Development and validation of an interpretable machine learning model for predicting the risk of hepatocellular carcinoma in patients with chronic hepatitis B: a case-control study.

The aim of this study was to develop and internally validate an interpretable machine learning (ML) model for predicting the risk of hepatocellular carcinoma (HCC) in patients with chronic hepatitis B (CHB) infection. We retrospectively collected clinical data from patients with HCC and CHB treated at the Fourth Affiliated Hospital of Guangxi Medical University from January 2022 to December 2022, including demographics, comorbidities, and laboratory parameters. The datasets were randomly divided into a training set (361 cases) and a validation set (155 cases) in a 7:3 ratio. Variables were screened using Least Absolute Shrinkage and Selection Operator (LASSO) and multifactor logistic regression. The prediction model of HCC risk in CHB patients was constructed based on five machine learning models, including logistic regression (LR), K-nearest neighbour (KNN), support vector machine (SVM), random forest (RF) and artificial neural network (ANN). Receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the model in terms of identification, calibration and clinical application. The SHapley Additive exPlanation (SHAP) method was used to rank the importance of the features and explain the final model. Among the five ML models constructed, the RF model has the best performance, and the RF model predicts the risk of HCC in patients with CHB in the training set [AUC: 0.996, 95% confidence interval (CI) (0.991-0.999)] and internal validation set [AUC: 0.993, 95% CI (0.986-1.000)]. It has high AUC, specificity, sensitivity, F1 score and low Brier score. Calibration showed good agreement between observed and predicted risks. The model yielded higher positive net benefits in DCA than when all participants were considered to be at high or low risk, indicating good clinical utility. In addition, the SHAP plot of the RF showed that age, basophil/lymphocyte ratio (BLR), D-Dimer, aspartate aminotransferase/alanine aminotransferase (AST/ALT), γ-glutamyltransferase (GGT) and alpha-fetoprotein (AFP) can help identify patients with CHB who are at high or low risk of developing HCC. ML models can be used as a tool to predict the risk of HCC in patients with CHB. The RF model has the best predictive performance and helps clinicians to identify high-risk patients and intervene early to reduce or delay the occurrence of HCC. However, the model needs to be further improved through large sample studies.

Wu L ，Liu Z ，Huang H ，Pan D ，Fu C ，Lu Y ，Zhou M ，Huang K ，Huang T ，Yang L ... -  《BMC GASTROENTEROLOGY》

Construction of a random survival forest model based on a machine learning algorithm to predict early recurrence after hepatectomy for adult hepatocellular carcinoma.

Zhang J ，Chen Q ，Zhang Y ，Zhou J ... -  《BMC CANCER》

Comparison of Two Modern Survival Prediction Tools, SORG-MLA and METSSS, in Patients With Symptomatic Long-bone Metastases Who Underwent Local Treatment With Surgery Followed by Radiotherapy and With Radiotherapy Alone.

Survival estimation for patients with symptomatic skeletal metastases ideally should be made before a type of local treatment has already been determined. Currently available survival prediction tools, however, were generated using data from patients treated either operatively or with local radiation alone, raising concerns about whether they would generalize well to all patients presenting for assessment. The Skeletal Oncology Research Group machine-learning algorithm (SORG-MLA), trained with institution-based data of surgically treated patients, and the Metastases location, Elderly, Tumor primary, Sex, Sickness/comorbidity, and Site of radiotherapy model (METSSS), trained with registry-based data of patients treated with radiotherapy alone, are two of the most recently developed survival prediction models, but they have not been tested on patients whose local treatment strategy is not yet decided. (1) Which of these two survival prediction models performed better in a mixed cohort made up both of patients who received local treatment with surgery followed by radiotherapy and who had radiation alone for symptomatic bone metastases? (2) Which model performed better among patients whose local treatment consisted of only palliative radiotherapy? (3) Are laboratory values used by SORG-MLA, which are not included in METSSS, independently associated with survival after controlling for predictions made by METSSS? Between 2010 and 2018, we provided local treatment for 2113 adult patients with skeletal metastases in the extremities at an urban tertiary referral academic medical center using one of two strategies: (1) surgery followed by postoperative radiotherapy or (2) palliative radiotherapy alone. Every patient's survivorship status was ascertained either by their medical records or the national death registry from the Taiwanese National Health Insurance Administration. After applying a priori designated exclusion criteria, 91% (1920) were analyzed here. Among them, 48% (920) of the patients were female, and the median (IQR) age was 62 years (53 to 70 years). Lung was the most common primary tumor site (41% [782]), and 59% (1128) of patients had other skeletal metastases in addition to the treated lesion(s). In general, the indications for surgery were the presence of a complete pathologic fracture or an impending pathologic fracture, defined as having a Mirels score of ≥ 9, in patients with an American Society of Anesthesiologists (ASA) classification of less than or equal to IV and who were considered fit for surgery. The indications for radiotherapy were relief of pain, local tumor control, prevention of skeletal-related events, and any combination of the above. In all, 84% (1610) of the patients received palliative radiotherapy alone as local treatment for the target lesion(s), and 16% (310) underwent surgery followed by postoperative radiotherapy. Neither METSSS nor SORG-MLA was used at the point of care to aid clinical decision-making during the treatment period. Survival was retrospectively estimated by these two models to test their potential for providing survival probabilities. We first compared SORG to METSSS in the entire population. Then, we repeated the comparison in patients who received local treatment with palliative radiation alone. We assessed model performance by area under the receiver operating characteristic curve (AUROC), calibration analysis, Brier score, and decision curve analysis (DCA). The AUROC measures discrimination, which is the ability to distinguish patients with the event of interest (such as death at a particular time point) from those without. AUROC typically ranges from 0.5 to 1.0, with 0.5 indicating random guessing and 1.0 a perfect prediction, and in general, an AUROC of ≥ 0.7 indicates adequate discrimination for clinical use. Calibration refers to the agreement between the predicted outcomes (in this case, survival probabilities) and the actual outcomes, with a perfect calibration curve having an intercept of 0 and a slope of 1. A positive intercept indicates that the actual survival is generally underestimated by the prediction model, and a negative intercept suggests the opposite (overestimation). When comparing models, an intercept closer to 0 typically indicates better calibration. Calibration can also be summarized as log(O:E), the logarithm scale of the ratio of observed (O) to expected (E) survivors. A log(O:E) > 0 signals an underestimation (the observed survival is greater than the predicted survival); and a log(O:E) < 0 indicates the opposite (the observed survival is lower than the predicted survival). A model with a log(O:E) closer to 0 is generally considered better calibrated. The Brier score is the mean squared difference between the model predictions and the observed outcomes, and it ranges from 0 (best prediction) to 1 (worst prediction). The Brier score captures both discrimination and calibration, and it is considered a measure of overall model performance. In Brier score analysis, the "null model" assigns a predicted probability equal to the prevalence of the outcome and represents a model that adds no new information. A prediction model should achieve a Brier score at least lower than the null-model Brier score to be considered as useful. The DCA was developed as a method to determine whether using a model to inform treatment decisions would do more good than harm. It plots the net benefit of making decisions based on the model's predictions across all possible risk thresholds (or cost-to-benefit ratios) in relation to the two default strategies of treating all or no patients. The care provider can decide on an acceptable risk threshold for the proposed treatment in an individual and assess the corresponding net benefit to determine whether consulting with the model is superior to adopting the default strategies. Finally, we examined whether laboratory data, which were not included in the METSSS model, would have been independently associated with survival after controlling for the METSSS model's predictions by using the multivariable logistic and Cox proportional hazards regression analyses. Between the two models, only SORG-MLA achieved adequate discrimination (an AUROC of > 0.7) in the entire cohort (of patients treated operatively or with radiation alone) and in the subgroup of patients treated with palliative radiotherapy alone. SORG-MLA outperformed METSSS by a wide margin on discrimination, calibration, and Brier score analyses in not only the entire cohort but also the subgroup of patients whose local treatment consisted of radiotherapy alone. In both the entire cohort and the subgroup, DCA demonstrated that SORG-MLA provided more net benefit compared with the two default strategies (of treating all or no patients) and compared with METSSS when risk thresholds ranged from 0.2 to 0.9 at both 90 days and 1 year, indicating that using SORG-MLA as a decision-making aid was beneficial when a patient's individualized risk threshold for opting for treatment was 0.2 to 0.9. Higher albumin, lower alkaline phosphatase, lower calcium, higher hemoglobin, lower international normalized ratio, higher lymphocytes, lower neutrophils, lower neutrophil-to-lymphocyte ratio, lower platelet-to-lymphocyte ratio, higher sodium, and lower white blood cells were independently associated with better 1-year and overall survival after adjusting for the predictions made by METSSS. Based on these discoveries, clinicians might choose to consult SORG-MLA instead of METSSS for survival estimation in patients with long-bone metastases presenting for evaluation of local treatment. Basing a treatment decision on the predictions of SORG-MLA could be beneficial when a patient's individualized risk threshold for opting to undergo a particular treatment strategy ranged from 0.2 to 0.9. Future studies might investigate relevant laboratory items when constructing or refining a survival estimation model because these data demonstrated prognostic value independent of the predictions of the METSSS model, and future studies might also seek to keep these models up to date using data from diverse, contemporary patients undergoing both modern operative and nonoperative treatments. Level III, diagnostic study.

Lee CC ，Chen CW ，Yen HK ，Lin YP ，Lai CY ，Wang JL ，Groot OQ ，Janssen SJ ，Schwab JH ，Hsu FM ，Lin WH ... -  《-》

Development of a machine learning model related to explore the association between heavy metal exposure and alveolar bone loss among US adults utilizing SHAP: a study based on NHANES 2015-2018.

Alveolar bone loss (ABL) is common in modern society. Heavy metal exposure is usually considered to be a risk factor for ABL. Some studies revealed a positive trend found between urinary heavy metals and periodontitis using multiple logistic regression and Bayesian kernel machine regression. Overfitting using kernel function, long calculation period, the definition of prior distribution and lack of rank of heavy metal will affect the performance of the statistical model. Optimal model on this topic still remains controversy. This study aimed: (1) to develop an algorithm for exploring the association between heavy metal exposure and ABL; (2) filter the actual causal variables and investigate how heavy metals were associated with ABL; and (3) identify the potential risk factors for ABL. Data were collected from National Health and Nutrition Examination Survey (NHANES) between 2015 and 2018 to develop a machine learning (ML) model. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression with 10-fold cross-validation. The selected data were balanced using the Synthetic Minority Oversampling Technique (SMOTE) and divided into a training set and testing set at a 3:1 ratio. Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Decision Tree (DT), and XGboost were used to construct the ML model. Accuracy, Area Under the Receiver Operating Characteristic Curve (AUC), Precision, Recall, and F1 score were used to select the optimal model for further analysis. The contribution of the variables to the ML model was explained using the Shapley Additive Explanations (SHAP) method. RF showed the best performance in exploring the association between heavy metal exposure and ABL, with an AUC (0.88), accuracy (0.78), precision (0.76), recall (0.83), and F1 score (0.79). Age was the most important factor in the ML model (mean| SHAP value| = 0.09), and Cd was the primary contributor. Sex had little effect on the ML model contribution. In this study, RF showed superior performance compared with the other five algorithms. Among the 12 heavy metals, Cd was the most important factor in the ML model. The relationship of Co & Pb and ABL are weaker than that of Cd. Among all the independent variables, age was considered the most important factor for this model. As for PIR, low-income participants present association with ABL. Mexican American and Non-Hispanic White show low association with ABL compared to Non-Hispanic Black and other races. Gender feature demonstrates a weak association with ABL. In the future, more advanced algorithms should be developed to validate these results and related parameters can be tuned to improve the accuracy of the model. not applicable.

Chen J 《BMC PUBLIC HEALTH》

Does the Presence of Missing Data Affect the Performance of the SORG Machine-learning Algorithm for Patients With Spinal Metastasis? Development of an Internet Application Algorithm.

The Skeletal Oncology Research Group machine-learning algorithm (SORG-MLA) was developed to predict the survival of patients with spinal metastasis. The algorithm was successfully tested in five international institutions using 1101 patients from different continents. The incorporation of 18 prognostic factors strengthens its predictive ability but limits its clinical utility because some prognostic factors might not be clinically available when a clinician wishes to make a prediction. We performed this study to (1) evaluate the SORG-MLA's performance with data and (2) develop an internet-based application to impute the missing data. A total of 2768 patients were included in this study. The data of 617 patients who were treated surgically were intentionally erased, and the data of the other 2151 patients who were treated with radiotherapy and medical treatment were used to impute the artificially missing data. Compared with those who were treated nonsurgically, patients undergoing surgery were younger (median 59 years [IQR 51 to 67 years] versus median 62 years [IQR 53 to 71 years]) and had a higher proportion of patients with at least three spinal metastatic levels (77% [474 of 617] versus 72% [1547 of 2151]), more neurologic deficit (normal American Spinal Injury Association [E] 68% [301 of 443] versus 79% [1227 of 1561]), higher BMI (23 kg/m 2 [IQR 20 to 25 kg/m 2 ] versus 22 kg/m 2 [IQR 20 to 25 kg/m 2 ]), higher platelet count (240 × 10 3 /µL [IQR 173 to 327 × 10 3 /µL] versus 227 × 10 3 /µL [IQR 165 to 302 × 10 3 /µL], higher lymphocyte count (15 × 10 3 /µL [IQR 9 to 21× 10 3 /µL] versus 14 × 10 3 /µL [IQR 8 to 21 × 10 3 /µL]), lower serum creatinine level (0.7 mg/dL [IQR 0.6 to 0.9 mg/dL] versus 0.8 mg/dL [IQR 0.6 to 1.0 mg/dL]), less previous systemic therapy (19% [115 of 617] versus 24% [526 of 2151]), fewer Charlson comorbidities other than cancer (28% [170 of 617] versus 36% [770 of 2151]), and longer median survival. The two patient groups did not differ in other regards. These findings aligned with our institutional philosophy of selecting patients for surgical intervention based on their level of favorable prognostic factors such as BMI or lymphocyte counts and lower levels of unfavorable prognostic factors such as white blood cell counts or serum creatinine level, as well as the degree of spinal instability and severity of neurologic deficits. This approach aims to identify patients with better survival outcomes and prioritize their surgical intervention accordingly. Seven factors (serum albumin and alkaline phosphatase levels, international normalized ratio, lymphocyte and neutrophil counts, and the presence of visceral or brain metastases) were considered possible missing items based on five previous validation studies and clinical experience. Artificially missing data were imputed using the missForest imputation technique, which was previously applied and successfully tested to fit the SORG-MLA in validation studies. Discrimination, calibration, overall performance, and decision curve analysis were applied to evaluate the SORG-MLA's performance. The discrimination ability was measured with an area under the receiver operating characteristic curve. It ranges from 0.5 to 1.0, with 0.5 indicating the worst discrimination and 1.0 indicating perfect discrimination. An area under the curve of 0.7 is considered clinically acceptable discrimination. Calibration refers to the agreement between the predicted outcomes and actual outcomes. An ideal calibration model will yield predicted survival rates that are congruent with the observed survival rates. The Brier score measures the squared difference between the actual outcome and predicted probability, which captures calibration and discrimination ability simultaneously. A Brier score of 0 indicates perfect prediction, whereas a Brier score of 1 indicates the poorest prediction. A decision curve analysis was performed for the 6-week, 90-day, and 1-year prediction models to evaluate their net benefit across different threshold probabilities. Using the results from our analysis, we developed an internet-based application that facilitates real-time data imputation for clinical decision-making at the point of care. This tool allows healthcare professionals to efficiently and effectively address missing data, ensuring that patient care remains optimal at all times. Generally, the SORG-MLA demonstrated good discriminatory ability, with areas under the curve greater than 0.7 in most cases, and good overall performance, with up to 25% improvement in Brier scores in the presence of one to three missing items. The only exceptions were albumin level and lymphocyte count, because the SORG-MLA's performance was reduced when these two items were missing, indicating that the SORG-MLA might be unreliable without these values. The model tended to underestimate the patient survival rate. As the number of missing items increased, the model's discriminatory ability was progressively impaired, and a marked underestimation of patient survival rates was observed. Specifically, when three items were missing, the number of actual survivors was up to 1.3 times greater than the number of expected survivors, while only 10% discrepancy was observed when only one item was missing. When either two or three items were omitted, the decision curves exhibited substantial overlap, indicating a lack of consistent disparities in performance. This finding suggests that the SORG-MLA consistently generates accurate predictions, regardless of the two or three items that are omitted. We developed an internet application ( https://sorg-spine-mets-missing-data-imputation.azurewebsites.net/ ) that allows the use of SORG-MLA with up to three missing items. The SORG-MLA generally performed well in the presence of one to three missing items, except for serum albumin level and lymphocyte count (which are essential for adequate predictions, even using our modified version of the SORG-MLA). We recommend that future studies should develop prediction models that allow for their use when there are missing data, or provide a means to impute those missing data, because some data are not available at the time a clinical decision must be made. The results suggested the algorithm could be helpful when a radiologic evaluation owing to a lengthy waiting period cannot be performed in time, especially in situations when an early operation could be beneficial. It could help orthopaedic surgeons to decide whether to intervene palliatively or extensively, even when the surgical indication is clear.

Huang CC ，Peng KP ，Hsieh HC ，Groot OQ ，Yen HK ，Tsai CC ，Karhade AV ，Lin YP ，Kao YT ，Yang JJ ，Dai SH ，Huang CC ，Chen CW ，Yen MH ，Xiao FR ，Lin WH ，Verlaan JJ ，Schwab JH ，Hsu FM ，Wong T ，Yang RS ，Yang SH ，Hu MH ... -  《-》