A clinical decision support system learned from data to personalize treatment recommendations towards preventing breast cancer metastasis

Xia Jiang, Alan Wells, Adam Brufsky, Richard E Neapolitan

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Objective A Clinical Decision Support System (CDSS) that can amass Electronic Health Record (EHR) and other patient data holds promise to provide accurate classification and guide treatment choices. Our objective is to develop the Decision Support System for Making Personalized Assessments and Recommendations Concerning Breast Cancer Patients (DPAC), which is a CDSS learned from data that recommends the optimal treatment decisions based on a patient's features. Method We developed a Bayesian network architecture called Causal Modeling with Internal Layers (CAMIL), and an algorithm called Treatment Feature Interactions (TFI), which learns from data the interactions needed in a CAMIL model. Using the TFI algorithm, we learned interactions for six treatments from the LSDS-5YDM dataset. We created a CAMIL model using these interactions, resulting in a DPAC which recommends treatments towards preventing 5-year breast cancer metastasis. Results In a 5-fold cross-validation analysis, we compared the probability of being metastasis free in 5 years for patients who made decisions recommended by DPAC to those who did not. These probabilities are (the probability for those making the decisions appears first): Chemotherapy (.938, .872); breast/chest wall radiation (.939, .902); nodal field radiation (.940, .784); antihormone (.941, .906); HER2 inhibitors (.934, .880); neadjuvant therapy (.931, .837). In an application of DPAC to the independent METABRIC dataset, the probabilities for chemotherapy were (.845, .788). Discussion Patients who took the advice of DPAC had, as a group, notably better outcomes than those who did not. We conclude that DPAC is effective at amassing and analyzing data towards treatment recommendations. Some of the findings in DPAC are controversial. For example, DPAC says that chemotherapy increases the chances of metastasis for many node negative patients. This controversy shows the importance of developing a conclusive version of DPAC to ensure we provide patients with the best patient-specific treatment recommendations.

Original languageEnglish (US)
Article numbere0213292
JournalPloS one
Volume14
Issue number3
DOIs
StatePublished - Mar 1 2019

Fingerprint

Clinical Decision Support Systems
decision support systems
Decision support systems
metastasis
breast neoplasms
Chemotherapy
Breast Neoplasms
Neoplasm Metastasis
drug therapy
Radiation
Bayesian networks
Therapeutics
Network architecture
Drug Therapy
Health
chest
Electronic Health Records
Thoracic Wall
breasts
electronics

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Jiang, Xia ; Wells, Alan ; Brufsky, Adam ; Neapolitan, Richard E. / A clinical decision support system learned from data to personalize treatment recommendations towards preventing breast cancer metastasis. In: PloS one. 2019 ; Vol. 14, No. 3.
@article{7558c61be2644defb9e7c13e8d498f13,
title = "A clinical decision support system learned from data to personalize treatment recommendations towards preventing breast cancer metastasis",
abstract = "Objective A Clinical Decision Support System (CDSS) that can amass Electronic Health Record (EHR) and other patient data holds promise to provide accurate classification and guide treatment choices. Our objective is to develop the Decision Support System for Making Personalized Assessments and Recommendations Concerning Breast Cancer Patients (DPAC), which is a CDSS learned from data that recommends the optimal treatment decisions based on a patient's features. Method We developed a Bayesian network architecture called Causal Modeling with Internal Layers (CAMIL), and an algorithm called Treatment Feature Interactions (TFI), which learns from data the interactions needed in a CAMIL model. Using the TFI algorithm, we learned interactions for six treatments from the LSDS-5YDM dataset. We created a CAMIL model using these interactions, resulting in a DPAC which recommends treatments towards preventing 5-year breast cancer metastasis. Results In a 5-fold cross-validation analysis, we compared the probability of being metastasis free in 5 years for patients who made decisions recommended by DPAC to those who did not. These probabilities are (the probability for those making the decisions appears first): Chemotherapy (.938, .872); breast/chest wall radiation (.939, .902); nodal field radiation (.940, .784); antihormone (.941, .906); HER2 inhibitors (.934, .880); neadjuvant therapy (.931, .837). In an application of DPAC to the independent METABRIC dataset, the probabilities for chemotherapy were (.845, .788). Discussion Patients who took the advice of DPAC had, as a group, notably better outcomes than those who did not. We conclude that DPAC is effective at amassing and analyzing data towards treatment recommendations. Some of the findings in DPAC are controversial. For example, DPAC says that chemotherapy increases the chances of metastasis for many node negative patients. This controversy shows the importance of developing a conclusive version of DPAC to ensure we provide patients with the best patient-specific treatment recommendations.",
author = "Xia Jiang and Alan Wells and Adam Brufsky and Neapolitan, {Richard E}",
year = "2019",
month = "3",
day = "1",
doi = "10.1371/journal.pone.0213292",
language = "English (US)",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

A clinical decision support system learned from data to personalize treatment recommendations towards preventing breast cancer metastasis. / Jiang, Xia; Wells, Alan; Brufsky, Adam; Neapolitan, Richard E.

In: PloS one, Vol. 14, No. 3, e0213292, 01.03.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A clinical decision support system learned from data to personalize treatment recommendations towards preventing breast cancer metastasis

AU - Jiang, Xia

AU - Wells, Alan

AU - Brufsky, Adam

AU - Neapolitan, Richard E

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Objective A Clinical Decision Support System (CDSS) that can amass Electronic Health Record (EHR) and other patient data holds promise to provide accurate classification and guide treatment choices. Our objective is to develop the Decision Support System for Making Personalized Assessments and Recommendations Concerning Breast Cancer Patients (DPAC), which is a CDSS learned from data that recommends the optimal treatment decisions based on a patient's features. Method We developed a Bayesian network architecture called Causal Modeling with Internal Layers (CAMIL), and an algorithm called Treatment Feature Interactions (TFI), which learns from data the interactions needed in a CAMIL model. Using the TFI algorithm, we learned interactions for six treatments from the LSDS-5YDM dataset. We created a CAMIL model using these interactions, resulting in a DPAC which recommends treatments towards preventing 5-year breast cancer metastasis. Results In a 5-fold cross-validation analysis, we compared the probability of being metastasis free in 5 years for patients who made decisions recommended by DPAC to those who did not. These probabilities are (the probability for those making the decisions appears first): Chemotherapy (.938, .872); breast/chest wall radiation (.939, .902); nodal field radiation (.940, .784); antihormone (.941, .906); HER2 inhibitors (.934, .880); neadjuvant therapy (.931, .837). In an application of DPAC to the independent METABRIC dataset, the probabilities for chemotherapy were (.845, .788). Discussion Patients who took the advice of DPAC had, as a group, notably better outcomes than those who did not. We conclude that DPAC is effective at amassing and analyzing data towards treatment recommendations. Some of the findings in DPAC are controversial. For example, DPAC says that chemotherapy increases the chances of metastasis for many node negative patients. This controversy shows the importance of developing a conclusive version of DPAC to ensure we provide patients with the best patient-specific treatment recommendations.

AB - Objective A Clinical Decision Support System (CDSS) that can amass Electronic Health Record (EHR) and other patient data holds promise to provide accurate classification and guide treatment choices. Our objective is to develop the Decision Support System for Making Personalized Assessments and Recommendations Concerning Breast Cancer Patients (DPAC), which is a CDSS learned from data that recommends the optimal treatment decisions based on a patient's features. Method We developed a Bayesian network architecture called Causal Modeling with Internal Layers (CAMIL), and an algorithm called Treatment Feature Interactions (TFI), which learns from data the interactions needed in a CAMIL model. Using the TFI algorithm, we learned interactions for six treatments from the LSDS-5YDM dataset. We created a CAMIL model using these interactions, resulting in a DPAC which recommends treatments towards preventing 5-year breast cancer metastasis. Results In a 5-fold cross-validation analysis, we compared the probability of being metastasis free in 5 years for patients who made decisions recommended by DPAC to those who did not. These probabilities are (the probability for those making the decisions appears first): Chemotherapy (.938, .872); breast/chest wall radiation (.939, .902); nodal field radiation (.940, .784); antihormone (.941, .906); HER2 inhibitors (.934, .880); neadjuvant therapy (.931, .837). In an application of DPAC to the independent METABRIC dataset, the probabilities for chemotherapy were (.845, .788). Discussion Patients who took the advice of DPAC had, as a group, notably better outcomes than those who did not. We conclude that DPAC is effective at amassing and analyzing data towards treatment recommendations. Some of the findings in DPAC are controversial. For example, DPAC says that chemotherapy increases the chances of metastasis for many node negative patients. This controversy shows the importance of developing a conclusive version of DPAC to ensure we provide patients with the best patient-specific treatment recommendations.

UR - http://www.scopus.com/inward/record.url?scp=85062613746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062613746&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0213292

DO - 10.1371/journal.pone.0213292

M3 - Article

C2 - 30849111

AN - SCOPUS:85062613746

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 3

M1 - e0213292

ER -