Utility of a Clinical Decision Support System in Weight Loss Prediction After Head and Neck Cancer Radiotherapy

Zhi Cheng, Minoru Nakatsugawa, Xian Chong Zhou, Chen Hu, Stephen Greco, Ana Ponce Kiess, Brandi Page, Sara Alcorn, John Haller, Kazuki Utsunomiya, Shinya Sugiyama, Wei Fu, John Wong, Junghoon Lee, Todd McNutt, Harry Quon

Research output: Contribution to journalArticle

Abstract

PURPOSE: To evaluate the utility of a clinical decision support system (CDSS) using a weight loss prediction model. METHODS: A prediction model for significant weight loss (loss of greater than or equal to 7.5% of body mass at 3-month post radiotherapy) was created with clinical, dosimetric, and radiomics predictors from 63 patients in an independent training data set (accuracy, 0.78; area under the curve [AUC], 0.81) using least absolute shrinkage and selection operator logistic regression. Four physicians with varying experience levels were then recruited to evaluate 100 patients in an independent validation data set of head and neck cancer twice (ie, a pre-post design): first without and then with the aid of a CDSS derived from the prediction model. At both evaluations, physicians were asked to predict the development (yes/no) and probability of significant weight loss for each patient on the basis of patient characteristics, including pretreatment dysphagia and weight loss and information from the treatment plan. At the second evaluation, physicians were also provided with the prediction model's results for weight loss probability. Physicians' predictions were compared with actual weight loss, and accuracy and AUC were investigated between the two evaluations. RESULTS: The mean accuracy of the physicians' ability to identify patients who will experience significant weight loss (yes/no) increased from 0.58 (range, 0.47 to 0.63) to 0.63 (range, 0.58 to 0.72) with the CDSS ( P = .06). The AUC of weight loss probability predicted by physicians significantly increased from 0.56 (range, 0.46 to 0.64) to 0.69 (range, 0.63 to 0.73) with the aid of the CDSS ( P < .05). Specifically, more improvement was observed among less-experienced physicians ( P < .01). CONCLUSION: Our preliminary results demonstrate that physicians' decisions may be improved by a weight loss CDSS model, especially among less-experienced physicians. Additional study with a larger cohort of patients and more participating physicians is thus warranted for understanding the usefulness of CDSSs.

Original languageEnglish (US)
Pages (from-to)1-11
Number of pages11
JournalJCO clinical cancer informatics
Issue number3
DOIs
StatePublished - Mar 1 2019

Fingerprint

Clinical Decision Support Systems
Head and Neck Neoplasms
Weight Loss
Radiotherapy
Physicians
Area Under Curve
Decision Support Techniques
Deglutition Disorders
Logistic Models

Cite this

Utility of a Clinical Decision Support System in Weight Loss Prediction After Head and Neck Cancer Radiotherapy. / Cheng, Zhi; Nakatsugawa, Minoru; Zhou, Xian Chong; Hu, Chen; Greco, Stephen; Kiess, Ana Ponce; Page, Brandi; Alcorn, Sara; Haller, John; Utsunomiya, Kazuki; Sugiyama, Shinya; Fu, Wei; Wong, John; Lee, Junghoon; McNutt, Todd; Quon, Harry.

In: JCO clinical cancer informatics, No. 3, 01.03.2019, p. 1-11.

Research output: Contribution to journalArticle

@article{9b13944e88ee49b99e0a5e4095a20505,
title = "Utility of a Clinical Decision Support System in Weight Loss Prediction After Head and Neck Cancer Radiotherapy",
abstract = "PURPOSE: To evaluate the utility of a clinical decision support system (CDSS) using a weight loss prediction model. METHODS: A prediction model for significant weight loss (loss of greater than or equal to 7.5{\%} of body mass at 3-month post radiotherapy) was created with clinical, dosimetric, and radiomics predictors from 63 patients in an independent training data set (accuracy, 0.78; area under the curve [AUC], 0.81) using least absolute shrinkage and selection operator logistic regression. Four physicians with varying experience levels were then recruited to evaluate 100 patients in an independent validation data set of head and neck cancer twice (ie, a pre-post design): first without and then with the aid of a CDSS derived from the prediction model. At both evaluations, physicians were asked to predict the development (yes/no) and probability of significant weight loss for each patient on the basis of patient characteristics, including pretreatment dysphagia and weight loss and information from the treatment plan. At the second evaluation, physicians were also provided with the prediction model's results for weight loss probability. Physicians' predictions were compared with actual weight loss, and accuracy and AUC were investigated between the two evaluations. RESULTS: The mean accuracy of the physicians' ability to identify patients who will experience significant weight loss (yes/no) increased from 0.58 (range, 0.47 to 0.63) to 0.63 (range, 0.58 to 0.72) with the CDSS ( P = .06). The AUC of weight loss probability predicted by physicians significantly increased from 0.56 (range, 0.46 to 0.64) to 0.69 (range, 0.63 to 0.73) with the aid of the CDSS ( P < .05). Specifically, more improvement was observed among less-experienced physicians ( P < .01). CONCLUSION: Our preliminary results demonstrate that physicians' decisions may be improved by a weight loss CDSS model, especially among less-experienced physicians. Additional study with a larger cohort of patients and more participating physicians is thus warranted for understanding the usefulness of CDSSs.",
author = "Zhi Cheng and Minoru Nakatsugawa and Zhou, {Xian Chong} and Chen Hu and Stephen Greco and Kiess, {Ana Ponce} and Brandi Page and Sara Alcorn and John Haller and Kazuki Utsunomiya and Shinya Sugiyama and Wei Fu and John Wong and Junghoon Lee and Todd McNutt and Harry Quon",
year = "2019",
month = "3",
day = "1",
doi = "10.1200/CCI.18.00058",
language = "English (US)",
pages = "1--11",
journal = "JCO clinical cancer informatics",
issn = "2473-4276",
publisher = "American Society of Clinical Oncology",
number = "3",

}

TY - JOUR

T1 - Utility of a Clinical Decision Support System in Weight Loss Prediction After Head and Neck Cancer Radiotherapy

AU - Cheng, Zhi

AU - Nakatsugawa, Minoru

AU - Zhou, Xian Chong

AU - Hu, Chen

AU - Greco, Stephen

AU - Kiess, Ana Ponce

AU - Page, Brandi

AU - Alcorn, Sara

AU - Haller, John

AU - Utsunomiya, Kazuki

AU - Sugiyama, Shinya

AU - Fu, Wei

AU - Wong, John

AU - Lee, Junghoon

AU - McNutt, Todd

AU - Quon, Harry

PY - 2019/3/1

Y1 - 2019/3/1

N2 - PURPOSE: To evaluate the utility of a clinical decision support system (CDSS) using a weight loss prediction model. METHODS: A prediction model for significant weight loss (loss of greater than or equal to 7.5% of body mass at 3-month post radiotherapy) was created with clinical, dosimetric, and radiomics predictors from 63 patients in an independent training data set (accuracy, 0.78; area under the curve [AUC], 0.81) using least absolute shrinkage and selection operator logistic regression. Four physicians with varying experience levels were then recruited to evaluate 100 patients in an independent validation data set of head and neck cancer twice (ie, a pre-post design): first without and then with the aid of a CDSS derived from the prediction model. At both evaluations, physicians were asked to predict the development (yes/no) and probability of significant weight loss for each patient on the basis of patient characteristics, including pretreatment dysphagia and weight loss and information from the treatment plan. At the second evaluation, physicians were also provided with the prediction model's results for weight loss probability. Physicians' predictions were compared with actual weight loss, and accuracy and AUC were investigated between the two evaluations. RESULTS: The mean accuracy of the physicians' ability to identify patients who will experience significant weight loss (yes/no) increased from 0.58 (range, 0.47 to 0.63) to 0.63 (range, 0.58 to 0.72) with the CDSS ( P = .06). The AUC of weight loss probability predicted by physicians significantly increased from 0.56 (range, 0.46 to 0.64) to 0.69 (range, 0.63 to 0.73) with the aid of the CDSS ( P < .05). Specifically, more improvement was observed among less-experienced physicians ( P < .01). CONCLUSION: Our preliminary results demonstrate that physicians' decisions may be improved by a weight loss CDSS model, especially among less-experienced physicians. Additional study with a larger cohort of patients and more participating physicians is thus warranted for understanding the usefulness of CDSSs.

AB - PURPOSE: To evaluate the utility of a clinical decision support system (CDSS) using a weight loss prediction model. METHODS: A prediction model for significant weight loss (loss of greater than or equal to 7.5% of body mass at 3-month post radiotherapy) was created with clinical, dosimetric, and radiomics predictors from 63 patients in an independent training data set (accuracy, 0.78; area under the curve [AUC], 0.81) using least absolute shrinkage and selection operator logistic regression. Four physicians with varying experience levels were then recruited to evaluate 100 patients in an independent validation data set of head and neck cancer twice (ie, a pre-post design): first without and then with the aid of a CDSS derived from the prediction model. At both evaluations, physicians were asked to predict the development (yes/no) and probability of significant weight loss for each patient on the basis of patient characteristics, including pretreatment dysphagia and weight loss and information from the treatment plan. At the second evaluation, physicians were also provided with the prediction model's results for weight loss probability. Physicians' predictions were compared with actual weight loss, and accuracy and AUC were investigated between the two evaluations. RESULTS: The mean accuracy of the physicians' ability to identify patients who will experience significant weight loss (yes/no) increased from 0.58 (range, 0.47 to 0.63) to 0.63 (range, 0.58 to 0.72) with the CDSS ( P = .06). The AUC of weight loss probability predicted by physicians significantly increased from 0.56 (range, 0.46 to 0.64) to 0.69 (range, 0.63 to 0.73) with the aid of the CDSS ( P < .05). Specifically, more improvement was observed among less-experienced physicians ( P < .01). CONCLUSION: Our preliminary results demonstrate that physicians' decisions may be improved by a weight loss CDSS model, especially among less-experienced physicians. Additional study with a larger cohort of patients and more participating physicians is thus warranted for understanding the usefulness of CDSSs.

UR - http://www.scopus.com/inward/record.url?scp=85062819187&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062819187&partnerID=8YFLogxK

U2 - 10.1200/CCI.18.00058

DO - 10.1200/CCI.18.00058

M3 - Article

C2 - 30860866

AN - SCOPUS:85062819187

SP - 1

EP - 11

JO - JCO clinical cancer informatics

JF - JCO clinical cancer informatics

SN - 2473-4276

IS - 3

ER -