Abstract
BACKGROUND CONTEXT
Metastatic spinal disease is an advanced stage of cancer patients and often suffer
from terrible psychological health status; however, the ability to estimate the risk
probability of this adverse outcome using current available data is very limited.
PURPOSE
The goal of this study was to propose a precise model based on machine learning techniques
to predict psychological status among cancer patients with spinal metastatic disease.
STUDY DESIGN/SETTING
A prospective cohort study.
PATIENT SAMPLE
A total of 1043 cancer patients with spinal metastatic disease were included.
OUTCOME MEASURES
The main outcome was severe psychological distress.
METHODS
The total of patients was randomly divided into a training dataset and a testing dataset
on a ratio of 9:1. Patient's demographics, lifestyle choices, cancer-related features,
clinical manifestations, and treatments were collected as potential model predictors
in the study. Five machine learning algorithms, including XGBoosting machine, random
forest, gradient boosting machine, support vector machine, and ensemble prediction
model, as well as a logistic regression model were employed to train and optimize
models in the training set, and their predictive performance was assessed in the testing
set.
RESULTS
Up to 21.48% of all patients who were recruited had severe psychological distress.
Elderly patients (p<0.001), female (p =0.045), current smoking (p=0.002) or drinking
(p=0.003), a lower level of education (p<0.001), a stronger spiritual desire (p<0.001),
visceral metastasis (p=0.005), and a higher Eastern Cooperative Oncology Group (ECOG)
score (p<0.001) were significantly associated with worse psychological health. With
an area under the curve (AUC) of 0.865 (95% CI: 0.788–0.941) and an accuracy of up
to 0.843, the gradient boosting machine algorithm performed best in the prediction
of the outcome, followed by the XGBooting machine algorithm (AUC: 0.851, 95% CI: 0.768–0.934;
Accuracy: 0.826) and ensemble prediction (AUC: 0.851, 95% CI: 0.770–0.932; Accuracy:
0.809) in the testing set. In contrast, the AUC of the logistic regression model was
only 0.836 (95% CI: 0.756–0.916; Accuracy: 0.783).
CONCLUSIONS
Machine learning models have greater predictive power and can offer useful tools to
identify individuals with spinal metastatic disease who are experiencing severe psychological
distress.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to The Spine JournalAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Incidence, associated factors, and survival in metastatic spinal cord compression secondary to lung cancer.Spine J. 2015; 15: 1263-1269
- Surgical treatment of metastatic spine disease: an update on national trends and clinical outcomes from 2010 to 2014.Spine J. 2020; 20: 915-924
- Addressing distress management challenges: recommendations from the consensus panel of the American Psychosocial Oncology Society and the Association of Oncology Social Work.CA Cancer J Clin. 2021; 71: 407-436
- Disability, psychological distress and quality of life in relation to cancer diagnosis and cancer type: population-based Australian study of 22,505 cancer survivors and 244,000 people without cancer.BMC Med. 2020; 18: 372
- Anxiety, depression, and end-of-life care utilization in adults with metastatic cancer.Psychooncology. 2021; 30: 1876-1883
- High anxiety and depression scores and mental health service use among South Asian advanced cancer patients: a multi-country study.J Pain Symptom Manage. 2021; 62: 997-1007
- The global prevalence of common mental disorders: a systematic review and meta-analysis 1980-2013.Int J Epidemiol. 2014; 43: 476-493
- Quality of life and mental health status among cancer patients with metastatic spinal disease.Front Public Health. 2022; 10916004
- Most efficient questionnaires to measure quality of life, physical function, and pain in patients with metastatic spine disease: a cross-sectional prospective survey study.Spine J. 2017; 17: 953-961
- Quality of life in “chronic” cancer survivors: a meta-analysis.J Cancer Surviv. 2020; 14: 504-517
- Epidemiology and national trends in prevalence and surgical management of metastatic spinal disease.J Clin Neurosci. 2018; 53: 183-187
- Depression and anxiety in relation to cancer incidence and mortality: a systematic review and meta-analysis of cohort studies.Mol Psychiatry. 2020; 25: 1487-1499
- Cumulative burden of psychiatric disorders and self-harm across 26 adult cancers.Nat Med. 2022; 28: 860-870
- How does stress affect you? An overview of stress, immunity, depression and disease.Epidemiol Psichiatr Soc. 2001; 10: 153-162
- The impact of chronic conditions on the economic burden of cancer survivorship: a systematic review.Expert Rev Pharmacoecon Outcomes Res. 2016; 16: 579-589
- Psychological distress and access to mental health services among cancer survivors: a national health interview survey analysis.J Gen Intern Med. 2021; 36: 3243-3245
- Distress management, Version 3.2019, NCCN clinical practice guidelines in oncology.J Natl Compr Canc Netw. 2019; 17: 1229-1249
- A guide to machine learning for biologists.Nat Rev Mol Cell Biol. 2022; 23: 40-55
- eDoctor: machine learning and the future of medicine.J Intern Med. 2018; 284: 603-619
- Machine learning and deep learning in medical imaging: intelligent imaging.J Med Imaging Radiat Sci. 2019; 50: 477-487
- Machine learning in medicine.Circulation. 2015; 132: 1920-1930
- Hospital anxiety and depression scale (HADS) accuracy in cancer patients.Support Care Cancer. 2020; 28: 3921-3926
- Gradient boosting machines, a tutorial.Front Neurorobot. 2013; 7: 21
- XGBoost: an optimal machine learning model with just structural features to discover MOF adsorbents of Xe/Kr.Acs Omega. 2021; 6: 9066-9076
- Characterising risk of in-hospital mortality following cardiac arrest using machine learning: a retrospective international registry study.PLoS Med. 2018; 15e1002709
Molnar C. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. 2nd ed. 2022. christophm.github.io/interpretable-ml-book/.
- Local interpretable model-agnostic explanations for classification of lymph node metastases.Sensors (Basel). 2019; 19: 2969
- Differences in health care resource utilization after surgery for metastatic spinal column tumors in patients with a concurrent affective disorder in the United States.World Neurosurg. 2022; 161: e252-e267
- Quality of life, anxiety, depression, and distress in patients with advanced and metastatic lung cancer.Palliat Support Care. 2022; : 1-8https://doi.org/10.1017/S147895152200116X
- Depression, anxiety, and performance status among the women with metastatic breast cancer receiving palliative care in Bangladesh: a cross sectional study.Health Sci Rep. 2022; 5: e911
- A nomogram for predicting depression in patients with hepatocellular carcinoma: an observational cross-sectional study.Int J Psychiatry Clin Pract. 2019; 23: 273-280
- Development and internal validation of a predictive risk model for anxiety after completion of treatment for early stage breast cancer.J Patient Rep Outcomes. 2020; 4: 103
- Development and validation of a model for predicting the risk of suicide in patients with cancer.Arch Suicide Res. 2022; : 1-16
- Updated external validation of the SORG machine learning algorithms for prediction of ninety-day and one-year mortality after surgery for spinal metastasis.Spine J. 2021; 21: 1679-1686
- Development and external validation of predictive algorithms for six-week mortality in spinal metastasis using 4,304 patients from five institutions.Spine J. 2022; 22: 2033-2041
- A novel nomogram to stratify quality of life among advanced cancer patients with spinal metastatic disease after examining demographics, dietary habits, therapeutic interventions, and mental health status.BMC Cancer. 2022; 22: 1205
- Prevalence of mental disorders and psychosocial distress in German adolescent and young adult cancer patients (AYA).Psychooncology. 2018; 27: 1802-1809
- Anxiety and depression after cancer diagnosis: prevalence rates by cancer type, gender, and age.J Affect Disord. 2012; 141: 343-351
- Depression and anxiety in long-term survivors 5 and 10 years after cancer diagnosis.Support Care Cancer. 2020; 28: 211-220
- Alcohol consumption, depression, insomnia and colorectal cancer screening: racial differences.Int J High Risk Behav Addict. 2015; 4: e23424
- Factors influencing psychological wellbeing of early breast cancer patients.Rep Pract Oncol Radiother. 2020; 25: 913-918
- Emotional problems, quality of life, and symptom burden in patients with lung cancer.Clin Lung Cancer. 2017; 18: 497-503
- The relationship between age, anxiety, and depression in older adults with cancer.Psychooncology. 2015; 24: 712-717
- Associations between breast cancer survivorship and adverse mental health outcomes: a matched population-based cohort study in the United Kingdom.PLoS Med. 2021; 18e1003504
- Clinically applicable deep learning for diagnosis and referral in retinal disease.Nat Med. 2018; 24: 1342-1350
- The NCCN guideline for distress management: a case for making distress the sixth vital sign.J Natl Compr Canc Netw. 2007; 5: 3-7
- Yoga for improving health-related quality of life, mental health and cancer-related symptoms in women diagnosed with breast cancer.Cochrane Database Syst Rev. 2017; 1CD010802
- Dance/movement therapy for improving psychological and physical outcomes in cancer patients.Cochrane Database Syst Rev. 2015; 1CD007103
- Effects of a home-based exercise program on anxiety and mood disturbances in older adults with cancer receiving chemotherapy.J Am Geriatr Soc. 2019; 67: 1005-1011
Article info
Publication history
Published online: May 11, 2023
Publication stage
In Press Journal Pre-ProofFootnotes
FDA device/drug status: Not applicable.
Author disclosures: LG: Nothing to disclose. YC: Nothing to disclose. XC: Nothing to disclose. XS: Nothing to disclose. ML: Nothing to disclose. XS: Nothing to disclose. YL: Nothing to disclose.
Identification
Copyright
© 2023 Elsevier Inc. All rights reserved.
