Paper Number
1434
Paper Type
Complete Research Paper
Abstract
Predictive healthcare in the case of pancreatic neuroendocrine tumors (PNETs) is a crucial operation as treatment challenges arise due to the heterogeneity of the disease. Surgical approaches vary based on aggressiveness, ranging from resection for milder cases to extensive removal for aggressive PNETs. Thus, machine learning (ML) models are crucial for precise prediction and categorizing PNETs for enhanced outcome forecasting. This systematic review sheds light on the practices of ML approaches within a comparative meta-analysis and a quality assessment employing the standardized IJMEDI checklist. The results show that ML studies within the field of predictive healthcare, despite their potential, face challenges like inadequate data preprocessing, unclear model architecture, and limited clinical applicability.
Recommended Citation
Heinrich, Kai and Keshavarzi, Armin, "Are Our Predictions Healthy? A Comparative Meta-Analysis of Machine Learning Studies in Predictive Healthcare" (2024). ECIS 2024 Proceedings. 2.
https://aisel.aisnet.org/ecis2024/track18_healthit/track18_healthit/2
Are Our Predictions Healthy? A Comparative Meta-Analysis of Machine Learning Studies in Predictive Healthcare
Predictive healthcare in the case of pancreatic neuroendocrine tumors (PNETs) is a crucial operation as treatment challenges arise due to the heterogeneity of the disease. Surgical approaches vary based on aggressiveness, ranging from resection for milder cases to extensive removal for aggressive PNETs. Thus, machine learning (ML) models are crucial for precise prediction and categorizing PNETs for enhanced outcome forecasting. This systematic review sheds light on the practices of ML approaches within a comparative meta-analysis and a quality assessment employing the standardized IJMEDI checklist. The results show that ML studies within the field of predictive healthcare, despite their potential, face challenges like inadequate data preprocessing, unclear model architecture, and limited clinical applicability.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.