Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Stud Health Technol Inform. 2022 Jan 14;289:65-68. doi: 10.3233/SHTI210860.
The goal of this study was to build a machine learning model for early prostate cancer prediction based on healthcare utilization patterns. We examined the frequency and pattern changes of healthcare utilization in 2916 prostate cancer patients 3 years prior to their prostate cancer diagnoses and explored several supervised machine learning techniques to predict possible prostate cancer diagnosis. Analysis of patients' medical activities between 1 year and 2 years prior to their prostate cancer diagnoses using XGBoost model provided the best prediction accuracy with high F1 score (0.9) and AUC score (0.73). These pilot results indicated that application of machine learning to healthcare utilization patterns may result in early identification of prostate cancer diagnosis.
本研究旨在基于医疗保健利用模式构建一种用于早期前列腺癌预测的机器学习模型。我们研究了 2916 例前列腺癌患者在确诊前 3 年的医疗保健利用频率和模式变化，并探索了几种监督机器学习技术来预测可能的前列腺癌诊断。使用 XGBoost 模型分析患者在确诊前 1 年至 2 年的医疗活动，可提供最佳预测准确性，具有较高的 F1 分数（0.9）和 AUC 分数（0.73）。这些初步结果表明，将机器学习应用于医疗保健利用模式可能有助于早期识别前列腺癌诊断。
