Machine learning model for predicting excessive muscle loss during neoadjuvant chemoradiotherapy in oesophageal cancer

Yoon, Han Gyul; Oh, Dongryul; Noh, Jae Myoung; Cho, Won Kyung; Sun, Jong‐Mu; Kim, Hong Kwan; Zo, Jae Ill; Shim, Young Mog; Kim, Kyunga

doi:10.1002/jcsm.12747

Cited by 15 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data from all participants were included to establish the SFT normative values for different sexes and ages. Meanwhile, the participants were randomly divided into the construction and verification groups at a ratio of 7:3, which was used in a previous study ( Yoon et al, 2021 ). The construction group was used to develop the SFT integrated score, and the verification group was used for the validity test.…”

Section: Methodsmentioning

confidence: 99%

Normative values and integrated score of functional fitness among Chinese community-dwelling older adults in Suzhou

Chen

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

Objectives: This study was performed to establish the normative values and integrated score of the functional fitness on the basis of the senior fitness test (SFT) among Chinese community-dwelling older adults in Suzhou.Methods: In this cross-sectional descriptive study, 1,122 community-dwelling older adults aged 60 years old and above were recruited at Suzhou, China, by using a multistage stratified sampling method and accepted the SFT measurements. Sex- and age-specific normative values of each index of the SFT were established by using the percentile method. The SFT integrated score was established using factor analysis according to the data of 70% of the participants (construction group) and verified using the error rate from the data of the remaining 30% of the participants (verification group).Results: Normative-referenced percentile values at the 5th, 10th, 25th, 35th, 50th, 65th, 75th, 90th, and 95th percentiles for each index of SFT were established for the men and women among the different age groups. Five indices of the SFT, namely, 2-min step test, 30-s arm curl, 30-s chair stand, chair sit-and-reach, and 8-ft up-and-go (TUGT), gradually declined with age in both sexes (p < .05). The SFT integrated score was calculated as follows: F = 3.8 × 2-min step test + 3.8 × 30-s arm curl + 3.8 × 30-s chair stand + 2.2 × back starch + 2.6 × chair sit-and-reach + 4 × TUGT − .04 × BMI. The formula was verified using the error rate. The error rates of the verification group compared with the construction group in each grade score of SFT were lower than 5%.Conclusion: Based on the data from the community-dwelling older adults in Suzhou, China, the functional fitness normative values for each index of the SFT and the integrated score of SFT were established. The SFT integrated score formula was verified to be reasonable and effective.

show abstract

Section: Methodsmentioning

confidence: 99%

Normative values and integrated score of functional fitness among Chinese community-dwelling older adults in Suzhou

Chen

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…ML models for predicting CT-based muscle loss in patients with oesophageal cancer have been evaluated in a previous study. 9 An ensemble model of LR and SVM using only changes in BMI and laboratory data as inputs achieved an AUC of 0.808. In addition to these data, we included other clinical and disease-specific features to develop ML models, and the RF model achieved an AUC of 0.856 and F1 score of 0.726.…”

Section: Discussionmentioning

confidence: 99%

“…Changes in these features were selected for analysis because changes in BMI and systemic inflammation are dynamic and associated with muscle loss during treatment. 9 Using longitudinal data also provides more useful information than using values at a single timepoint in ovarian cancer. 6 The data for the included patients were complete because records with missing values were excluded, and the application of an imputation method was not required.…”

Section: Data Processingmentioning

confidence: 99%

“…[3][4][5][6] However, the utility of such measurements may be limited in clinical practice because the required process is labour-intensive and time-consuming. 9 To assess changes in muscle, pre-and post-treatment CT scans should be processed by specific software, and the muscle is manually or semi-automatically segmented on a cross-sectional image at L3 to calculate the area of skeletal muscle. The skeletal muscle index (SMI) is then calculated using the muscle area and patient height, and the changes in muscle mass are evaluated.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explainable machine learning model for predicting skeletal muscle loss during surgery and adjuvant chemotherapy in ovarian cancer

Hsu

Weng

et al. 2023

J cachexia sarcopenia muscle

View full text Add to dashboard Cite

BackgroundSkeletal muscle loss during treatment is associated with poor survival outcomes in patients with ovarian cancer. Although changes in muscle mass can be assessed on computed tomography (CT) scans, this labour‐intensive process can impair its utility in clinical practice. This study aimed to develop a machine learning (ML) model to predict muscle loss based on clinical data and to interpret the ML model by applying SHapley Additive exPlanations (SHAP) method.MethodsThis study included the data of 617 patients with ovarian cancer who underwent primary debulking surgery and platinum‐based chemotherapy at a tertiary centre between 2010 and 2019. The cohort data were split into training and test sets based on the treatment time. External validation was performed using 140 patients from a different tertiary centre. The skeletal muscle index (SMI) was measured from pre‐ and post‐treatment CT scans, and a decrease in SMI ≥ 5% was defined as muscle loss. We evaluated five ML models to predict muscle loss, and their performance was determined using the area under the receiver operating characteristic curve (AUC) and F1 score. The features for analysis included demographic and disease‐specific characteristics and relative changes in body mass index (BMI), albumin, neutrophil‐to‐lymphocyte ratio (NLR), and platelet‐to‐lymphocyte ratio (PLR). The SHAP method was applied to determine the importance of the features and interpret the ML models.ResultsThe median (inter‐quartile range) age of the cohort was 52 (46–59) years. After treatment, 204 patients (33.1%) experienced muscle loss in the training and test datasets, while 44 (31.4%) patients experienced muscle loss in the external validation dataset. Among the five evaluated ML models, the random forest model achieved the highest AUC (0.856, 95% confidence interval: 0.854–0.859) and F1 score (0.726, 95% confidence interval: 0.722–0.730). In the external validation, the random forest model outperformed all ML models with an AUC of 0.874 and an F1 score of 0.741. The results of the SHAP method showed that the albumin change, BMI change, malignant ascites, NLR change, and PLR change were the most important factors in muscle loss. At the patient level, SHAP force plots demonstrated insightful interpretation of our random forest model to predict muscle loss.ConclusionsExplainable ML model was developed using clinical data to identify patients experiencing muscle loss after treatment and provide information of feature contribution. Using the SHAP method, clinicians may better understand the contributors to muscle loss and target interventions to counteract muscle loss.

show abstract

“…al. used a logistic regression model and a supportive vector machine to predict excessive muscle loss during neoadjuvant radio-chemotherapy by analyzing patients' blood samples and body mass index [119]. Interestingly, ML may also be used to propose risk factors for anastomotic leakage after esophagectomy [120].…”

Section: Epidemiology Radiation Oncology and Blood Biomarkersmentioning

confidence: 99%

Machine Learning for Future Subtyping of the Tumor Microenvironment of Gastro-Esophageal Adenocarcinomas

Klein

Duda

2021

Cancers

View full text Add to dashboard Cite

Tumor progression involves an intricate interplay between malignant cells and their surrounding tumor microenvironment (TME) at specific sites. The TME is dynamic and is composed of stromal, parenchymal, and immune cells, which mediate cancer progression and therapy resistance. Evidence from preclinical and clinical studies revealed that TME targeting and reprogramming can be a promising approach to achieve anti-tumor effects in several cancers, including in GEA. Thus, it is of great interest to use modern technology to understand the relevant components of programming the TME. Here, we discuss the approach of machine learning, which recently gained increasing interest recently because of its ability to measure tumor parameters at the cellular level, reveal global features of relevance, and generate prognostic models. In this review, we discuss the relevant stromal composition of the TME in GEAs and discuss how they could be integrated. We also review the current progress in the application of machine learning in different medical disciplines that are relevant for the management and study of GEA.

show abstract

Machine learning model for predicting excessive muscle loss during neoadjuvant chemoradiotherapy in oesophageal cancer

Cited by 15 publications

References 41 publications

Normative values and integrated score of functional fitness among Chinese community-dwelling older adults in Suzhou

Normative values and integrated score of functional fitness among Chinese community-dwelling older adults in Suzhou

Explainable machine learning model for predicting skeletal muscle loss during surgery and adjuvant chemotherapy in ovarian cancer

Machine Learning for Future Subtyping of the Tumor Microenvironment of Gastro-Esophageal Adenocarcinomas

Contact Info

Product

Resources

About