with adrenal disorders in
Search for other papers by Olav Inge Håskjold in
Google Scholar
PubMed
Search for other papers by Henrik Stenestø Foshaug in
Google Scholar
PubMed
Search for other papers by Therese Benedikte Iversen in
Google Scholar
PubMed
Search for other papers by Helga Charlotte Kjøren in
Google Scholar
PubMed
UiT – The Arctic University of Norway, Institute of Clinical Medicine
Search for other papers by Vegard Heimly Brun in
Google Scholar
PubMed
carcinomas. All three anaplastic cancers were correctly identified. We saw no medullary thyroid cancers in our study period. Figure 2 Confusion matrix comparing ultrasound prediction with actual histopathological diagnosis. Prediction was based on non
Search for other papers by Tianze Ding in
Google Scholar
PubMed
Search for other papers by Peijie Liu in
Google Scholar
PubMed
Search for other papers by Jie Jia in
Google Scholar
PubMed
Search for other papers by Hui Wu in
Google Scholar
PubMed
Search for other papers by Jie Zhu in
Google Scholar
PubMed
Search for other papers by Kefeng Yang in
Google Scholar
PubMed
Introduction: Gestational diabetes mellitus (GDM) significantly affects pregnancy outcomes. Therefore, it is crucial to develop prediction models since they can guide timely interventions to reduce the incidence of GDM and its associated adverse effects.
Methods: A total of 554 pregnant women were selected and their sociodemographic characteristics, clinical data and dietary data were collected. Dietary data was investigated by a validated semi-quantitative food frequency questionnaire (FFQ). We applied random forest mean decrease impurity for feature selection and the models are built using Logistic Regression, XGBoost, and LightGBM algorithms. The prediction performance of different models was compared by Accuracy, Sensitivity, Specificity, Area Under Curve (AUC) and Hosmer-Lemeshow test.
Results: Blood glucose, age, pre-pregnancy body mass index (BMI), triglycerides and high-density lipoprotein cholesterol (HDL) were the top five features according to the feature selection. Among the three algorithms, XGBoost performed best with an AUC of 0.788, LightGBM came second (AUC = 0.749), and Logistic Regression performed the worst (AUC = 0.712). In addition, XGBoost and LightGBM both achieved a fairly good performance when dietary information was included, surpassing their performance on the non-dietary dataset (0.788 vs. 0.718 in XGBoost; 0.749 vs. 0.726 in LightGBM).
Conclusion: XGBoost and LightGBM algorithms outperform Logistic Regression in predicting GDM among the Chinese pregnant women. In addition, dietary data may have a positive effect on improving model performance, which deserves more in-depth investigation with larger sample size.
Search for other papers by Yang Lv in
Google Scholar
PubMed
Search for other papers by Xu Han in
Google Scholar
PubMed
Search for other papers by Chunyan Zhang in
Google Scholar
PubMed
Search for other papers by Yuan Fang in
Google Scholar
PubMed
Search for other papers by Ning Pu in
Google Scholar
PubMed
Search for other papers by Yuan Ji in
Google Scholar
PubMed
Search for other papers by Dansong Wang in
Google Scholar
PubMed
Search for other papers by Xu Xuefeng in
Google Scholar
PubMed
Search for other papers by Wenhui Lou in
Google Scholar
PubMed
surgical/needled specimen can give rise to the prognosis prediction and nonoperative management guidance to some extents, but this is usually based on a fixed small biopsy sample that may not reflect the heterogeneity present in advanced tumors ( 2