A Machine Learning Classification Model for Gastrointestinal Health in Cancer Survivors: Roles of Telomere Length and Social Determinants of Health
Abstract
:1. Introduction
2. Methods
2.1. Sample and Procedures
2.2. Features
2.2.1. Demographic and Clinical Data, Including Inflammatory Markers
2.2.2. Telomere Length (TL) Measurement
2.2.3. Social Determinants of Health (SDOH)
2.3. Outcome
GI Health
2.4. Data Analyses
2.4.1. Initial Data Analysis (For Feature Selection)
2.4.2. Machine Learning Model
2.5. Conceptual Framework
3. Results
3.1. Initial Descriptive Analyses
3.1.1. Participant Characteristics, Clinical Data, SDOH, and GI Health
3.1.2. Potential Risk Factors for GI Health Within the Training Dataset
3.2. Machine Learning Models for GI Health
3.2.1. Performance Comparison for Classification Models
3.2.2. Feature Importance
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Siegel, R.L.; Giaquinto, A.N.; Jemal, A. Cancer statistics, 2024. CA Cancer J. Clin. 2024, 74, 12–49. [Google Scholar] [CrossRef] [PubMed]
- Lustberg, M.B.; Kuderer, N.M.; Desai, A.; Bergerot, C.; Lyman, G.H. Mitigating long-term and delayed adverse events associated with cancer treatment: Implications for survivorship. Nat. Rev. Clin. Oncol. 2023, 20, 527–542. [Google Scholar] [CrossRef] [PubMed]
- Firkins, J.; Hansen, L.; Driessnack, M.; Dieckmann, N. Quality of life in “chronic” cancer survivors: A meta-analysis. J. Cancer Surviv. 2020, 14, 504–517. [Google Scholar] [CrossRef] [PubMed]
- Miller, K.D.; Nogueira, L.; Devasia, T.; Mariotto, A.B.; Yabroff, K.R.; Jemal, A.; Kramer, J.; Siegel, R.L. Cancer treatment and survivorship statistics, 2022. CA Cancer J. Clin. 2022, 72, 409–436. [Google Scholar] [CrossRef]
- Song, B.C.; Bai, J. Microbiome-gut-brain axis in cancer treatment-related psychoneurological toxicities and symptoms: A systematic review. Support. Care Cancer 2021, 29, 605–617. [Google Scholar] [CrossRef] [PubMed]
- Mitra, A.; Biegert, G.W.G.; Delgado, A.Y.; Karpinets, T.V.; Solley, T.N.; Mezzari, M.P.; Yoshida-Court, K.; Petrosino, J.F.; Mikkelson, M.D.; Lin, L. Microbial diversity and composition is associated with patient-reported toxicity during chemoradiation therapy for cervical cancer. Int. J. Radiant. Oncol. Biol. Phys. 2020, 107, 163–171. [Google Scholar] [CrossRef] [PubMed]
- Han, C.J.; Yang, G.S.; Syrjala, K. Symptom experiences in colorectal cancer survivors after cancer treatments: A systematic review and meta-analysis. Cancer Nurs. 2020, 43, E132–E158. [Google Scholar] [CrossRef] [PubMed]
- Han, C.J.; Reding, K.W.; Kalady, M.F.; Yung, R.; Greenlee, H.; Paskett, E.D. Factors associated with long-term gastrointestinal symptoms in colorectal cancer survivors in the women’s health initiatives (WHI study). PLoS ONE 2023, 18, e0286058. [Google Scholar] [CrossRef]
- Deleemans, J.M.; Chleilat, F.; Reimer, R.A.; Baydoun, M.; Piedalue, K.-A.; Lowry, D.E.; Henning, J.-W.; Carlson, L.E. The chemo-gut pilot study: Associations between gut microbiota, gastrointestinal symptoms, and psychosocial health outcomes in a cross-sectional sample of young adult cancer survivors. Curr. Oncol. 2022, 29, 2973–2994. [Google Scholar] [CrossRef]
- Muls, A.C.; Watson, L.; Shaw, C.; Andreyev, H.J.N. Managing gastrointestinal symptoms after cancer treatment: A practical approach for gastroenterologists. Frontline Gastroenterol. 2013, 4, 57–68. [Google Scholar] [CrossRef]
- Wiranata, J.A.; Hutajulu, S.H.; Astari, Y.K.; Leo, B.; Bintoro, B.S.; Hardianti, M.S.; Taroeno-Hariadi, K.W.; Kurnianda, J.; Purwanto, I. Patient-reported outcomes and symptom clusters pattern of chemotherapy-induced toxicity in patients with early breast cancer. PLoS ONE 2024, 19, e0298928. [Google Scholar] [CrossRef] [PubMed]
- Sipaviciute, A.; Sileika, E.; Burneckis, A.; Dulskas, A. Late gastrointestinal toxicity after radiotherapy for rectal cancer: A systematic review. Int. J. Color. Dis. 2020, 35, 977–983. [Google Scholar] [CrossRef]
- Baltussen, J.C.; de Glas, N.A.; van Holstein, Y.; van der Elst, M.; Trompet, S.; Uit den Boogaard, A.; van der Plas-Krijgsman, W.; Labots, G.; Holterhues, C.; van der Bol, J.M.; et al. Chemotherapy-Related Toxic Effects and Quality of Life and Physical Functioning in Older Patients. JAMA Network Open 2023, 6, e2339116. [Google Scholar] [CrossRef]
- Podolski, A.J.; Gucalp, R. GI Toxicities from Cancer Therapy. In Geriatric Gastroenterology; Springer: Berlin/Heidelberg, Germany, 2021; pp. 341–379. [Google Scholar] [CrossRef]
- Dumic, I.; Nordin, T.; Jecmenica, M.; Stojkovic Lalosevic, M.; Milosavljevic, T.; Milovanovic, T. Gastrointestinal tract disorders in older age. Can. J. Gastroentero. Hepatol 2019, 2019, 6757524. [Google Scholar] [CrossRef] [PubMed]
- Busby-Whitehead, J.; Whitehead, W.E.; Sperber, A.D.; Palsson, O.S.; Simrén, M. The aging gut: Symptoms compatible with disorders of gut-brain interaction (DGBI) in older adults in the general population. J. Am. Geriatr. Soc. 2024, 72, 479–489. [Google Scholar] [CrossRef]
- Rentscher, K.E.; Bethea, T.N.; Zhai, W.; Small, B.J.; Zhou, X.; Ahles, T.A.; Ahn, J.; Breen, E.C.; Cohen, H.J.; Extermann, M. Epigenetic aging in older breast cancer survivors and noncancer controls: Preliminary findings from the Thinking and Living with Cancer Study. Cancer 2023, 129, 2741–2753. [Google Scholar] [CrossRef] [PubMed]
- Gallicchio, L.; Guida, J.L.; Green, P.A. Introduction to the special section on cancer survivors and treatment-related accelerated aging. J. Cancer Surviv. 2024, 1–4. [Google Scholar] [CrossRef] [PubMed]
- Wang, H.; Chen, X.; Wang, S.; Zhang, H. Exploration of the causal effects of leukocyte telomere length and four gastrointestinal diseases: A two-sample bidirectional Mendelian randomization study. BMC Gastroenterol. 2023, 23, 446. [Google Scholar] [CrossRef]
- Wang, S.; El Jurdi, N.; Thyagarajan, B.; Prizment, A.; Blaes, A.H. Accelerated Aging in Cancer Survivors: Cellular Senescence, Frailty, and Possible Opportunities for Interventions. Int. J. Mol. Sci. 2024, 25, 3319. [Google Scholar] [CrossRef] [PubMed]
- Brown, J.C.; Sturgeon, K.; Sarwer, D.B.; Troxel, A.B.; DeMichele, A.M.; Denlinger, C.S.; Schmitz, K.H. The effects of exercise and diet on oxidative stress and telomere length in breast cancer survivors. Breast Cancer Res. Treat. 2023, 199, 109–117. [Google Scholar] [CrossRef] [PubMed]
- Xu, X.; Qu, K.; Pang, Q.; Wang, Z.; Zhou, Y.; Liu, C. Association between telomere length and survival in cancer patients: A meta-analysis and review of literature. Front. Med. 2016, 10, 191–203. [Google Scholar] [CrossRef] [PubMed]
- Vince, R.A.; Jiang, R.; Bank, M.; Quarles, J.; Patel, M.; Sun, Y.; Hartman, H.; Zaorsky, N.G.; Jia, A.; Shoag, J. Evaluation of social determinants of health and prostate cancer outcomes among black and white patients: A systematic review and meta-analysis. JAMA Netw. Open 2023, 6, e2250416. [Google Scholar] [CrossRef] [PubMed]
- Han, C.J.; Tounkara, F.; Kalady, M.; Noonan, A.M.; Burse, N.R.; Paskett, E.D.; Von Ah, D. Risk factors of health-related quality of life among gastrointestinal cancer survivors in the US: With a focus on social and behavioral determinants of health (SBDH). Int. J. Environ. Res. Public Health 2023, 20, 6676. [Google Scholar] [CrossRef] [PubMed]
- Yao, J.; Chen, X.; Meng, F.; Cao, H.; Shu, X. Combined influence of nutritional and inflammatory status and depressive symptoms on mortality among US cancer survivors: Findings from the NHANES. Brain Behav. Immun. 2024, 115, 109–117. [Google Scholar] [CrossRef] [PubMed]
- Antoni, M.H.; Moreno, P.I.; Penedo, F.J. Stress management interventions to facilitate psychological and physiological adaptation and optimal health outcomes in cancer patients and survivors. Annu. Rev. Psychol. 2023, 74, 423–455. [Google Scholar] [CrossRef]
- Needham, B.L.; Adler, N.; Gregorich, S.; Rehkopf, D.; Lin, J.; Blackburn, E.H.; Epel, E.S. Socioeconomic status, health behavior, and leukocyte telomere length in the National Health and Nutrition Examination Survey, 1999–2002. Soc. Sci. Med. 2013, 85, 1–8. [Google Scholar] [CrossRef]
- Kumar, K.; Kumar, P.; Deb, D.; Unguresan, M.-L.; Muresan, V. Artificial intelligence and machine learning based intervention in medical infrastructure: A review and future trends. Healthcare 2023, 11, 207. [Google Scholar] [CrossRef] [PubMed]
- Oyebode, O.; Fowles, J.; Steeves, D.; Orji, R. Machine learning techniques in adaptive and personalized systems for health and wellness. Int. J. Human-Comp. Int. 2022, 39, 1938–1962. [Google Scholar] [CrossRef]
- Black, J.E.; Kueper, J.K.; Williamson, T.S. An introduction to machine learning for classification and prediction. Fam. Pract. 2023, 40, 200–204. [Google Scholar] [CrossRef] [PubMed]
- Shu, X.; Ye, Y. Knowledge Discovery: Methods from data mining and machine learning. Soc. Sci. Res. 2023, 110, 102817. [Google Scholar] [CrossRef] [PubMed]
- Zhang, B.; Shi, H.; Wang, H. Machine learning and AI in cancer prognosis, prediction, and treatment selection: A critical approach. J. Multidiscip. Healthc. 2023, 16, 1779–1791. [Google Scholar] [CrossRef]
- Dye, B.; Barker, L.; Selwitz, R.; Lewis, B.; Wu, T.; Fryar, C.; Ostchega, Y.; Beltran, E.; Ley, E. Overview and quality assurance for the National Health and Nutrition Examination Survey (NHANES) oral health component, 1999–2002. Community Dent. Oral Epidemiol. 2007, 35, 140–151. [Google Scholar] [CrossRef]
- Johnson, C.L.; Paulose-Ram, R.; Ogden, C.L.; Carroll, M.D.; Kruszon-Moran, D.; Dohrmann, S.M.; Curtin, L.R. National health and nutrition examination survey: Analytic guidelines, 1999–2010. Vital Health Stat 2 2013, 161, 1–24. [Google Scholar]
- Qiao, H.; Chen, Y.; Qian, C.; Guo, Y. Clinical data mining: Challenges, opportunities, and recommendations for translational applications. J Transl Med. 2024, 22, 185. [Google Scholar] [CrossRef] [PubMed]
- Liu, B.; Taioli, E. Seasonal variations of complete blood count and inflammatory biomarkers in the US population-analysis of NHANES data. PLoS ONE 2015, 10, e0142382. [Google Scholar] [CrossRef]
- Mazidi, M.; Kengne, A.P.; Sahebkar, A.; Banach, M. Telomere Length Is Associated With Cardiometabolic Factors in US Adults. Angiology 2018, 69, 164–169. [Google Scholar] [CrossRef] [PubMed]
- Mazidi, M.; Kengne, A.P.; Vatanparast, H. Food Security and Leukocyte Telomere Length in Adult Americans. Oxid. Med. Cell Longev. 2017, 2017, 5427657. [Google Scholar] [CrossRef] [PubMed]
- Mazidi, M.; Penson, P.; Banach, M. Association between telomere length and complete blood count in US adults. Arch. Med. Sci. 2017, 13, 601–605. [Google Scholar] [CrossRef]
- Shen, G.; Huang, J.Y.; Huang, Y.Q.; Feng, Y.Q. The Relationship between Telomere Length and Cancer Mortality: Data from the 1999–2002 National Healthy and Nutrition Examination Survey (NHANES). J. Nutr. Health Aging 2020, 24, 9–15. [Google Scholar] [CrossRef] [PubMed]
- NHANES—National Health and Nutrition Examination Survey Homepage. Available online: www.cdc.gov (accessed on 16 July 2024).
- Gómez, C.A.; Kleinman, D.V.; Pronk, N.; Gordon, G.L.W.; Ochiai, E.; Blakey, C.; Johnson, A.; Brewer, K.H. Addressing health equity and social determinants of health through Healthy People 2030. J. Public Health Manag. Pract. 2021, 27 (Suppl. 6), S249–S257. [Google Scholar] [CrossRef]
- Committee on the Recommended Social and Behavioral Domains and Measures for Electronic Health Records; Board on Population Health and Public Health Practice; Institute of Medicine. Capturing Social and Behavioral Domains and Measures in Electronic Health Records: Phase 2; National Academies Press: Washington, DC, USA, 2015. [Google Scholar]
- Giuse, N.B.; Koonce, T.Y.; Kusnoor, S.V.; Prather, A.A.; Gottlieb, L.M.; Huang, L.C.; Phillips, S.E.; Shyr, Y.; Adler, N.E.; Stead, W.W. Institute of Medicine Measures of Social and Behavioral Determinants of Health: A Feasibility Study. Am. J. Prev. Med. 2017, 52, 199–206. [Google Scholar] [CrossRef] [PubMed]
- Byhoff, E.; Tripodis, Y.; Freund, K.M.; Garg, A. Gender Differences in Social and Behavioral Determinants of Health in Aging Adults. J. Gen. Intern. Med. 2019, 34, 2310–2312. [Google Scholar] [CrossRef] [PubMed]
- Kendall, A.; Olson, C.M.; Frongillo, E.A., Jr. Validation of the Radimer/Cornell measures of hunger and food insecurity. J. Nutr. 1995, 125, 2793–2801. [Google Scholar] [PubMed]
- Bush, K.; Kivlahan, D.R.; McDonell, M.B.; Fihn, S.D.; Bradley, K.A. The AUDIT alcohol consumption questions (AUDIT-C): An effective brief screening test for problem drinking. Ambulatory Care Quality Improvement Project (ACQUIP). Alcohol Use Disorders Identification Test. Arch. Intern. Med. 1998, 158, 1789–1795. [Google Scholar] [CrossRef] [PubMed]
- Zhang, L.; Ferguson, T.F.; Simonsen, N.; Chen, L.; Tseng, T.S. Racial/Ethnic Disparities in Health-Related Quality of Life among Participants with Self-Reported Diabetes from NHANES 2001–2010. Diabetes Educ. 2014, 40, 496–506. [Google Scholar] [CrossRef] [PubMed]
- Cabello-Solorzano, K.; De Araujo, I.O.; Peña, M.; Correia, L.; Tallón-Ballesteros, A.J. The impact of data normalization on the accuracy of machine learning algorithms: A comparative analysis. In Lecture Notes in Networks and Systems; Springer: Berlin/Heidelberg, Germany, 2023; pp. 344–353. [Google Scholar] [CrossRef]
- Gobbens, R.J.; Luijkx, K.G.; Wijnen-Sponselee, M.T.; Schols, J.M. Towards an integral conceptual model of frailty. J. Nutr. Health Aging 2010, 14, 175–181. [Google Scholar] [CrossRef] [PubMed]
- Swanson, K.; Wu, E.; Zhang, A.; Alizadeh, A.A.; Zou, J. From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. Cell 2023, 186, 1772–1791. [Google Scholar] [CrossRef] [PubMed]
- Cruz, J.A.; Wishart, D.S. Applications of machine learning in cancer prediction and prognosis. Cancer Inform. 2006, 2, 59–77. [Google Scholar] [CrossRef]
- Rafique, R.; Islam, S.R.; Kazi, J.U. Machine learning in the prediction of cancer therapy. Comput. Struct. Biotechnol. J. 2021, 19, 4003–4017. [Google Scholar] [CrossRef] [PubMed]
- Haun, M.W.; Simon, L.; Sklenarova, H.; Zimmermann-Schlegel, V.; Friederich, H.C.; Hartmann, M. Predicting anxiety in cancer survivors presenting to primary care—A machine learning approach accounting for physical comorbidity. Cancer Med. 2021, 10, 5001–5016. [Google Scholar] [CrossRef] [PubMed]
- Badger, T.A.; Segrin, C.; Crane, T.E.; Chalasani, P.; Arslan, W.; Hadeed, M.; Sikorskii, A. Social determinants of health and symptom burden during cancer treatment. Nurs. Res. 2023, 72, 103–113. [Google Scholar] [CrossRef]
- McCall, M.K.; Connolly, M.; Nugent, B.; Conley, Y.P.; Bender, C.M.; Rosenzweig, M.Q. Symptom experience, management, and outcomes according to race and social determinants including genomics, epigenomics, and metabolomics (SEMOARS+ GEM): An explanatory model for breast cancer treatment disparity. J. Cancer Educ. 2020, 35, 428–440. [Google Scholar] [CrossRef]
- Westrick, A.C.; Langa, K.M.; Eastman, M.; Ospina-Romero, M.; Mullins, M.A.; Kobayashi, L.C. Functional aging trajectories of older cancer survivors: A latent growth analysis of the US Health and Retirement Study. J. Cancer Surviv. 2023, 17, 1499–1509. [Google Scholar] [CrossRef]
- Chi, Z.; Bai, X.; Zhang, Z. Risk relationship between leukocyte telomere length and constipation: A Mendelian randomization study. Front. Med. 2023, 10, 1177785. [Google Scholar] [CrossRef] [PubMed]
- Singh, S.; Giron, L.B.; Shaikh, M.W.; Shankaran, S.; Engen, P.A.; Bogin, Z.R.; Bambi, S.A.; Goldman, A.R.; Azevedo, J.L.; Orgaz, L. Distinct intestinal microbial signatures linked to accelerated systemic and intestinal biological aging. Microbiome 2024, 12, 31. [Google Scholar] [CrossRef]
- Hooten, N.N.; Pacheco, N.L.; Smith, J.T.; Evans, M.K. The accelerated aging phenotype: The role of race and social determinants of health on aging. Ageing Res. Rev. 2022, 73, 101536. [Google Scholar] [CrossRef] [PubMed]
- Androulakis, I.P. From cells to society: Untangling the web of stress, inflammation, and social determinants of health. Front. Sci. 2024, 2, 1358784. [Google Scholar] [CrossRef]
- Tarver, W.L.; Justice, Z.; Jonnalagadda, P.; Rahurkar, S.; Obeng-Gyasi, S.; Krok-Schoen, J.L.; Petrecca, A.; Paskett, E.D. A scoping review of the evidence on survivorship care plans among minority, rural, and low-income populations. J. Cancer Surviv. 2024, 1–39. [Google Scholar] [CrossRef]
- Vardy, J.; Liew, A.; Turner, J.; Kerin-Ayres, K.; Butler, S.; Deguchi, C.; Khatri, S.; Wildbore, C.; Mo, C.; Hamayun, M. What happens to cancer survivors attending a structured cancer survivorship clinic? Symptoms, quality of life, and lifestyle changes over the first year at the Sydney Cancer Survivorship Centre clinic. Support. Care Cancer. 2021, 29, 1337–1345. [Google Scholar] [CrossRef]
- Addison, S.; Shirima, D.; Aboagye-Mensah, E.B.; Dunovan, S.G.; Pascal, E.Y.; Lustberg, M.B.; Arthur, E.K.; Nolan, T.S. Effects of tandem cognitive behavioral therapy and healthy lifestyle interventions on health-related outcomes in cancer survivors: A systematic review. J. Cancer Surviv. 2022, 16, 1023–1046. [Google Scholar] [CrossRef] [PubMed]
- Nouve, Y.; Zhao, S.; Zheng, Y. Decoding the misperception: Exploring measurement error in self-rated assessments of diet quality. Food Qual. Prefer. 2024, 120, 105234. [Google Scholar] [CrossRef]
- Tucker, A.C.; Bresnahan, C.; John, S.; Johnson, J.; Leung, C.W.; Mui, Y.; Hager, E.R.; Wolfson, J.A. Food (in) security in relation to nutrition (in) security in a national cross-sectional sample of Supplemental Nutrition Assistance Program participants: Considerations of an emerging construct. Am. J. Clin. Nutr. 2024, 119, 1475–1484. [Google Scholar] [CrossRef] [PubMed]
- Robien, K.; Clausen, M.; Sullo, E.; Ford, Y.R.; Griffith, K.A.; Le, D.; Wickersham, K.E.; Wallington, S.F. Prevalence of food insecurity among cancer survivors in the United States: A scoping review. J. Acad. Nutr. Diet. 2023, 123, 330–346. [Google Scholar] [CrossRef] [PubMed]
- Christian, V.J.; Miller, K.R.; Martindale, R.G. Food insecurity, malnutrition, and the microbiome. Curr. Nutr. Rep. 2020, 9, 356–360. [Google Scholar] [CrossRef] [PubMed]
- Hussaini, S.Q.; Chen, K.Y.; Blackford, A.L.; Chino, F.; Gupta, A. Food insecurity and gastrointestinal (GI) cancer mortality in the United States, 2015 to 2019. J. Clin. Oncol. 2023, 41, 788. [Google Scholar] [CrossRef]
Total Cancer Survivors (N = 645) | Training Set a (n = 75% of Total Sample, n = 484) | Test Set b (n = 25% of Total Sample, n = 161) | p |
---|---|---|---|
Age (years), mean ± SE (range) | 66.3 ± 14.7 (21–85) | 65.5 ± 16.2 (22–85) | 0.102 |
Female (n,%) | 235 (49.5) | 84 (50.7) | 0.311 |
Modified comorbidity index (≥2) (n,%) | 168 (42.3) | 66 (43.2) | 0.122 |
Types of cancers (n,%) | Skin: 152 (21.2) | Skin: 44 (27.3) | 0.143 |
GU: 102 (21.0) | Breast: 35 (21.7) | ||
Breast: 75 (15.6) | GU: 30 (18.6) | ||
Ovary–Uterine: 45 (9.3) | Head and Neck: 21 (13.0) | ||
Head and Neck: 42 (8.6) | GI: 15 (9.3) | ||
GI: 41 (8.4) | Ovary–Uterine: 8 (5.0) | ||
Lung: 15 (3.1) | Lung: 5 (3.1) | ||
Hematological: 12 (2.5) | Hematological: 3 (1.9) | ||
Body mass index (BMI), kg/m2, mean ± SE | 30.1 (0.2) | 31.2 (0.3) | 0.982 |
BMI, kg/m2 (n, %) < 25 | 170 (35.2) | 56 (34.7) | 0.675 |
25 ≤ BMI < 30 | 160 (33.1) | 57 (35.1) | |
30 ≤ BMI | 153 (31.7) | 48 (30.2) | |
WBC (k/μL), normal (4–11 k/μL), mean ± SE | 7.02 (2.1) | 7.04 (2.0) | 0.192 |
CRP (mg/dL), normal (<0.3 mg/dL), mean ± SE | 0.51 (0.9) | 0.62 (1.4) | 0.124 |
Telomere lengths (kb), mean ± SE | 0.93 (0.2) | 0.93 (0.2) | 0.823 |
Gastrointestinal health (n, %) | Worse: 157 (32.5) | Worse: 59 (36.6) | 0.412 |
Better: 327 (67.5) | Better: 101 (62.7) | ||
SDOH variables | |||
Race/Ethnicity | 0.413 | ||
Non-Hispanic White | 356 (73.3) | 121(75.0) | |
Non-Hispanic Black | 53 (10.9) | 18 (11.0) | |
Non-Hispanic Other | 6 (1.2) | 2 (1.2) | |
Hispanic | 69 (14.2) | 20 (12.8) | |
Marital status | 0.541 | ||
Married/Partnered | 329 (68.1) | 110 (68.3) | |
Divorced/Widowed/Single | 155 (31.9) | 51 (31.7) | |
Education | 0.112 | ||
High school or less | 247 (51.0) | 80 (49.7) | |
College or technical school | 130 (26.9) | 44 (27.3) | |
Graduate school | 107 (22.1) | 37 (23.0) | |
Household income (yr.) | 0.353 | ||
Less than USD 25,000 | 169 (34.9) | 57 (35.4) | |
USD 25,000 to <USD 55,000 | 150 (31.0) | 51 (31.7) | |
USD 55,000 to <USD 75,000 | 45 (9.2) | 17 (10.6) | |
USD 75,000 and over | 107 (22.1) | 33 (20.5) | |
Poverty–Income ratio (PIR) < 1 (yes): annual household income below the poverty level. | 193 (39.7) | 60 (37.3) | 0.423 |
Food insecurity (yes) | 42 (8.6) | 13 (8.1) | 0.879 |
Cancer health behaviors (yes) | |||
Current smoking status | 86 (17.7) | 31 (19.3) | 0.114 |
Current heavy alcohol use | 86 (17.7) | 21 (13.0) | 0.198 |
Regular physical activity | 286 (58.8) | 76 (47.2) | 0.108 |
Diet quality (HEI-2015 score, 0–100, mean ± SE) | 48.8 (12.3) | 48.9 (8.3) | 0.103 |
Total Cancer Survivors (N = 484) n (%) Otherwise Specified | GI Health (n, %) | ||
---|---|---|---|
Better (n = 327, 67.5%) | Worse (n = 157, 32.5%) | p | |
Age (years), mean ± SE, range | 63.3 (10.9) | 66.4 (11.2) | 47.4, 0.031 |
Female (n,%) | 153 (47) | 103(65) | 6.1, 0.013 |
Modified comorbidity index (≥2) (n,%) | 133(41) | 71 (45) | 5.4, 0.043 |
Types of cancers (n,%) | Skin: 65 (20.1) | Skin: 31(19.8) | 12.1, 0.100 |
GU: 62 (19) | GU: 26 (16.2) | ||
Breast: 53 (16.3) | Breast: 27(17.3) | ||
Ovary–Uterine: 37 (11.3) | Ovary–Uterine: 18 (11.5) | ||
Head and Neck: 31 (9.5) | Head and Neck: 17 (10.9) | ||
GI: 27 (8.5) | GI: 15 (9.3) | ||
Lung: 13 (4.1) | Lung: 8 (5.2) | ||
Hematological: 36 (11.2) | Hematological: 15 (9.8) | ||
Body mass index (BMI), kg/m2, mean ± SE | 31.1 (0.1) | 30.1 (0.4) | 0.982 |
BMI, kg/m2 (n, %) < 25 | 102 (31.3) | 47 (29.8) | 0.853 |
25 ≤ BMI < 30 | 96 (29.5) | 48 (30.3) | |
30 > BMI | 128 (39.8) | 62 (39.9) | |
WBC (k/μL), normal (4–11 k/μL), mean ± SE | 5.4 (1.1) | 8.5 (1.5) | 146.3, 0.046 |
CRP (mg/dL), normal (<0.3 mg/dL), mean ± SE | 0.4 (0.8) | 1.0 (1.1) | 238.4, 0.001 |
Telomere lengths (kb), mean ± SE | 0.97 (0.2) | 0.64 (0.3) | 85.1, 0.013 |
SDOH variables | |||
Race/Ethnicity | 24.2, 0.039 | ||
Non-Hispanic White | 260 (80.3) | 122 (77.3) | |
Non-Hispanic Black | 35 (10.7) | 17 (10.5) | |
Non-Hispanic Other | 5 (1.5) | 2 (1.5) | |
Hispanic | 24 (7.5) | 17 (10.7) | |
Marital status | 3.6, 0.730 | ||
Married/Partnered | 220 (67.9) | 104 (65.6) | |
Divorced/Widowed/Single | 104 (32.1) | 54 (34.4) | |
Education | 16.6, 0.502 | ||
High school or less | 158 (48.8) | 81 (51.1) | |
College or technical school | 88 (27.1) | 41 (25.8) | |
Graduate school | 78 (24.1) | 36 (23.1) | |
Household income (yr.) | 8.43, 0.038 | ||
Less than USD 25,000 | 114 (35.3) | 58 (36.8) | |
USD 25,000 to <USD 55,000 | 100 (31.0) | 45 (28.3) | |
USD 55,000 to <USD 75,000 | 50 (15.4) | 26 (16.4) | |
USD 75,000 and over | 59 (18.3) | 29 (18.5) | |
Poverty–Income ratio (PIR) < 1 indicating a high poverty level (yes): annual household income below the poverty level. | 113 (34.9) | 59 (37.6) | 18.01, <0.001 |
Food insecurity (yes) | 18 (5.6) | 13 (8.0) | 17.01, 0.021 |
Cancer health behaviors (yes) | |||
Current smoking status | 53 (16.3) | 31 (19.5) | 13.1, 0.080 |
Current heavy alcohol use | 49 (15.2) | 34 (21.3) | 37.01, <0.001 |
Regular physical activity | 189 (58.3) | 61 (38.5) | 52.4, 0.035 |
Diet quality (HEI-2015 score, 0–100, mean ± SE) | 52.5 (5.6) | 47.3 (7.5) | 56.1, 0.038 |
Model | AUC | Accuracy | Precision | Sensitivity (Recall) | Specificity | F1 Score |
---|---|---|---|---|---|---|
Training Dataset (mean, 95% CI) | ||||||
LR | 0.7918 (0.69–0.83) | 0.7192 (0.61–0.74) | 0.7214 (0.67–0.74) | 0.8978 (0.87–0.90) | 0.4197 (0.39–0.53) | 0.8111 (0.78–0.83) |
SVM | 0.7994 (0.76–0.82) | 0.7112 (0.68–0.75) | 0.7753 (0.75–0.78) | 0.7585 (0.73–0.77) | 0.6321 (0.61–0.65) | 0.7668 (0.71–0.79) |
Decision Tree | 0.9738 (0.66–0.97) | 0.9089 (0.66–0.93) | 0.9340 (0.71–0.97) | 0.9195 (0.76–0.92) | 0.8912 (0.79–0.95) | 0.9267 (0.74–0.97) |
RF | 0.9842 (0.78–0.99) | 0.9341 (0.74–0.98) | 0.9213 (0.77–0.95) | 0.9783 (0.84–0.99) | 0.8601 (0.57–0.89) | 0.9489 (0.80–0.98) |
GBM | 0.8952 (0.81–0.93) | 0.7907 (0.75–0.86) | 0.7867 (0.76–0.89) | 0.9133 (0.87–0.97) | 0.5855 (0.54–0.65) | 0.8453 (0.81–0.87) |
XGBoost | 0.8929 (0.75–0.92) | 0.7755 (0.73–0.87) | 0.9195 (0.75–0.97) | 0.5544 (0.52–0.84) | 0.5544 (0.52–0.65) | 0.8414 (0.80–0.88) |
Test Dataset (mean, 95% CI) | ||||||
LR | 0.7904 (0.69–0.83) | 0.7287 (0.68–0.75) | 0.7447 (0.72–0.77) | 0.8642 (0.84–0.90) | 0.5312 (0.42–0.56) | 0.8012 (0.71–0.86) |
SVM | 0.7774 (0.76–0.80) | 0.7054 (0.62–0.72) | 0.7609 (0.72–0.79) | 0.7407 (0.71–0.86) | 0.6458 (0.61–0.68) | 0.7595 (0.74–0.79) |
Decision Tree | 0.6480 (0.61–0.77) | 0.6512 (0.63–0.70) | 0.7093 (0.65–0.83) | 0.7531 (0.71–0.79) | 0.4792 (0.44–0.53) | 0.7305 (0.64–0.82) |
RF | 0.7760 (0.68–0.86) | 0.7364 (0.64–0.83) | 0.7640 (0.71–0.82) | 0.8395 (0.74–0.92) | 0.7425 (0.67–0.82) | 0.8000 (0.72–0.88) |
GBM | 0.8035 (0.71–0.89) | 0.7442 (0.71–0.79) | 0.7792 (0.75–0.82) | 0.8642 (0.82–0.91) | 0.7626 (0.68–0.81) | 0.8092 (0.68–0.92) |
XGBoost | 0.7834 (0.75–0.81) | 0.7287 (0.62–0.77) | 0.7500 (0.71–0.79) | 0.8519 (0.76–0.94) | 0.5208 (0.42–0.55) | 0.7977 (0.76–0.84) |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Han, C.J.; Ning, X.; Burd, C.E.; Tounkara, F.; Kalady, M.F.; Noonan, A.M.; Von Ah, D. A Machine Learning Classification Model for Gastrointestinal Health in Cancer Survivors: Roles of Telomere Length and Social Determinants of Health. Int. J. Environ. Res. Public Health 2024, 21, 1694. https://doi.org/10.3390/ijerph21121694
Han CJ, Ning X, Burd CE, Tounkara F, Kalady MF, Noonan AM, Von Ah D. A Machine Learning Classification Model for Gastrointestinal Health in Cancer Survivors: Roles of Telomere Length and Social Determinants of Health. International Journal of Environmental Research and Public Health. 2024; 21(12):1694. https://doi.org/10.3390/ijerph21121694
Chicago/Turabian StyleHan, Claire J., Xia Ning, Christin E. Burd, Fode Tounkara, Matthew F. Kalady, Anne M. Noonan, and Diane Von Ah. 2024. "A Machine Learning Classification Model for Gastrointestinal Health in Cancer Survivors: Roles of Telomere Length and Social Determinants of Health" International Journal of Environmental Research and Public Health 21, no. 12: 1694. https://doi.org/10.3390/ijerph21121694
APA StyleHan, C. J., Ning, X., Burd, C. E., Tounkara, F., Kalady, M. F., Noonan, A. M., & Von Ah, D. (2024). A Machine Learning Classification Model for Gastrointestinal Health in Cancer Survivors: Roles of Telomere Length and Social Determinants of Health. International Journal of Environmental Research and Public Health, 21(12), 1694. https://doi.org/10.3390/ijerph21121694