Development and external validation of a machine learning-based prediction model for the cancer-related fatigue diagnostic screening in adult cancer patients: a cross-sectional study in China

Development and validation of machine learning models based on stacked generalization to predict psychosocial maladjustment in patients with acute myocardial infarction

BACKGROUND

Psychosocial maladjustment threatens the recovery of patients with acute myocardial infarction (AMI), and early identification of patients with psychosocial maladjustment may facilitate provision of reference to targeted interventions. The aims of this study were to: (1) identify key factors influencing patient psychosocial maladjustment, and (2) develop a machine learning predictive model based on Stacked Generalization.

METHODS

Young and middle-aged patients with AMI (n = 734) were recruited from two tertiary hospitals (Center I and Center II) in Guangdong Province. Sociodemographic Characteristics, Perceived Stress Scale, Fear of Progression Questionnaire-Short Form, and Social Support Rating Scale data were collected before discharge, and psychosocial adjustment assessed one month after discharge using the Psychosocial Adjustment to Illness Scale. Six machine learning methods were trained on Center I to analyze the collected data and build a predictive model. Stacked Generalization was adopted to ensemble the models and build a final predictive model. Key factors and their contributions to the model were determined using SHapley Additive exPlanations (SHAP).

RESULTS

One month after discharge, psychosocial maladjustment incidence rates in Centers I and II were 59.2% and 58.3%, respectively. Eight key predictors of psychosocial adjustment were selected: employment status, exercise habits, diabetes, number of vascular lesions, chest tightness or chest pain, perceived stress, fear of disease progression, and social support. In the internal validation, Support Vector Classification (SVC) performed better in terms of Brier score, sensitivity, and negative predictive value; Decision Tree (DT) performed better in calibration slope, specificity, and precision; while Random Forest (RF) performed better in terms of area under the curve (AUC), Youden, and accuracy values. An LDS-R model stacked by SVC, logistic regression, DT, and RF, achieved the best comprehensive performance and generalization error, with accuracy = 0.834, AUC = 0.909, precision = 0.855, and calibration slope = 1.066 in external validation, indicating that the model is robust and the most suitable for promotion. SHAP provided insights into the model's predictions.

CONCLUSION

The LDS-R model is a practical tool for identifying patients at high risk for psychosocial maladjustment before discharge. Our identification of significant factors influencing psychosocial maladjustment may inform future development of interventions.

Development and validation of machine learning models for predicting cancer-related fatigue in lymphoma survivors

BACKGROUND

New cases of lymphoma are rising, and the symptom burden, like cancer-related fatigue (CRF), severely impacts the quality of life of lymphoma survivors. However, clinical diagnosis and treatment of CRF are inadequate and require enhancement.

OBJECTIVE

The main objective of this study is to construct machine learning-based CRF prediction models for lymphoma survivors to help healthcare professionals accurately identify the CRF population and better personalize treatment and care for patients.

METHODS

A cross-sectional study in China recruited lymphoma patients from June 2023 to March 2024, dividing them into two datasets for model construction and external validation. Six machine learning algorithms were used in this study: Logistic Regression (LR), Random Forest, Single Hidden Layer Neural Network, Support Vector Machine, eXtreme Gradient Boosting, and Light Gradient Boosting Machine (LightGBM). Performance metrics like the area under the receiver operating characteristic (AUROC) and calibration curves were compared. The clinical applicability was assessed by decision curve, and Shapley additive explanations was employed to explain variable significance.

RESULTS

CRF incidence was 40.7 % (dataset I) and 44.8 % (dataset II). LightGBM showed strong performance in training and internal validation. LR excelled in external validation with the highest AUROC and best calibration. Pain, total protein, physical function, and sleep disturbance were important predictors of CRF.

CONCLUSION

The study presents a machine learning-based CRF prediction model for lymphoma patients, offering dynamic, data-driven assessments that could enhance the development of automated CRF screening tools for personalized management in clinical practice.

Machine Learning Approaches to Predict Symptoms in People With Cancer: Systematic Review

BACKGROUND

People with cancer frequently experience severe and distressing symptoms associated with cancer and its treatments. Predicting symptoms in patients with cancer continues to be a significant challenge for both clinicians and researchers. The rapid evolution of machine learning (ML) highlights the need for a current systematic review to improve cancer symptom prediction.

OBJECTIVE

This systematic review aims to synthesize the literature that has used ML algorithms to predict the development of cancer symptoms and to identify the predictors of these symptoms. This is essential for integrating new developments and identifying gaps in existing literature.

METHODS

We conducted this systematic review in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist. We conducted a systematic search of CINAHL, Embase, and PubMed for English records published from 1984 to August 11, 2023, using the following search terms: cancer, neoplasm, specific symptoms, neural networks, machine learning, specific algorithm names, and deep learning. All records that met the eligibility criteria were individually reviewed by 2 coauthors, and key findings were extracted and synthesized. We focused on studies using ML algorithms to predict cancer symptoms, excluding nonhuman research, technical reports, reviews, book chapters, conference proceedings, and inaccessible full texts.

RESULTS

A total of 42 studies were included, the majority of which were published after 2017. Most studies were conducted in North America (18/42, 43%) and Asia (16/42, 38%). The sample sizes in most studies (27/42, 64%) typically ranged from 100 to 1000 participants. The most prevalent category of algorithms was supervised ML, accounting for 39 (93%) of the 42 studies. Each of the methods-deep learning, ensemble classifiers, and unsupervised ML-constituted 3 (3%) of the 42 studies. The ML algorithms with the best performance were logistic regression (9/42, 17%), random forest (7/42, 13%), artificial neural networks (5/42, 9%), and decision trees (5/42, 9%). The most commonly included primary cancer sites were the head and neck (9/42, 22%) and breast (8/42, 19%), with 17 (41%) of the 42 studies not specifying the site. The most frequently studied symptoms were xerostomia (9/42, 14%), depression (8/42, 13%), pain (8/42, 13%), and fatigue (6/42, 10%). The significant predictors were age, gender, treatment type, treatment number, cancer site, cancer stage, chemotherapy, radiotherapy, chronic diseases, comorbidities, physical factors, and psychological factors.

CONCLUSIONS

This review outlines the algorithms used for predicting symptoms in individuals with cancer. Given the diversity of symptoms people with cancer experience, analytic approaches that can handle complex and nonlinear relationships are critical. This knowledge can pave the way for crafting algorithms tailored to a specific symptom. In addition, to improve prediction precision, future research should compare cutting-edge ML strategies such as deep learning and ensemble methods with traditional statistical models.

Cancer-related fatigue: Towards a more targeted approach based on classification by biomarkers and psychological factors

Cancer-related fatigue is a frequent, burdensome and often insufficiently treated symptom. A more targeted treatment of fatigue is urgently needed. Therefore, we examined biomarkers and clinical factors to identify fatigue subtypes with potentially different pathophysiologies. The study population comprised disease-free breast cancer survivors of a German population-based case-control study who were re-assessed on average 6 (FU1, n = 1871) and 11 years (FU2, n = 1295) after diagnosis. At FU1 and FU2, we assessed fatigue with the 20-item multidimensional Fatigue Assessment Questionnaire and further factors by structured telephone-interviews. Serum samples collected at FU1 were analyzed for IL-1ß, IL-2, IL-4, IL-6, IL-10, TNF-a, GM-CSF, IL-5, VEGF-A, SAA, CRP, VCAM-1, ICAM-1, leptin, adiponectin and resistin. Exploratory cluster analyses among survivors with fatigue at FU1 and no history of depression yielded three clusters (CL1, CL2 and CL3). CL1 (n = 195) on average had high levels of TNF-α, IL1-β, IL-6, resistin, VEGF-A and GM-CSF, and showed high BMI and pain levels. Fatigue in CL1 manifested rather in physical dimensions. Contrarily, CL2 (n = 78) was characterized by high leptin level and had highest cognitive fatigue. CL3 (n = 318) did not show any prominent characteristics. Fatigued survivors with a history of depression (n = 214) had significantly higher physical, emotional and cognitive fatigue and showed significantly less amelioration of fatigue from FU1 to FU2 than survivors without depression. In conclusion, from the broad phenotype "cancer-related fatigue" we were able to delineate subgroups characterized by biomarkers or history of depression. Future investigations may take these subtypes into account, ultimately enabling a better targeted therapy of fatigue.

Multidimensional Predictors of Cancer-Related Fatigue Based on the Predisposing, Precipitating, and Perpetuating (3P) Model: A Systematic Review

Cancer-related fatigue (CRF) is a widespread symptom with high prevalence in cancer patients, seriously affecting their quality of life. In the context of precision care, constructing machine learning-based prediction models for early screening and assessment of CRF is beneficial to this situation. To further understand the predictors of CRF for model construction, we conducted a comprehensive search in PubMed, Web of Science, Embase, and Scopus databases, combining CRF with predictor-related terms. A total of 27 papers met the inclusion criteria. We evaluated the above studies into three subgroups following the predisposing, precipitating, and perpetuating (3P) factor model. (1) Predisposing factors-baseline fatigue, demographic characteristics, clinical characteristics, psychosocial traits and physical symptoms. (2) Precipitating factors-type and stage of chemotherapy, inflammatory factors, laboratory indicators and metabolic changes. (3) Perpetuating factors-a low level of physical activity and poorer nutritional status. Future research should prioritize large-scale prospective studies with emerging technologies to identify accurate predictors of CRF. The assessment and management of CRF should also focus on the above factors, especially the controllable precipitating factors, to improve the quality of life of cancer survivors.

Characteristics and predictors associated with cancer-related fatigue among solid and liquid tumors

PURPOSE

Cancer-related fatigue (CRF) is a devastating complication with limited recognized clinical risk factors. We examined characteristics among solid and liquid cancers utilizing Machine learning (ML) approaches for predicting CRF.

METHODS

We utilized 2017 National Inpatient Sample database and employed generalized linear models to assess the association between CRF and the outcome of burden of illness among hospitalized solid and non-solid tumors patients. And further applied lasso, ridge and Random Forest (RF) for building our linear and non-linear ML models.

RESULTS

The 2017 database included 196,330 prostate (PCa), 66,385 leukemia (Leuk), 107,245 multiple myeloma (MM), and 41,185 cancers of lip, oral cavity and pharynx (CLOP) patients, and among them, there were 225, 140, 125 and 115 CRF patients, respectively. CRF was associated with a higher burden of illness among Leuk and MM, and higher mortality among PCa. For the PCa patients, both the test and the training data had best areas under the ROC curve [AUC = 0.91 (test) vs. 0.90 (train)] for both lasso and ridge ML. For the CLOP, this was 0.86 and 0.79 for ridge; 0.87 and 0.84 for lasso; 0.82 for both test and train for RF and for the Leuk cohort, 0.81 (test) and 0.76 (train) for both ridge and lasso.

CONCLUSION

This study provided an effective platform to assess potential risks and outcomes of CRF in patients hospitalized for the management of solid and non-solid tumors. Our study showed ML methods performed well in predicting the CRF among solid and liquid tumors.