AI Article Synopsis
- This study compared the effectiveness of modern machine learning models and traditional statistical models in predicting overall mortality for patients with type 2 diabetes.
- Over 22,500 participants from the UK Biobank were analyzed, revealing that machine learning techniques significantly outperformed the classic Cox model in predicting mortality rates.
- An online prediction tool was created using the best-performing DeepHit model, showcasing the promise of machine learning in enhancing personalized healthcare for diabetes patients.
Article Abstract
Aims: This study aims to compare the performance of contemporary machine learning models with statistical models in predicting all-cause mortality in patients with type 2 diabetes mellitus and to develop a user-friendly mortality risk prediction tool.
Methods: A prospective cohort study was conducted including 22,579 people with diabetes from the UK Biobank. Models evaluated include Cox proportional hazards, random survival forests (RSF), gradient boosting (GB) survival, DeepSurv, and DeepHit.
Results: Over a median follow-up period of 9 years, 2,665 patients died. Machine learning models outperformed the Cox model in the validation dataset, with C-index values of 0.72-0.73 vs. 0.71 for Cox (p < 0.01). Deep learning models, particularly DeepHit, demonstrated superior calibration and achieved lower Brier scores (0.09 vs. 0.10 for Cox, p < 0.05). An online prediction tool based on the DeepHit was developed for patient care: http://123.57.42.89:6006/.
Conclusions: Machine learning models performed better than statistical models, highlighting the potential of machine learning techniques for predicting all-cause mortality risk and facilitating personalized healthcare management for individuals with diabetes.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.dsx.2024.103135 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Background: Coronary heart disease (CHD) and depression frequently co-occur, significantly impacting patient outcomes. However, comprehensive health status assessment tools for this complex population are lacking. This study aimed to develop and validate an explainable machine learning model to evaluate overall health status in patients with comorbid CHD and depression.
View Article and Find Full Text PDFPinpointing the timing of prenatal stress associated with infant biobehavioral reactivity.
Psychoneuroendocrinology
January 2025
Department of Psychiatry, University of Michigan - Michigan Medicine, USA.
Prenatal stress has a well-established link to negative biobehavioral outcomes in young children, particularly for girls, but the specific timing during gestation of these associations remains unknown. In the current study, we examined differential effects of timing of prenatal stress on two infant biobehavioral outcomes [i.e.
View Article and Find Full Text PDFEmerging Technologies for Multiphoton Writing and Reading of Polymeric Architectures for Biomedical Applications.
Annu Rev Biomed Eng
January 2025
1School of Engineering, Brown University, Providence, Rhode Island, USA;
The rise in popularity of two-photon polymerization (TPP) as an additive manufacturing technique has impacted many areas of science and engineering, particularly those related to biomedical applications. Compared with other fabrication methods used for biomedical applications, TPP offers 3D, nanometer-scale fabrication dexterity (free-form). Moreover, the existence of turnkey commercial systems has increased accessibility.
View Article and Find Full Text PDFDesigner Organs: Ethical Genetic Modifications in the Era of Machine Perfusion.
Annu Rev Biomed Eng
January 2025
1Center for Engineering for Medicine and Surgery, Department of Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA;
Gene therapy is a rapidly developing field, finally yielding clinical benefits. Genetic engineering of organs for transplantation may soon be an option, thanks to convergence with another breakthrough technology, ex vivo machine perfusion (EVMP). EVMP allows access to the functioning organ for genetic manipulation prior to transplant.
View Article and Find Full Text PDFUser and Developer Views on Using AI Technologies to Facilitate the Early Detection of Skin Cancers in Primary Care Settings: Qualitative Semistructured Interview Study.
JMIR Cancer
January 2025
Wolfson Institute of Population Health, Queen Mary University of London, London, United Kingdom.
Background: Skin cancers, including melanoma and keratinocyte cancers, are among the most common cancers worldwide, and their incidence is rising in most populations. Earlier detection of skin cancer leads to better outcomes for patients. Artificial intelligence (AI) technologies have been applied to skin cancer diagnosis, but many technologies lack clinical evidence and/or the appropriate regulatory approvals.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!