A Multiview Model for Detecting the Inappropriate Use of Prescription Medication: Machine Learning Approach

Zhuo, Lin; Cheng, Yinchu; Liu, Shaoqin; Yu, Yang; Tang, Shuang; Jian-cun, Zhen; Zhao, Junfeng; Zhan, Siyan

doi:10.2196/16312

Cited by 4 publications

(1 citation statement)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is an increasing trend to study how machine learning (ML) tools can be used to augment medical professionals' decisions concerning diagnosis, treatment safety, and quality of patient care [2,3]. Several pharmaceutical studies [4][5][6][7] have applied ML to find anomalous prescriptions but not tailored to RT. In RT, several studies [8][9][10][11] have used ML to look at the treatment parameters to detect errors in treatment plans, but not focus on prescription error detection.…”

Section: Introductionmentioning

confidence: 99%

A novel data-driven algorithm to predict anomalous prescription based on patient's feature set

Li¹,

Wright²,

Hales³

et al. 2021

Preprint

View full text Add to dashboard Cite

Appropriate dosing of radiation is crucial to patient safety in radiotherapy. Current quality assurance depends heavily on a peer-review process, where the physician's peer review on each patient's treatment plan including dose and fractionation. However, such a process is manual and laborious. Physicians may not identify errors due to time constraints and case load. We designed a novel prescription anomaly detection algorithm that utilizes historical data from the past to predict anomalous cases. Such a tool can serve as an electronic peer who will assist the peer-review process providing extra safety to the patients. In our primary model, we created two dissimilarity metrics, R and F . R defining how far a new patient's prescription is from historical prescriptions. F represents how far away a patient's feature set is from that of the group with an identical or similar prescription. We flag prescription if either metric is greater than specific optimized cut-off values.We used thoracic cancer patients (n = 2356) as an example and extracted seven features. Here, we report our testing f1 score, which is between 73%-94% for different treatment technique groups.We also independently validate our results by conducting a mock peer review with three thoracic specialists. Our model has a lower type II error rate compared to manual peer-review physicians.Our model has many advantages over traditional machine learning algorithms, particularly that it does not suffer from class-imbalance. It can also explain why it flags each case and separate prescription and non-prescription-related features without learning from the data.

show abstract