Initial Development of a Computer Algorithm to Identify Patients With Breast and Lung Cancer Having Poor Prognosis in a Safety Net Hospital

Ramona L. Rhodes, Sabiha Kazi, Lei Xuan, Ruben Amarasingham, Ethan A. Halm

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Background: Physicians often have difficulty with prognostication and identification of patients who are in need of counseling about options for care at the end of life. Consequently, the objective of this study was to describe the initial stages in development of a computerized algorithm that will identify breast and lung cancer patients most in need of counseling about care options, including advance care planning, palliative care, and hospice. Methods: Clinical and non-clinical data were extracted from the electronic medical record of breast and lung cancer patients admitted to a large, urban hospital for the year 2010. These data were used to create an electronic (e-EOL) algorithm designed to identify advanced cancer patients who could benefit from in-depth discussion about end-of-life care options. Results: There were 369 eligible breast (42%) and lung (58%) cancer patients identified by ICD-9 code. The e-EOL algorithm identified 53 (14%) patients that met assigned criteria (presence of metastatic disease and albumin < 2.5 g/dl). The sensitivity, specificity, and positive predictive value of the first generation algorithm were 21%, 96%, and 91% when compared to physician expert chart review. Survival analysis showed that 6-month survival for algorithm positive cases was 46% versus 78% for algorithm negative cases, and 1-year survival was 32% versus 72%, respectively. Conclusions: Initial testing of the e-EOL algorithm appears to be promising. Other markers of advanced illness will added to the algorithm to improve its test operating characteristics so it may be used to identify patients with poor prognosis in real time.

Original languageEnglish (US)
Pages (from-to)678-683
Number of pages6
JournalAmerican Journal of Hospice and Palliative Medicine
Volume33
Issue number7
DOIs
StatePublished - Aug 1 2016

Fingerprint

Safety-net Providers
Lung Neoplasms
Breast Neoplasms
Terminal Care
International Classification of Diseases
Counseling
Advance Care Planning
Physicians
Hospices
Survival
Electronic Health Records
Urban Hospitals
Survival Analysis
Palliative Care
Albumins
Breast
Sensitivity and Specificity

Keywords

  • cancer
  • electronic medical record
  • end-of-life care
  • health information technology
  • palliative care
  • prognosis
  • safety net

ASJC Scopus subject areas

  • Medicine(all)

Cite this

@article{a128f2957d4b4ff7ad026a73cd853168,
title = "Initial Development of a Computer Algorithm to Identify Patients With Breast and Lung Cancer Having Poor Prognosis in a Safety Net Hospital",
abstract = "Background: Physicians often have difficulty with prognostication and identification of patients who are in need of counseling about options for care at the end of life. Consequently, the objective of this study was to describe the initial stages in development of a computerized algorithm that will identify breast and lung cancer patients most in need of counseling about care options, including advance care planning, palliative care, and hospice. Methods: Clinical and non-clinical data were extracted from the electronic medical record of breast and lung cancer patients admitted to a large, urban hospital for the year 2010. These data were used to create an electronic (e-EOL) algorithm designed to identify advanced cancer patients who could benefit from in-depth discussion about end-of-life care options. Results: There were 369 eligible breast (42{\%}) and lung (58{\%}) cancer patients identified by ICD-9 code. The e-EOL algorithm identified 53 (14{\%}) patients that met assigned criteria (presence of metastatic disease and albumin < 2.5 g/dl). The sensitivity, specificity, and positive predictive value of the first generation algorithm were 21{\%}, 96{\%}, and 91{\%} when compared to physician expert chart review. Survival analysis showed that 6-month survival for algorithm positive cases was 46{\%} versus 78{\%} for algorithm negative cases, and 1-year survival was 32{\%} versus 72{\%}, respectively. Conclusions: Initial testing of the e-EOL algorithm appears to be promising. Other markers of advanced illness will added to the algorithm to improve its test operating characteristics so it may be used to identify patients with poor prognosis in real time.",
keywords = "cancer, electronic medical record, end-of-life care, health information technology, palliative care, prognosis, safety net",
author = "Rhodes, {Ramona L.} and Sabiha Kazi and Lei Xuan and Ruben Amarasingham and Halm, {Ethan A.}",
year = "2016",
month = "8",
day = "1",
doi = "10.1177/1049909115591499",
language = "English (US)",
volume = "33",
pages = "678--683",
journal = "American Journal of Hospice and Palliative Medicine",
issn = "1049-9091",
publisher = "SAGE Publications Inc.",
number = "7",

}

TY - JOUR

T1 - Initial Development of a Computer Algorithm to Identify Patients With Breast and Lung Cancer Having Poor Prognosis in a Safety Net Hospital

AU - Rhodes, Ramona L.

AU - Kazi, Sabiha

AU - Xuan, Lei

AU - Amarasingham, Ruben

AU - Halm, Ethan A.

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Background: Physicians often have difficulty with prognostication and identification of patients who are in need of counseling about options for care at the end of life. Consequently, the objective of this study was to describe the initial stages in development of a computerized algorithm that will identify breast and lung cancer patients most in need of counseling about care options, including advance care planning, palliative care, and hospice. Methods: Clinical and non-clinical data were extracted from the electronic medical record of breast and lung cancer patients admitted to a large, urban hospital for the year 2010. These data were used to create an electronic (e-EOL) algorithm designed to identify advanced cancer patients who could benefit from in-depth discussion about end-of-life care options. Results: There were 369 eligible breast (42%) and lung (58%) cancer patients identified by ICD-9 code. The e-EOL algorithm identified 53 (14%) patients that met assigned criteria (presence of metastatic disease and albumin < 2.5 g/dl). The sensitivity, specificity, and positive predictive value of the first generation algorithm were 21%, 96%, and 91% when compared to physician expert chart review. Survival analysis showed that 6-month survival for algorithm positive cases was 46% versus 78% for algorithm negative cases, and 1-year survival was 32% versus 72%, respectively. Conclusions: Initial testing of the e-EOL algorithm appears to be promising. Other markers of advanced illness will added to the algorithm to improve its test operating characteristics so it may be used to identify patients with poor prognosis in real time.

AB - Background: Physicians often have difficulty with prognostication and identification of patients who are in need of counseling about options for care at the end of life. Consequently, the objective of this study was to describe the initial stages in development of a computerized algorithm that will identify breast and lung cancer patients most in need of counseling about care options, including advance care planning, palliative care, and hospice. Methods: Clinical and non-clinical data were extracted from the electronic medical record of breast and lung cancer patients admitted to a large, urban hospital for the year 2010. These data were used to create an electronic (e-EOL) algorithm designed to identify advanced cancer patients who could benefit from in-depth discussion about end-of-life care options. Results: There were 369 eligible breast (42%) and lung (58%) cancer patients identified by ICD-9 code. The e-EOL algorithm identified 53 (14%) patients that met assigned criteria (presence of metastatic disease and albumin < 2.5 g/dl). The sensitivity, specificity, and positive predictive value of the first generation algorithm were 21%, 96%, and 91% when compared to physician expert chart review. Survival analysis showed that 6-month survival for algorithm positive cases was 46% versus 78% for algorithm negative cases, and 1-year survival was 32% versus 72%, respectively. Conclusions: Initial testing of the e-EOL algorithm appears to be promising. Other markers of advanced illness will added to the algorithm to improve its test operating characteristics so it may be used to identify patients with poor prognosis in real time.

KW - cancer

KW - electronic medical record

KW - end-of-life care

KW - health information technology

KW - palliative care

KW - prognosis

KW - safety net

UR - http://www.scopus.com/inward/record.url?scp=84977091128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977091128&partnerID=8YFLogxK

U2 - 10.1177/1049909115591499

DO - 10.1177/1049909115591499

M3 - Article

C2 - 26140931

AN - SCOPUS:84977091128

VL - 33

SP - 678

EP - 683

JO - American Journal of Hospice and Palliative Medicine

JF - American Journal of Hospice and Palliative Medicine

SN - 1049-9091

IS - 7

ER -