Devasahay Sylvester Rohan, Karpagam Sylvia, Ma Nang Laik
Data Science, School of information Systems, Singapore Management University, Singapore.
Information Technology specialized in Analytics, Bangalore, India.
Mhealth. 2017 Apr 17;3:12. doi: 10.21037/mhealth.2017.03.03. eCollection 2017.
There is growing attention over the last few years about non-attendance in hospitals and its clinical and economic consequences. There have been several studies documenting the various aspects of non-attendance in hospitals. Project Predicting Appoint Misses (PAM) was started with the intention of being able to predict the type of patients that would not come for appointments after making bookings.
Historic hospital appointment data merged with "distance from hospital" variable was used to run Logistic Regression, Support Vector Machine and Recursive Partitioning to decide the contributing variables to missed appointments.
Variables that are "class", "time", "demographics" related have an effect on the target variable, however, prediction models may not perform effectively due to very subtle influence on the target variable. Previously assumed major contributors like "age", "distance" did not have a major effect on the target variable.
With the given data it will be very difficult to make any moderate/strong prediction of the Appointment misses. That being said with the help of the cut off we are able to capture all of the "appointment misses" in addition to also capturing the actualized appointments.
在过去几年中，医院患者爽约及其临床和经济后果越来越受到关注。已有多项研究记录了医院患者爽约的各个方面。开展“预测预约失约项目”（PAM）的目的是能够预测预约后不来就诊的患者类型。
将历史医院预约数据与“距医院距离”变量合并，用于进行逻辑回归、支持向量机和递归划分，以确定导致预约失约的相关变量。
与“类别”“时间”“人口统计学”相关的变量对目标变量有影响，然而，由于对目标变量的影响非常细微，预测模型可能无法有效发挥作用。之前假定的主要影响因素如“年龄”“距离”对目标变量没有重大影响。
根据给定的数据，很难对预约失约进行任何中度/强度的预测。话虽如此，借助临界值，我们除了能够捕捉到实际发生的预约外，还能够捕捉到所有的“预约失约”情况。
