運用機器學習方法檢測小兒發展遲緩病症

Abstract

研究目的:對臨床治療師而言，準確鑑別可能出現發展遲緩（DD）的兒童始終是一項挑戰。近年研究指出，若兒童能及早接受介入治療，其臨床預後顯著優於未接受介入者。本研究旨在探討兒童接受三類治療（物理治療、職能治療與語言治療）的頻率，是否可作為檢測其是否罹患發展遲緩的依據。此方法的核心價值在於，相關特徵取得成本極低，若能建立有效的預測模型，將可用於初步篩檢，在進行昂貴且複雜的診斷程序之前，先行辨識可能有 DD 風險的兒童。 研究方法:本研究使用台灣某醫院於 2012 至 2016 年間蒐集之臨床資料，共涵蓋 2,552 位門診個案（共 34,862 筆就診紀錄，平均年齡 72.34 月）。基於該資料集，本研究分別建立三種機器學習預測模型：深度神經網路（Deep Neural Network, DNN）、支援向量機（Support Vector Machine, SVM）以及決策樹（Decision Tree, DT），以評估所提出方法的效能。 研究結果:實驗結果顯示，就 F1 分數（靈敏度與陽性預測值的調和平均數）而言，當需要維持高靈敏度時，DT 模型的表現優於 DNN 與 SVM 模型。具體而言，本研究所建立的 DT 模型達成靈敏度 0.902 與陽性預測值 0.723 的表現。 研究結論:本研究結果顯示，兒童接受治療的頻率蘊含重要訊息，能有效應用於發展遲緩的預測。由於此類特徵可在不增加額外成本的情況下獲取，且實驗結果展現良好效能，因此可合理推測，依此建立之預測模型具備高度臨床應用潛力，並有望顯著改善發展遲緩兒童的治療成效。

Objective: Accurate identification of children who will develop delay (DD) is challenging for ther¬apists because recent studies have reported that children who underwent early inter¬vention achieved more favorable outcomes than those who did not. In this study, we have investigated how the frequencies of three types of therapy, namely the physical therapy, the occupational therapy, and the speech therapy, received by a child can be exploited to predict whether the child suffers from DD or not. The effectiveness of the proposed approach is of high interest as these features can be obtained with essen¬tially no cost and therefore a prediction model built accordingly can be employed to screen the subjects who may develop DD before advanced and costly diagnoses are carried out. Methods: This study has been conducted based on a data set comprising the records of 2,552 outpatients (N = 34,862 visits, mean age = 72.34 months) collected at a hospital in Tai¬wan from 2012 to 2016. We then built 3 types of machine learning based prediction models, namely the deep neural network models (DNN), the support vector machine (SVM) models, and the decision tree (DT) models, to evaluate the effectiveness of the proposed approach. Results: Experimental results reveal that in terms of the F1 score, which is the harmonic mean of the sensitivity and the positive predictive value, the DT models outperformed the DNN models and the SVM models, if a high level of sensitivity is desired. In particular, the DT model developed in this study delivered the sensitivity at 0.902 and the positive predictive value at 0.723. Conclusions: What has been learned from this study is that the frequencies of the therapies that a child has received provide valuable information for predicting whether the child suffers from DD. Due to the performance observed in the experiments and the fact that these features can be obtained essentially without any cost, it is conceivable that the prediction models built accordingly can be wide exploited in clinical practices and significantly improve the treatment outcomes of the children who develop DD.