Background: Primary biliary cholangitis (PBC) is a rare autoimmune liver disease with few effective treatments and a poor prognosis, and its incidence is on the rise. There is an urgent need for more targeted treatment strategies to accurately identify high-risk patients. The use of stochastic survival forest models in machine learning is an innovative approach to constructing a prognostic model for PBC that can improve the prognosis by identifying high-risk patients for targeted treatment. Method: Based on the inclusion and exclusion criteria, the clinical data and follow-up data of patients diagnosed with PBC-associated cirrhosis between January 2011 and December 2021 at Taizhou Hospital of Zhejiang Province were retrospectively collected and analyzed. Data analyses and random survival forest model construction were based on the R language. Result: Through a Cox univariate regression analysis of 90 included samples and 46 variables, 17 variables with p-values <0.1 were selected for initial model construction. The out-of-bag (OOB) performance error was 0.2094, and K-fold cross-validation yielded an internal validation C-index of 0.8182. Through model selection, cholinesterase, bile acid, the white blood cell count, total bilirubin, and albumin were chosen for the final predictive model, with a final OOB performance error of 0.2002 and C-index of 0.7805. Using the final model, patients were stratified into high- and low-risk groups, which showed significant differences with a P value <0.0001. The area under the curve was used to evaluate the predictive ability for patients in the first, third, and fifth years, with respective results of 0.9595, 0.8898, and 0.9088. Conclusion: The present study constructed a prognostic model for PBC-associated cirrhosis patients using a random survival forest model, which accurately stratified patients into low- and high-risk groups. Treatment strategies can thus be more targeted, leading to improved outcomes for high-risk patients.

In biomedical research, spin is the overinterpretation of findings, and it is a growing concern. To date, the presence of spin has not been evaluated in prognostic model research in oncology, including studies developing and validating models for individualized risk prediction.

We conducted a systematic review, searching MEDLINE and EMBASE for oncology-related studies that developed and validated a prognostic model using machine learning published between 1st January, 2019, and 5th September, 2019. We used existing spin frameworks and described areas of highly suggestive spin practices.

We included 62 publications (including 152 developed models; 37 validated models). Reporting was inconsistent between methods and the results in 27% of studies due to additional analysis and selective reporting. Thirty-two studies (out of 36 applicable studies) reported comparisons between developed models in their discussion and predominantly used discrimination measures to support their claims (78%). Thirty-five studies (56%) used an overly strong or leading word in their title, abstract, results, discussion, or conclusion.

The potential for spin needs to be considered when reading, interpreting, and using studies that developed and validated prognostic models in oncology. Researchers should carefully report their prognostic model research using words that reflect their actual results and strength of evidence.

Cancer has received extensive recognition for its high mortality rate, with metastatic cancer being the top cause of cancer-related deaths. Metastatic cancer involves the spread of the primary tumor to other body organs. As much as the early detection of cancer is essential, the timely detection of metastasis, the identification of biomarkers, and treatment choice are valuable for improving the quality of life for metastatic cancer patients. This study reviews the existing studies on classical machine learning (ML) and deep learning (DL) in metastatic cancer research. Since the majority of metastatic cancer research data are collected in the formats of PET/CT and MRI image data, deep learning techniques are heavily involved. However, its black-box nature and expensive computational cost are notable concerns. Furthermore, existing models could be overestimated for their generality due to the non-diverse population in clinical trial datasets. Therefore, research gaps are itemized; follow-up studies should be carried out on metastatic cancer using machine learning and deep learning tools with data in a symmetric manner.

Describe and evaluate the methodological conduct of prognostic prediction models developed using machine learning methods in oncology.

We conducted a systematic review in MEDLINE and Embase between 01/01/2019 and 05/09/2019, for studies developing a prognostic prediction model using machine learning methods in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement, Prediction model Risk Of Bias ASsessment Tool (PROBAST) and CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) to assess the methodological conduct of included publications. Results were summarised by modelling type: regression-, non-regression-based and ensemble machine learning models.

Sixty-two publications met inclusion criteria developing 152 models across all publications. Forty-two models were regression-based, 71 were non-regression-based and 39 were ensemble models. A median of 647 individuals (IQR: 203 to 4059) and 195 events (IQR: 38 to 1269) were used for model development, and 553 individuals (IQR: 69 to 3069) and 50 events (IQR: 17.5 to 326.5) for model validation. A higher number of events per predictor was used for developing regression-based models (median: 8, IQR: 7.1 to 23.5), compared to alternative machine learning (median: 3.4, IQR: 1.1 to 19.1) and ensemble models (median: 1.7, IQR: 1.1 to 6). Sample size was rarely justified (n = 5/62; 8%). Some or all continuous predictors were categorised before modelling in 24 studies (39%). 46% (n = 24/62) of models reporting predictor selection before modelling used univariable analyses, and common method across all modelling types. Ten out of 24 models for time-to-event outcomes accounted for censoring (42%). A split sample approach was the most popular method for internal validation (n = 25/62, 40%). Calibration was reported in 11 studies. Less than half of models were reported or made available.

The methodological conduct of machine learning based clinical prediction models is poor. Guidance is urgently needed, with increased awareness and education of minimum prediction modelling standards. Particular focus is needed on sample size estimation, development and validation analysis methods, and ensuring the model is available for independent validation, to improve quality of machine learning based clinical prediction models.

The present study aimed to develop prognostic prediction models based on machine learning (ML) for non-metastatic colon cancer (CRC), which can provide a precise quantitative risk assessment and serve as an assistive method for treatment strategy development. The possibility of improving prediction accuracy using nonlinear methods compared to linear methods was investigated.

A cancer-specific survival (CSS) model constructed using logistic regression, extreme gradient boosting (XGBoost), and random forest algorithms was trained on the Surveillance, Epidemiology, and End Results datasets for 15,254 patients with non-metastatic CRC (split into training [70%] and internal validation [30%] datasets) and externally validated with an outpatient cohort of 311 cases from Xiyuan Hospital in China. A Chinese cohort was also used to develop recurrence and metastasis (R&M) models for CRC patients. The experiments for each model were performed 100 times to obtain average scores and 95% confidence intervals. The model performance was evaluated using the area under the receiver operating characteristic curve (AUC) values.

The XGBoost approach showed the highest AUC values of 0.86 (0.84-0.88), 0.82 (0.81-0.83), and 0.81 (0.79-0.82) for one-, three-, and five-year CSS cohorts, respectively, along with a relatively high generalization ability. The XGBoost approach also performed best for the R&M model, with the AUC values of 0.71 (0.64-0.79), 0.79 (0.74-0.86), and 0.89 (0.82-0.95) for one-, three-, and five-year R&M cohorts, respectively. The rankings of predictor importance for the CSS and R&M models were different, and the higher model accuracy was associated with more prognostic predictors.

Three different ML algorithms for developing prognostic prediction models for non-metastatic CRC were compared. The predictive performance results showed that the nonlinear XGBoost approach performed best, suggesting that it can be used for quantifying the prognostic risk. It was also demonstrated that the model performance can be improved when more prognostic predictors are considered.

Being able to predict a patient's life expectancy can help doctors and patients prioritize treatments and supportive care. For predicting life expectancy, physicians have been shown to outperform traditional models that use only a few predictor variables. It is possible that a machine learning model that uses many predictor variables and diverse data sources from the electronic medical record can improve on physicians' performance. For patients with metastatic cancer, we compared accuracy of life expectancy predictions by the treating physician, a machine learning model, and a traditional model.

A machine learning model was trained using 14 600 metastatic cancer patients' data to predict each patient's distribution of survival time. Data sources included note text, laboratory values, and vital signs. From 2015-2016, 899 patients receiving radiotherapy for metastatic cancer were enrolled in a study in which their radiation oncologist estimated life expectancy. Survival predictions were also made by the machine learning model and a traditional model using only performance status. Performance was assessed with area under the curve for 1-year survival and calibration plots.

The radiotherapy study included 1190 treatment courses in 899 patients. A total of 879 treatment courses in 685 patients were included in this analysis. Median overall survival was 11.7 months. Physicians, machine learning model, and traditional model had area under the curve for 1-year survival of 0.72 (95% CI 0.63-0.81), 0.77 (0.73-0.81), and 0.68 (0.65-0.71), respectively.

The machine learning model's predictions were more accurate than those of the treating physician or a traditional model.

Patients suffering from gastrointestinal cancer comprise a large group receiving home hospice care in China, however, little is known about the prediction of their survival time. This study aimed to develop a gastrointestinal cancer-specific non-lab nomogram predicting survival time in home-based hospice.

We retrospectively studied the patients with gastrointestinal cancer from a home-based hospice between 2008 and 2018. General baseline characteristics, disease-related characteristics, and related assessment scale scores were collected from the case records. The data were randomly split into a training set (75%) for developing a predictive nomogram and a testing set (25%) for validation. A non-lab nomogram predicting the 30-day and 60-day survival probability was created using the least absolute shrinkage and selection operator (LASSO) Cox regression. We evaluated the performance of our predictive model by means of the area under receiver operating characteristic curve (AUC) and calibration curve.

A total of 1618 patients were included and divided into two sets: 1214 patients (110 censored) as training dataset and 404 patients (33 censored) as testing dataset. The median survival time for overall included patients was 35 days (IQR, 17-66). The 5 most significant prognostic variables were identified to construct the nomogram among all 28 initial variables, including Karnofsky Performance Status (KPS), abdominal distention, edema, quality of life (QOL), and duration of pain. In training dataset validation, the AUC at 30 days and 60 days were 0.723 (95% CI, 0.694-0.753) and 0.733 (95% CI, 0.702-0.763), respectively. Similarly, the AUC value was 0.724 (0.673-0.774) at 30 days and 0.725 (0.672-0.778) at 60 days in the testing dataset validation. Further, the calibration curves revealed good agreement between the nomogram predictions and actual observations in both the training and testing dataset.

This non-lab nomogram may be a useful clinical tool. It needs prospective multicenter validation as well as testing with Chinese clinicians in charge of hospice patients with gastrointestinal cancer to assess acceptability and usability.

Patients with synchronous colon cancer metastases have highly variable overall survival (OS), making accurate predictive models challenging to build. We aim to use machine learning to more accurately predict OS in these patients and to present this predictive model in the form of nomograms for patients and clinicians.

Using the National Cancer Database (2010-2014), we identified right colon (RC) and left colon (LC) cancer patients with synchronous metastases. Each primary site was split into training and testing datasets. Nomograms predicting 3- year OS were created for each site using Cox proportional hazard regression with lasso regression. Each model was evaluated by both calibration (comparison of predicted vs observed OS) and validation (degree of concordance as measured by the c-index) methodologies.

A total of 11 018 RC and 8346 LC patients were used to construct and validate the nomograms. After stratifying each model into five risk groups, the predicted OS was within the 95% CI of the observed OS in four out of five risk groups for both the RC and LC models. Externally validated c-indexes at 3 years for the RC and LC models were 0.794 and 0.761, respectively.

Utilization of machine learning can result in more accurate predictive models for patients with metastatic colon cancer. Nomograms built from these models can assist clinicians and patients in the shared decision-making process of their cancer care.