Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC)
Yves Paul Vincent Mbous,1 Zasim Azhar Siddiqui,1 Murtuza Bharmal,2 Traci LeMasters,1 Joanna Kolodney,3 George A Kelley,4 Khalid M Kamal,1 Usha Sambamoorthi5 1School of Pharmacy, Department of Pharmaceutical Systems and Policy, West Virginia University, Morgantown, WV, USA; 2AstraZeneca Oncology Outc...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2024-12-01
|
| Series: | ClinicoEconomics and Outcomes Research |
| Subjects: | |
| Online Access: | https://www.dovepress.com/predictive-and-interpretable-machine-learning-of-economic-burden-the-r-peer-reviewed-fulltext-article-CEOR |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846126541989216256 |
|---|---|
| author | Mbous YPV Siddiqui ZA Bharmal M LeMasters T Kolodney J Kelley GA Kamal KM Sambamoorthi U |
| author_facet | Mbous YPV Siddiqui ZA Bharmal M LeMasters T Kolodney J Kelley GA Kamal KM Sambamoorthi U |
| author_sort | Mbous YPV |
| collection | DOAJ |
| description | Yves Paul Vincent Mbous,1 Zasim Azhar Siddiqui,1 Murtuza Bharmal,2 Traci LeMasters,1 Joanna Kolodney,3 George A Kelley,4 Khalid M Kamal,1 Usha Sambamoorthi5 1School of Pharmacy, Department of Pharmaceutical Systems and Policy, West Virginia University, Morgantown, WV, USA; 2AstraZeneca Oncology Outcomes Research, AstraZeneca, Boston, Massachusetts, USA; 3School of Medicine, Department of Hematology/Oncology, West Virginia University, Morgantown, WV, USA; 4School of Public Health, Department of Epidemiology and Biostatistics, West Virginia University, Morgantown, WV, USA; 5College of Pharmacy, Department of Pharmacotherapy, University of North Texas Health Science Center, Fort Worth, TX, USACorrespondence: Khalid M Kamal, School of Pharmacy, Department of Pharmaceutical Systems and Policy, West Virginia University, Robert C. Byrd Health Sciences Center [North], P.O. Box 9510, Morgantown, WV, USA, Tel +1 304-293-1652, Email kkamal@hsc.wvu.eduObjective: To evaluate chronic conditions as leading predictors of economic burden over time among older adults with incident primary Merkel Cell Carcinoma (MCC) using machine learning methods.Methods: We used a retrospective cohort of older adults (age ≥ 67 years) diagnosed with MCC between 2009 and 2019. For these elderly MCC patients, we derived three phases (pre-diagnosis, during-treatment, and post-treatment) anchored around cancer diagnosis date. All three phases had 12 months baseline and 12-months follow-up periods. Chronic conditions were identified in baseline and follow-up periods, whereas annual total and out-of-pocket (OOP) healthcare expenditures were measured during the 12-month follow-up. XGBoost regression models and SHapley Additive exPlanations (SHAP) methods were used to identify leading predictors and their associations with economic burden.Results: Congestive heart failure (CHF), chronic kidney disease (CKD) and depression had the highest average incremental total expenditures during pre-diagnosis, treatment, and post-treatment phases, respectively ($25,004, $24,221, and $16,277 (CHF); $22,524, $19,350, $20,556 (CKD); and $21,645, $22,055, $18,350 (depression)), whereas the average incremental OOP expenditures during the same periods were $3703, $3,013, $2,442 (CHF); $2,457, $2,518, $2,914 (CKD); and $3,278, $2,322, $2,783 (depression). Except for hypertension and HIV, all chronic conditions had higher expenditures compared to those without the chronic conditions. Predictive models across each of phases of care indicated that CHF, CKD, and heart diseases were among the top 10 leading predictors; however, their feature importance ranking declined over time. Although depression was one of the leading drivers of expenditures in unadjusted descriptive models, it was not among the top 10 predictors.Conclusion: Among older adults with MCC, cardiac and renal conditions were the leading drivers of total expenditures and OOP expenditures. Our findings suggest that managing cardiac and renal conditions may be important for cost containment efforts.Keywords: Merkel cell carcinoma, healthcare expenditures, chronic conditions, XGBoost, SHAP, SEER-Medicare |
| format | Article |
| id | doaj-art-f9a043f7310546a397672f4897ab5b04 |
| institution | Kabale University |
| issn | 1178-6981 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | ClinicoEconomics and Outcomes Research |
| spelling | doaj-art-f9a043f7310546a397672f4897ab5b042024-12-12T16:44:09ZengDove Medical PressClinicoEconomics and Outcomes Research1178-69812024-12-01Volume 1684786898262Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC)Mbous YPVSiddiqui ZABharmal MLeMasters TKolodney JKelley GAKamal KMSambamoorthi UYves Paul Vincent Mbous,1 Zasim Azhar Siddiqui,1 Murtuza Bharmal,2 Traci LeMasters,1 Joanna Kolodney,3 George A Kelley,4 Khalid M Kamal,1 Usha Sambamoorthi5 1School of Pharmacy, Department of Pharmaceutical Systems and Policy, West Virginia University, Morgantown, WV, USA; 2AstraZeneca Oncology Outcomes Research, AstraZeneca, Boston, Massachusetts, USA; 3School of Medicine, Department of Hematology/Oncology, West Virginia University, Morgantown, WV, USA; 4School of Public Health, Department of Epidemiology and Biostatistics, West Virginia University, Morgantown, WV, USA; 5College of Pharmacy, Department of Pharmacotherapy, University of North Texas Health Science Center, Fort Worth, TX, USACorrespondence: Khalid M Kamal, School of Pharmacy, Department of Pharmaceutical Systems and Policy, West Virginia University, Robert C. Byrd Health Sciences Center [North], P.O. Box 9510, Morgantown, WV, USA, Tel +1 304-293-1652, Email kkamal@hsc.wvu.eduObjective: To evaluate chronic conditions as leading predictors of economic burden over time among older adults with incident primary Merkel Cell Carcinoma (MCC) using machine learning methods.Methods: We used a retrospective cohort of older adults (age ≥ 67 years) diagnosed with MCC between 2009 and 2019. For these elderly MCC patients, we derived three phases (pre-diagnosis, during-treatment, and post-treatment) anchored around cancer diagnosis date. All three phases had 12 months baseline and 12-months follow-up periods. Chronic conditions were identified in baseline and follow-up periods, whereas annual total and out-of-pocket (OOP) healthcare expenditures were measured during the 12-month follow-up. XGBoost regression models and SHapley Additive exPlanations (SHAP) methods were used to identify leading predictors and their associations with economic burden.Results: Congestive heart failure (CHF), chronic kidney disease (CKD) and depression had the highest average incremental total expenditures during pre-diagnosis, treatment, and post-treatment phases, respectively ($25,004, $24,221, and $16,277 (CHF); $22,524, $19,350, $20,556 (CKD); and $21,645, $22,055, $18,350 (depression)), whereas the average incremental OOP expenditures during the same periods were $3703, $3,013, $2,442 (CHF); $2,457, $2,518, $2,914 (CKD); and $3,278, $2,322, $2,783 (depression). Except for hypertension and HIV, all chronic conditions had higher expenditures compared to those without the chronic conditions. Predictive models across each of phases of care indicated that CHF, CKD, and heart diseases were among the top 10 leading predictors; however, their feature importance ranking declined over time. Although depression was one of the leading drivers of expenditures in unadjusted descriptive models, it was not among the top 10 predictors.Conclusion: Among older adults with MCC, cardiac and renal conditions were the leading drivers of total expenditures and OOP expenditures. Our findings suggest that managing cardiac and renal conditions may be important for cost containment efforts.Keywords: Merkel cell carcinoma, healthcare expenditures, chronic conditions, XGBoost, SHAP, SEER-Medicarehttps://www.dovepress.com/predictive-and-interpretable-machine-learning-of-economic-burden-the-r-peer-reviewed-fulltext-article-CEORmerkel cell carcinomaout-of-pocket expenditureseconomic burdencancer carechronic conditions |
| spellingShingle | Mbous YPV Siddiqui ZA Bharmal M LeMasters T Kolodney J Kelley GA Kamal KM Sambamoorthi U Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC) ClinicoEconomics and Outcomes Research merkel cell carcinoma out-of-pocket expenditures economic burden cancer care chronic conditions |
| title | Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC) |
| title_full | Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC) |
| title_fullStr | Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC) |
| title_full_unstemmed | Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC) |
| title_short | Predictive and Interpretable Machine Learning of Economic Burden: The Role of Chronic Conditions Among Elderly Patients with Incident Primary Merkel Cell Carcinoma (MCC) |
| title_sort | predictive and interpretable machine learning of economic burden the role of chronic conditions among elderly patients with incident primary merkel cell carcinoma mcc |
| topic | merkel cell carcinoma out-of-pocket expenditures economic burden cancer care chronic conditions |
| url | https://www.dovepress.com/predictive-and-interpretable-machine-learning-of-economic-burden-the-r-peer-reviewed-fulltext-article-CEOR |
| work_keys_str_mv | AT mbousypv predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc AT siddiquiza predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc AT bharmalm predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc AT lemasterst predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc AT kolodneyj predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc AT kelleyga predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc AT kamalkm predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc AT sambamoorthiu predictiveandinterpretablemachinelearningofeconomicburdentheroleofchronicconditionsamongelderlypatientswithincidentprimarymerkelcellcarcinomamcc |