A Temporal Examination of Platelet Counts as a Predictor of Prognosis in Lung, Prostate, and Colon Cancer Patients

Joanna L. Sylman, Hunter B. Boyce, Annachiara Mitrugno, Garth W. Tormoen, I. Chun Thomas, Todd H. Wagner, Jennifer S. Lee, John T. Leppert, Owen McCarty, Parag Mallick

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Platelets, components of hemostasis, when present in excess (>400 K/μL, thrombocytosis) have also been associated with worse outcomes in lung, ovarian, breast, renal, and colorectal cancer patients. Associations between thrombocytosis and cancer outcomes have been made mostly from single-time-point studies, often at the time of diagnosis. Using laboratory data from the Department of Veterans Affairs (VA), we examined the potential benefits of using longitudinal platelet counts in improving patient prognosis predictions. Ten features (summary statistics and engineered features) were derived to describe the platelet counts of 10,000+ VA lung, prostate, and colon cancer patients and incorporated into an age-adjusted LASSO regression analysis to determine feature importance, and predict overall or relapse-free survival, which was compared to the previously used approach of monitoring for thrombocytosis near diagnosis (Postdiag AG400 model). Temporal features describing acute platelet count increases/decreases were found to be important in cancer survival and relapse-survival that helped stratify good and bad outcomes of cancer patient groups. Predictions of overall and relapse-free survival were improved by up to 30% compared to the Postdiag AG400 model. Our study indicates the association of temporally derived platelet count features with a patients' prognosis predictions.

Original languageEnglish (US)
Article number6564
JournalScientific Reports
Volume8
Issue number1
DOIs
StatePublished - Dec 1 2018

Fingerprint

Platelet Count
Colonic Neoplasms
Lung Neoplasms
Prostatic Neoplasms
Thrombocytosis
Survival
Veterans
Recurrence
Neoplasms
Kidney Neoplasms
Hemostasis
Ovarian Neoplasms
Colorectal Neoplasms
Blood Platelets
Regression Analysis
Breast Neoplasms

ASJC Scopus subject areas

  • General

Cite this

Sylman, J. L., Boyce, H. B., Mitrugno, A., Tormoen, G. W., Thomas, I. C., Wagner, T. H., ... Mallick, P. (2018). A Temporal Examination of Platelet Counts as a Predictor of Prognosis in Lung, Prostate, and Colon Cancer Patients. Scientific Reports, 8(1), [6564]. https://doi.org/10.1038/s41598-018-25019-1

A Temporal Examination of Platelet Counts as a Predictor of Prognosis in Lung, Prostate, and Colon Cancer Patients. / Sylman, Joanna L.; Boyce, Hunter B.; Mitrugno, Annachiara; Tormoen, Garth W.; Thomas, I. Chun; Wagner, Todd H.; Lee, Jennifer S.; Leppert, John T.; McCarty, Owen; Mallick, Parag.

In: Scientific Reports, Vol. 8, No. 1, 6564, 01.12.2018.

Research output: Contribution to journalArticle

Sylman, JL, Boyce, HB, Mitrugno, A, Tormoen, GW, Thomas, IC, Wagner, TH, Lee, JS, Leppert, JT, McCarty, O & Mallick, P 2018, 'A Temporal Examination of Platelet Counts as a Predictor of Prognosis in Lung, Prostate, and Colon Cancer Patients', Scientific Reports, vol. 8, no. 1, 6564. https://doi.org/10.1038/s41598-018-25019-1
Sylman, Joanna L. ; Boyce, Hunter B. ; Mitrugno, Annachiara ; Tormoen, Garth W. ; Thomas, I. Chun ; Wagner, Todd H. ; Lee, Jennifer S. ; Leppert, John T. ; McCarty, Owen ; Mallick, Parag. / A Temporal Examination of Platelet Counts as a Predictor of Prognosis in Lung, Prostate, and Colon Cancer Patients. In: Scientific Reports. 2018 ; Vol. 8, No. 1.
@article{fe44b37f3866434dac74623b94a98b3a,
title = "A Temporal Examination of Platelet Counts as a Predictor of Prognosis in Lung, Prostate, and Colon Cancer Patients",
abstract = "Platelets, components of hemostasis, when present in excess (>400 K/μL, thrombocytosis) have also been associated with worse outcomes in lung, ovarian, breast, renal, and colorectal cancer patients. Associations between thrombocytosis and cancer outcomes have been made mostly from single-time-point studies, often at the time of diagnosis. Using laboratory data from the Department of Veterans Affairs (VA), we examined the potential benefits of using longitudinal platelet counts in improving patient prognosis predictions. Ten features (summary statistics and engineered features) were derived to describe the platelet counts of 10,000+ VA lung, prostate, and colon cancer patients and incorporated into an age-adjusted LASSO regression analysis to determine feature importance, and predict overall or relapse-free survival, which was compared to the previously used approach of monitoring for thrombocytosis near diagnosis (Postdiag AG400 model). Temporal features describing acute platelet count increases/decreases were found to be important in cancer survival and relapse-survival that helped stratify good and bad outcomes of cancer patient groups. Predictions of overall and relapse-free survival were improved by up to 30{\%} compared to the Postdiag AG400 model. Our study indicates the association of temporally derived platelet count features with a patients' prognosis predictions.",
author = "Sylman, {Joanna L.} and Boyce, {Hunter B.} and Annachiara Mitrugno and Tormoen, {Garth W.} and Thomas, {I. Chun} and Wagner, {Todd H.} and Lee, {Jennifer S.} and Leppert, {John T.} and Owen McCarty and Parag Mallick",
year = "2018",
month = "12",
day = "1",
doi = "10.1038/s41598-018-25019-1",
language = "English (US)",
volume = "8",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - A Temporal Examination of Platelet Counts as a Predictor of Prognosis in Lung, Prostate, and Colon Cancer Patients

AU - Sylman, Joanna L.

AU - Boyce, Hunter B.

AU - Mitrugno, Annachiara

AU - Tormoen, Garth W.

AU - Thomas, I. Chun

AU - Wagner, Todd H.

AU - Lee, Jennifer S.

AU - Leppert, John T.

AU - McCarty, Owen

AU - Mallick, Parag

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Platelets, components of hemostasis, when present in excess (>400 K/μL, thrombocytosis) have also been associated with worse outcomes in lung, ovarian, breast, renal, and colorectal cancer patients. Associations between thrombocytosis and cancer outcomes have been made mostly from single-time-point studies, often at the time of diagnosis. Using laboratory data from the Department of Veterans Affairs (VA), we examined the potential benefits of using longitudinal platelet counts in improving patient prognosis predictions. Ten features (summary statistics and engineered features) were derived to describe the platelet counts of 10,000+ VA lung, prostate, and colon cancer patients and incorporated into an age-adjusted LASSO regression analysis to determine feature importance, and predict overall or relapse-free survival, which was compared to the previously used approach of monitoring for thrombocytosis near diagnosis (Postdiag AG400 model). Temporal features describing acute platelet count increases/decreases were found to be important in cancer survival and relapse-survival that helped stratify good and bad outcomes of cancer patient groups. Predictions of overall and relapse-free survival were improved by up to 30% compared to the Postdiag AG400 model. Our study indicates the association of temporally derived platelet count features with a patients' prognosis predictions.

AB - Platelets, components of hemostasis, when present in excess (>400 K/μL, thrombocytosis) have also been associated with worse outcomes in lung, ovarian, breast, renal, and colorectal cancer patients. Associations between thrombocytosis and cancer outcomes have been made mostly from single-time-point studies, often at the time of diagnosis. Using laboratory data from the Department of Veterans Affairs (VA), we examined the potential benefits of using longitudinal platelet counts in improving patient prognosis predictions. Ten features (summary statistics and engineered features) were derived to describe the platelet counts of 10,000+ VA lung, prostate, and colon cancer patients and incorporated into an age-adjusted LASSO regression analysis to determine feature importance, and predict overall or relapse-free survival, which was compared to the previously used approach of monitoring for thrombocytosis near diagnosis (Postdiag AG400 model). Temporal features describing acute platelet count increases/decreases were found to be important in cancer survival and relapse-survival that helped stratify good and bad outcomes of cancer patient groups. Predictions of overall and relapse-free survival were improved by up to 30% compared to the Postdiag AG400 model. Our study indicates the association of temporally derived platelet count features with a patients' prognosis predictions.

UR - http://www.scopus.com/inward/record.url?scp=85045995332&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045995332&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-25019-1

DO - 10.1038/s41598-018-25019-1

M3 - Article

AN - SCOPUS:85045995332

VL - 8

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 6564

ER -