Performance of prediction models on survival outcomes of colorectal cancer with surgical resection: A systematic review and meta-analysis

Clinical Prediction Models for Prognosis of Colorectal Liver Metastases: A Comprehensive Review of Regression-Based and Machine Learning Models

Colorectal liver metastasis (CRLM) is a disease entity that warrants special attention due to its high frequency and potential curability. Identification of "high-risk" patients is increasingly popular for risk stratification and personalization of the management pathway. Traditional regression-based methods have been used to derive prediction models for these patients, and lately, focus has shifted to artificial intelligence-based models, with employment of variable supervised and unsupervised techniques. Multiple endpoints, like overall survival (OS), disease-free survival (DFS) and development or recurrence of postoperative complications have all been used as outcomes in these studies. This review provides an extensive overview of available clinical prediction models focusing on the prognosis of CRLM and highlights the different predictor types incorporated in each model. An overview of the modelling strategies and the outcomes chosen is provided. Specific patient and treatment characteristics included in the models are discussed in detail. Model development and validation methods are presented and critically appraised, and model performance is assessed within a proposed framework.

Accounting for time dependency in meta-analyses of concordance probability estimates

Recent years have seen the development of many novel scoring tools for disease prognosis and prediction. To become accepted for use in clinical applications, these tools have to be validated on external data. In practice, validation is often hampered by logistical issues, resulting in multiple small-sized validation studies. It is therefore necessary to synthesize the results of these studies using techniques for meta-analysis. Here we consider strategies for meta analyzing the concordance probability for time-to-event data ("C-index"), which has become a popular tool to evaluate the discriminatory power of prediction models with a right-censored outcome. We show that standard meta-analysis of the C-index may lead to biased results, as the magnitude of the concordance probability depends on the length of the time interval used for evaluation (defined e.g., by the follow-up time, which might differ considerably between studies). To address this issue, we propose a set of methods for random-effects meta-regression that incorporate time directly as covariate in the model equation. In addition to analyzing nonlinear time trends via fractional polynomial, spline, and exponential decay models, we provide recommendations on suitable transformations of the C-index before meta-regression. Our results suggest that the C-index is best meta-analyzed using fractional polynomial meta-regression with logit-transformed C-index values. Classical random-effects meta-analysis (not considering time as covariate) is demonstrated to be a suitable alternative when follow-up times are small. Our findings have implications for the reporting of C-index values in future studies, which should include information on the length of the time interval underlying the calculations.

Prediction models for heart failure in the community: A systematic review and meta-analysis

AIMS

Multivariable prediction models can be used to estimate risk of incident heart failure (HF) in the general population. A systematic review and meta-analysis was performed to determine the performance of models.

METHODS AND RESULTS

From inception to 3 November 2022 MEDLINE and EMBASE databases were searched for studies of multivariable models derived, validated and/or augmented for HF prediction in community-based cohorts. Discrimination measures for models with c-statistic data from ≥3 cohorts were pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using PROBAST. We included 36 studies with 59 prediction models. In meta-analysis, the Atherosclerosis Risk in Communities (ARIC) risk score (summary c-statistic 0.802, 95% confidence interval [CI] 0.707-0.883), GRaph-based Attention Model (GRAM; 0.791, 95% CI 0.677-0.885), Pooled Cohort equations to Prevent Heart Failure (PCP-HF) white men model (0.820, 95% CI 0.792-0.843), PCP-HF white women model (0.852, 95% CI 0.804-0.895), and REverse Time AttentIoN model (RETAIN; 0.839, 95% CI 0.748-0.916) had a statistically significant 95% PI and excellent discrimination performance. The ARIC risk score and PCP-HF models had significant summary discrimination among cohorts with a uniform prediction window. 77% of model results were at high risk of bias, certainty of evidence was low, and no model had a clinical impact study.

CONCLUSIONS

Prediction models for estimating risk of incident HF in the community demonstrate excellent discrimination performance. Their usefulness remains uncertain due to high risk of bias, low certainty of evidence, and absence of clinical effectiveness research.

Nomogram Predicting the Prognosis of Patients with Surgically Resected Stage IA Non-small Cell Lung Cancer

The American Joint Committee on Cancer (AJCC) 8th stage system was limited in accuracy for predicting prognosis of stage IA non-small cell lung cancer (NSCLC) patients. This study aimed to establish and validate two nomograms that predict overall survival (OS) and lung cancer-specific survival (LCSS) in surgically resected stage IA NSCLC patients. Postoperative patients with stage IA NSCLC in SEER database between 2004 and 2015 were examined. Survival and clinical information according to the inclusion and exclusion criteria were collected. All patients were randomly divided into the training cohort and validation cohort with a ratio of 7:3. Independent prognosis factors were evaluated using univariate and multivariate Cox regression analyses, and predictive nomogram was established based on these factors. Nomogram performance was measured using the C-index, calibration plots, and DCA. Patients were grouped by quartiles of nomogram scores and survival curves were plotted by Kaplan-Meier analysis. In total, 33,533 patients were included in the study. The nomogram contained 12 prognostic factors in OS and 10 prognostic factors in LCSS. In the validation set, the C-index was 0.652 for predicting OS and 0.651 for predicting LCSS. The calibration curves for the nomogram-predicted probability of OS and LCSS showed good agreement between the actual observation and nomogram prediction. DCA indicated that the clinical value of the nomograms were higher than AJCC 8th stage for predicting OS and LCSS. Nomogram scores related risk stratification revealed statistically significant difference which have better discrimination than AJCC 8th stage. The nomogram can accurately predict OS and LCSS in surgically resected patients with stage IA NSCLC.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13193-022-01700-w.

Estimating postoperative mortality in colorectal surgery- a systematic review of risk prediction models

PURPOSE

Risk prediction models are frequently used to support decision-making in colorectal surgery but can be inaccurate. Machine learning (ML) is becoming increasingly popular, and its application may increase predictive accuracy. We compared conventional risk prediction models for postoperative mortality (based on regression analysis) with ML models to determine the benefit of the latter approach.

METHODS

The study was registered in PROSPERO(CRD42022364753). Following the PRISMA guidelines, a systematic search of three databases (MEDLINE, EMBASE, WoS) was conducted (from 1/1/2000 to 29/09/2022). Studies were included if they reported the development of a risk model to estimate short-term postoperative mortality for patients undergoing colorectal surgery. Discrimination and calibration performance metrics were compared. Studies were evaluated against CHARMS and TRIPOD criteria.

RESULTS

3,052 articles were screened, and 45 studies were included. The total sample size was 1,356,058 patients. Six studies used ML techniques for model development. Most studies (n = 42) reported the area under the receiver operating characteristic curve (AUROC) as a measure of discrimination. There was no significant difference in the mean AUROC values between regression models (0.833 s.d. ± 0.52) and ML (0.846 s.d. ± 0.55), p = 0.539. Calibration statistics, which measure the agreement between predicted estimates and observed outcomes, were less consistent. Risk of bias assessment found most concerns in the data handling and analysis domains of eligible studies.

CONCLUSIONS

Our study showed comparable predictive performance between regression and ML methods in colorectal surgery. Integration of ML in colorectal risk prediction is promising but further refinement of the models is required to support routine clinical adoption.

Survival outcomes of stage I colorectal cancer: development and validation of the ACEPLY model using two prospective cohorts

BACKGROUND

Approximately 10% of stage I colorectal cancer (CRC) patients experience unfavorable clinical outcomes after surgery. However, little is known about the subset of stage I patients who are predisposed to high risk of recurrence or death. Previous evidence was limited by small sample sizes and lack of validation.

METHODS

We aimed to identify early indicators and develop a risk stratification model to inform prognosis of stage I patients by employing two large prospective cohorts. Prognostic factors for stage II tumors, including T stage, number of nodes examined, preoperative carcinoma embryonic antigen (CEA), lymphovascular invasion, perineural invasion (PNI), and tumor grade were investigated in the discovery cohort, and significant findings were further validated in the other cohort. We adopted disease-free survival (DFS) as the primary outcome for maximum statistical power and recurrence rate and overall survival (OS) as secondary outcomes. Hazard ratios (HRs) were estimated from Cox proportional hazard models, which were subsequently utilized to develop a multivariable model to predict DFS. Predictive performance was assessed in relation to discrimination, calibration and net benefit.

RESULTS

A total of 728 and 413 patients were included for discovery and validation. Overall, 6.7% and 4.1% of the patients developed recurrences during follow-up. We identified consistent significant effects of PNI and higher preoperative CEA on inferior DFS in both the discovery (PNI: HR = 4.26, 95% CI: 1.70-10.67, p = 0.002; CEA: HR = 1.46, 95% CI: 1.13-1.87, p = 0.003) and the validation analysis (PNI: HR = 3.31, 95% CI: 1.01-10.89, p = 0.049; CEA: HR = 1.58, 95% CI: 1.10-2.28, p = 0.014). They were also significantly associated with recurrence rate. Age at diagnosis was a prominent determinant of OS. A prediction model on DFS using Age at diagnosis, CEA, PNI, and number of LYmph nodes examined (ACEPLY) showed significant discriminative performance (C-index: 0.69, 95% CI:0.60-0.77) in the external validation cohort. Decision curve analysis demonstrated added clinical benefit of applying the model for risk stratification.

CONCLUSIONS

PNI and preoperative CEA are useful indicators for inferior survival outcomes of stage I CRC. Identification of stage I patients at high risk of recurrence is feasible using the ACEPLY model, although the predictive performance is yet to be improved.

Predicting the benefit of stereotactic body radiotherapy of colorectal cancer metastases

•

Predicting the benefit from Stereotactic body radiotherapy (SBRT) of colorectal cancer metastases.

•

CLInical Categorical Algorithm (CLICAL©) – a predictive algorithm applied to SBRT.

•

The benefit from SBRT varies among patients with metastatic colorectal cancer.

•

CLICAL© may be used as a screening tool for SBRT referrals.

Aim

Methods

Results

Conclusion

Diet- and Lifestyle-Based Prediction Models to Estimate Cancer Recurrence and Death in Patients With Stage III Colon Cancer (CALGB 89803/Alliance)

PURPOSE

Current tools in predicting survival outcomes for patients with colon cancer predominantly rely on clinical and pathologic characteristics, but increasing evidence suggests that diet and lifestyle habits are associated with patient outcomes and should be considered to enhance model accuracy.

METHODS

Using an adjuvant chemotherapy trial for stage III colon cancer (CALGB 89803), we developed prediction models of disease-free survival (DFS) and overall survival by additionally incorporating self-reported nine diet and lifestyle factors. Both models were assessed by multivariable Cox proportional hazards regression and externally validated using another trial for stage III colon cancer (CALGB/SWOG 80702), and visual nomograms of prediction models were constructed accordingly. We also proposed three hypothetical scenarios for patients with (1) good-risk, (2) average-risk, and (3) poor-risk clinical and pathologic features, and estimated their predictive survival by considering clinical and pathologic features with or without adding self-reported diet and lifestyle factors.

RESULTS

Among 1,024 patients (median age 60.0 years, 43.8% female), we observed 394 DFS events and 311 deaths after median follow-up of 7.3 years. Adding self-reported diet and lifestyle factors to clinical and pathologic characteristics meaningfully improved performance of prediction models (c-index from 0.64 [95% CI, 0.62 to 0.67] to 0.69 [95% CI, 0.67 to 0.72] for DFS, and from 0.67 [95% CI, 0.64 to 0.70] to 0.71 [95% CI, 0.69 to 0.75] for overall survival). External validation also indicated good performance of discrimination and calibration. Adding most self-reported favorable diet and lifestyle exposures to multivariate modeling improved 5-year DFS of all patients and by 6.3% for good-risk, 21.4% for average-risk, and 42.6% for poor-risk clinical and pathologic features.

CONCLUSION

Diet and lifestyle factors further inform current recurrence and survival prediction models for patients with stage III colon cancer.

Scoring systems for the management of oncological hepato-pancreato-biliary patients

Oncological scoring systems in surgery are used as evidence-based decision aids to best support management through assessing prognosis, effectiveness and recurrence. Currently, the use of scoring systems in the hepato-pancreato-biliary (HPB) field is limited as concerns over precision and applicability prevent their widespread clinical implementation. The aim of this review was to discuss clinically useful oncological scoring systems for surgical management of HPB patients. A narrative review was conducted to appraise oncological HPB scoring systems. Original research articles of established and novel scoring systems were searched using Google Scholar, PubMed, Cochrane, and Ovid Medline. Selected models were determined by authors. This review discusses nine scoring systems in cancers of the liver (CLIP, BCLC, ALBI Grade, RETREAT, Fong's score), pancreas (Genç's score, mGPS), and biliary tract (TMHSS, MEGNA). Eight models used exclusively objective measurements to compute their scores while one used a mixture of both subjective and objective inputs. Seven models evaluated their scoring performance in external populations, with reported discriminatory c-statistic ranging from 0.58 to 0.82. Selection of model variables was most frequently determined using a combination of univariate and multivariate analysis. Calibration, another determinant of model accuracy, was poorly reported amongst nine scoring systems. A diverse range of HPB surgical scoring systems may facilitate evidence-based decisions on patient management and treatment. Future scoring systems need to be developed using heterogenous patient cohorts with improved stratification, with future trends integrating machine learning and genetics to improve outcome prediction.

A Prediction Model for Tumor Recurrence in Stage II–III Colorectal Cancer Patients: From a Machine Learning Model to Genomic Profiling

Background: Colorectal cancer (CRC) is one of the most prevalent malignant diseases worldwide. Risk prediction for tumor recurrence is important for making effective treatment decisions and for the survival outcomes of patients with CRC after surgery. Herein, we aimed to explore a prediction algorithm and the risk factors for postoperative tumor recurrence using a machine learning (ML) approach with standardized pathology reports for patients with stage II and III CRC. Methods: Pertinent clinicopathological features were compiled from medical records and standardized pathology reports of patients with stage II and III CRC. Four ML models based on logistic regression (LR), random forest (RF), classification and regression decision trees (CARTs), and support vector machine (SVM) were applied for the development of the prediction algorithm. The area under the curve (AUC) of the ML models was determined in order to compare the prediction accuracy. Genomic studies were performed using a panel-targeted next-generation sequencing approach. Results: A total of 1073 patients who received curative intent surgery at the National Cheng Kung University Hospital between January 2004 and January 2019 were included. Based on conventional statistical methods, chemotherapy (p = 0.003), endophytic tumor configuration (p = 0.008), TNM stage III disease (p < 0.001), pT4 (p < 0.001), pN2 (p < 0.001), increased numbers of lymph node metastases (p < 0.001), higher lymph node ratios (LNR) (p < 0.001), lymphovascular invasion (p < 0.001), perineural invasion (p < 0.001), tumor budding (p = 0.004), and neoadjuvant chemoradiotherapy (p = 0.025) were found to be correlated with the tumor recurrence of patients with stage II–III CRC. While comparing the performance of different ML models for predicting cancer recurrence, the AUCs for LR, RF, CART, and SVM were found to be 0.678, 0.639, 0.593, and 0.581, respectively. The LR model had a better accuracy value of 0.87 and a specificity value of 1 in the testing set. Two prognostic factors, age and LNR, were selected by multivariable analysis and the four ML models. In terms of age, older patients received fewer cycles of chemotherapy and radiotherapy (p < 0.001). Right-sided colon tumors (p = 0.002), larger tumor sizes (p = 0.008) and tumor volumes (p = 0.049), TNM stage II disease (p < 0.001), and advanced pT3–4 stage diseases (p = 0.04) were found to be correlated with the older age of patients. However, pN2 diseases (p = 0.005), lymph node metastasis number (p = 0.001), LNR (p = 0.004), perineural invasion (p = 0.018), and overall survival rate (p < 0.001) were found to be decreased in older patients. Furthermore, PIK3CA and DNMT3A mutations (p = 0.032 and 0.039, respectively) were more frequently found in older patients with stage II–III CRC compared to their younger counterparts. Conclusions: This study demonstrated that ML models have a comparable predictive power for determining cancer recurrence in patients with stage II–III CRC after surgery. Advanced age and high LNR were significant risk factors for cancer recurrence, as determined by ML algorithms and multivariable analyses. Distinctive genomic profiles may contribute to discrete clinical behaviors and survival outcomes between patients of different age groups. Studies incorporating complete molecular and genomic profiles in cancer prediction models are beneficial for patients with stage II–III CRC.

Prediction of incident atrial fibrillation in community-based electronic health records: a systematic review with meta-analysis

Objective

Atrial fibrillation (AF) is common and is associated with an increased risk of stroke. We aimed to systematically review and meta-analyse multivariable prediction models derived and/or validated in electronic health records (EHRs) and/or administrative claims databases for the prediction of incident AF in the community.

Methods

Ovid Medline and Ovid Embase were searched for records from inception to 23 March 2021. Measures of discrimination were extracted and pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using Prediction model Risk Of Bias ASsessment Tool and certainty in effect estimates by Grading of Recommendations, Assessment, Development and Evaluation.

Results

Eleven studies met inclusion criteria, describing nine prediction models, with four eligible for meta-analysis including 9 289 959 patients. The CHADS (Congestive heart failure, Hypertension, Age>75, Diabetes mellitus, prior Stroke or transient ischemic attack) (summary c-statistic 0.674; 95% CI 0.610 to 0.732; 95% PI 0.526–0.815), CHA₂DS₂-VASc (Congestive heart failure, Hypertension, Age>75 (2 points), Stroke/transient ischemic attack/thromboembolism (2 points), Vascular disease, Age 65–74, Sex category) (summary c-statistic 0.679; 95% CI 0.620 to 0.736; 95% PI 0.531–0.811) and HATCH (Hypertension, Age, stroke or Transient ischemic attack, Chronic obstructive pulmonary disease, Heart failure) (summary c-statistic 0.669; 95% CI 0.600 to 0.732; 95% PI 0.513–0.803) models resulted in a c-statistic with a statistically significant 95% PI and moderate discriminative performance. No model met eligibility for inclusion in meta-analysis if studies at high risk of bias were excluded and certainty of effect estimates was ‘low’. Models derived by machine learning demonstrated strong discriminative performance, but lacked rigorous external validation.

Conclusions

Models externally validated for prediction of incident AF in community-based EHR demonstrate moderate predictive ability and high risk of bias. Novel methods may provide stronger discriminative performance.

Systematic review registration

PROSPERO CRD42021245093.

Right and Left Colorectal Cancer: Differences in Post-Surgical-Care Outcomes and Survival in Elderly Patients

Simple Summary

The objective of this investigation is to analyze the differences between right and left colon cancer survival and test if these differences have transcendental importance for assistance to improve the survival and quality care of these patients. The results show that both entities are significantly different in terms of evolution, progression, complications and survival. Patients with right colon cancer have a worse prognosis, even in the early stages of the disease, due to more advanced N stages, a larger tumor size, more frequently poorly differentiated tumors and a greater positivity of lymphovascular invasion than left colon cancer. Improvement of the prognosis can be implemented mainly by reducing the specific mortality of colon cancer by achieving early detection and also stratified and personalized by location and age of onset, as well as surgical and oncological treatment of these patients.

Abstract

(1) There is evidence of the embryological, anatomical, histological, genetic and immunological differences between right colon cancer (RCC) and left colon cancer (LCC). This research has the general objective of studying the differences in outcome between RCC and LCC. (2) A longitudinal analytical study with prospective follow-up of the case–control type was conducted from 1 January 2010 to 31 December 2017 including 398 patients with 1:1 matching, depending on the location of the tumor. Inclusion criteria: programmed colectomies, 15 cm above the anal margin, adults and R0 surgery. (3) Precisely 6.8% of the exitus occurred in the first 6 months of the intervention. At 6 months, patients with LCC presented a mean survival of 7 months higher than RCC (p = 0.028). In the first stages, it can be observed that most of the exitus are for patients with RCC (stage I p = 0.021, stage II p = 0.014). In the last stages, the distribution of the deaths does not show differences between locations (stage III p = 0.683, stage IV p = 0.898). (4) The results show that RCC and LCC are significantly different in terms of evolution, progression, complications and survival. Patients with RCC have a worse prognosis, even in the early stages of the disease, due to more advanced N stages, larger tumor size, more frequently poorly differentiated tumors and a greater positivity of lymphovascular invasion than LCC.

Development and validation of a model to predict survival in colorectal cancer using a gradient-boosted machine

OBJECTIVE

The success of treatment planning relies critically on our ability to predict the potential benefit of a therapy. In colorectal cancer (CRC), several nomograms are available to predict different outcomes based on the use of tumour specific features. Our objective is to provide an accurate and explainable prediction of the risk to die within 10 years after CRC diagnosis, by incorporating the tumour features and the patient medical and demographic information.

DESIGN

In the prostate, lung, colorectal and ovarian cancer screening (PLCO) Trial, participants (n=154 900) were randomised to screening with flexible sigmoidoscopy, with a repeat screening at 3 or 5 years, or to usual care. We selected patients who were diagnosed with CRC during the follow-up to train a gradient-boosted model to predict the risk to die within 10 years after CRC diagnosis. Using Shapley values, we determined the 20 most relevant features and provided explanation to prediction.

RESULTS

During the follow-up, 2359 patients were diagnosed with CRC. Median follow-up was 16.8 years (14.4-18.9) for mortality. In total, 686 patients (29%) died from CRC during the follow-up. The dataset was randomly split into a training (n=1887) and a testing (n=472) dataset. The area under the receiver operating characteristic was 0.84 (±0.04) and accuracy was 0.83 (±0.04) with a 0.5 classification threshold. The model is available online for research use.

CONCLUSIONS

We trained and validated a model with prospective data from a large multicentre cohort of patients. The model has high predictive performances at the individual scale. It could be used to discuss treatment strategies.

Meta-analysis of survival outcomes following surgical and non surgical treatments for colorectal cancer metastasis to the lung

BACKGROUND

Controversy exists regarding the optimal management of colorectal lung metastases (CRLM). This meta-analysis compared surgical (Surg) versus interventional (chemotherapy and/or radiotherapy) and observational non-surgical (NSurg) management of CRLM.

METHODS

A systematic review of the major databases including Medline, Embase, SCOPUS and the Cochrane library was performed.

RESULTS

One randomized and nine observational studies including 2232 patients: 1551 (69%) comprised the Surg cohort, 521 (23%) the interventional NSurg group and 160 (7%) the observational NSurg group. A significantly higher overall survival (OS) was observed when Surg was compared to interventional NSurg at 1 year (Surg 88%, 310/352; interventional NSurg 64%, 245/383; odds ratio (OR) 2.77 (confidence interval (CI) 1.94-3.97), P = 0.001), at 3 years (Surg 59%, 857/1444; interventional NSurg 26%, 138/521; OR 2.61 (CI 1.65-4.15), P = 0.002), at 5 years (Surg 47%, 533/1144; interventional NSurg 23%, 45/196; OR 3.24 (CI 1.42-7.39), P = 0.009) and at 10 years (Surg 27%, 306/1122; interventional NSurg 1%, 2/168; OR 15.64 (CI 1.87-130.76), P = 0.031). Surg was associated with a greater OS than observational NSurg at only 1 year (Surg 92%, 98/107; observational NSurg 83%, 133/160; OR 6.69 (CI 1.33-33.58), P = 0.037) and was similar to observational NSurg at all other OS time points. Comparable survival was observed among Surg and overall NSurg cohorts at 3- and 5-year survival in articles published within the last 3 years.

CONCLUSIONS

Recent evidence suggests comparable survival with Surg and NSurg modalities for CRLM, contrasting to early evidence where Surg had an improved survival. Significant selection bias contributes to this finding, prompting the need for high powered randomized controlled trials and registry data.

Development and validation of a nomogram to predict the prognosis of patients with squamous cell carcinoma of the bladder

Background: The present study aimed to develop and validate a nomogram based on expanded TNM staging to predict the prognosis for patients with squamous cell carcinoma of the bladder (SCCB).

Methods: A total of 595 eligible patients with SCCB identified in the Surveillance, Epidemiology, and End Results (SEER) dataset were randomly divided into training set (n = 416) and validation set (n = 179). The likelihood ratio test was used to select potentially relevant factors for developing the nomogram. The performance of the nomogram was validated on the training and validation sets using a C-index with 95% confidence interval (95% CI) and calibration curve, and was further compared with TNM staging system.

Results: The nomogram included six factors: age, T stage, N stage, M stage, the method of surgery and tumor size. The C-indexes of the nomogram were 0.768 (0.741–0.795) and 0.717 (0.671–0.763) in the training and validation sets, respectively, which were higher than the TNM staging system with C-indexes of 0.580 (0.543–0.617) and 0.540 (0.484–0.596) in the training and validation sets, respectively. Furthermore, the decision curve analysis (DCA) proved that the nomogram provided superior clinical effectiveness.

Conclusions: We developed a nomogram that help predict individualized prognosis for patients with SCCB.

A nomogram from the SEER database for predicting the prognosis of patients with non-small cell lung cancer

OBJECTIVE

The purpose of this study was to establish and validate a nomogram to predict the prognosis in patients with non-small cell lung cancer (NSCLC) from multiple perspectives.

RESULTS

A total of 98,640 eligible patients were randomly divided into a training set (n = 69,048) and a validation set (n = 29,592). The baseline characteristics of the two sets were similar. We used clinical data from patients in the training set for univariate and multivariate Cox regression analyses. Twelve independent risk factors were incorporated for constructed a prognostic nomogram. And the nomogram with a concordance index of 0.777 (95 % CI, 0.775 to 0.779) for overall survival. The calibration curve results showed that the actual survival rate was consistent with the predicted survival rate. The area under curve of the receiver operating characteristic curves demonstrated that the nomogram has a high prediction of the overall survival rate in patients with NSCLC.

CONCLUSION

We have developed a nomogram with high prediction accuracy and discrimination ability, which can help clinicians making personalized survival predictions for NSCLC patients.

Nomogram Predicting Overall Survival of Resected Locally Advanced Rectal Cancer Patients with Neoadjuvant Chemoradiotherapy

PURPOSE

The overall survival (OS) of resected locally advanced rectal cancer patients who underwent neoadjuvant chemoradiotherapy (nCRT) was significantly different, even among patients with the same tumor stage. The nomogram was designed to predict OS of rectal cancer with nCRT and divide the patients into different risk groups.

MATERIALS AND METHODS

Based on materials from 911 rectal cancer patients with nCRT, the multivariable Cox regression model was carried out to select the significant prognostic factors for overall survival. And then, the nomogram was formulated using these independent prognostic factors. The discrimination of the nomogram was assessed by concordance index (C-index), calibration curves and time-dependent area under curve (AUC). The patients respective risk scores were calculated through the nomogram. The best cut-off risk score was calculated to stratify the patients. The survival curves of the two different risk cohorts were performed, which assessed the predictive ability of the nomogram.

RESULTS

Age, cT stage, pretreatment CEA, pretreatment CA19-9, surgery, posttreatment CEA, posttreatment CA19-9, pT stage, pN stage and adjuvant chemotherapy were selected for the construction of the nomogram. And then the nomogram was constructed with independent prognostic factors. The C-index of the nomogram was 0.724, which showed the nomogram provided good discernment. The acceptable agreement between the predictions of nomogram and actual observations was illustrated by calibration plots for 3-, 5- and 10-year OS in the cohort. Time-dependent AUC with 6-fold cross-validation also showed consistent results of the nomogram. Risk group stratification confirmed that the nomogram had great capacity for distinguishing the prognosis.

CONCLUSION

The nomogram was developed and validated to predict overall survival of resected locally advanced rectal cancer patients with nCRT. The proposed nomogram might help clinicians to develop individualized treatment strategies. However, further studies are warranted to optimize the nomogram by finding out other unknown prognostic factors, and more external validation is still required.

Risk factors and risk prediction models for colorectal cancer metastasis and recurrence: an umbrella review of systematic reviews and meta-analyses of observational studies

BACKGROUND

There is a clear need for systematic appraisal of models/factors predicting colorectal cancer (CRC) metastasis and recurrence because clinical decisions about adjuvant treatment are taken on the basis of such variables.

METHODS

We conducted an umbrella review of all systematic reviews of observational studies (with/without meta-analysis) that evaluated risk factors of CRC metastasis and recurrence. We also generated an updated synthesis of risk prediction models for CRC metastasis and recurrence. We cross-assessed individual risk factors and risk prediction models.

RESULTS

Thirty-four risk factors for CRC metastasis and 17 for recurrence were investigated. Twelve of 34 and 4/17 risk factors with p < 0.05 were estimated to change the odds of the outcome at least 3-fold. Only one risk factor (vascular invasion for lymph node metastasis [LNM] in pT1 CRC) presented convincing evidence. We identified 24 CRC risk prediction models. Across 12 metastasis models, six out of 27 unique predictors were assessed in the umbrella review and four of them changed the odds of the outcome at least 3-fold. Across 12 recurrence models, five out of 25 unique predictors were assessed in the umbrella review and only one changed the odds of the outcome at least 3-fold.

CONCLUSIONS

This study provides an in-depth evaluation and cross-assessment of 51 risk factors and 24 prediction models. Our findings suggest that a minority of influential risk factors are employed in prediction models, which indicates the need for a more rigorous and systematic model construction process following evidence-based methods.

Statistical Challenges in Development of Prognostic Models in Diffuse Large B-Cell Lymphoma: Comparison Between Existing Models - A Systematic Review

Background and Aim

Based on advances in the diagnosis, classification, and management of diffuse large B-cell lymphoma (DLBCL), a number of new prognostic models have been proposed. The aim of this study was to review and compare different prognostic models of DLBCL based on the statistical methods used to evaluate the performance of each model, as well as to analyze the possible limitations of the methods.

Methods and Results

A literature search identified 46 articles that proposed 55 different prognostic models for DLBCL by combining different clinical, laboratory, and other parameters of prognostic significance. In addition, six studies used nomograms, which avoid risk categorization, to create prognostic models. Only a minority of studies assessed discrimination and/or calibration to compare existing models built upon different statistical methods in the process of development of a new prognostic model. All models based on nomograms reported the c-index as a measure of discrimination. There was no uniform evaluation of the performance in other prognostic models. We compared these models of DLBCL by calculating differences and ratios of 3-year overall survival probabilities between the high- and the low-risk groups. We found that the highest and lowest ratio between low- and high-risk groups was 6 and 1.31, respectively, while the difference between these groups was 18.9% and 100%, respectively. However, these studies had limited duration of follow-up and the number of patients ranged from 71 to 335.

Conclusion

There is no universal statistical instrument that could facilitate a comparison of prognostic models in DLBCL. However, when developing a prognostic model, it is recommended to report its discrimination and calibration in order to facilitate comparisons between different models. Furthermore, prognostic models based on nomograms are becoming more appealing owing to individualized disease-related risk estimations. However, they have not been validated yet in other study populations.

A nomogram to predict survival of patients with intermediate-stage hepatocellular carcinoma after transarterial chemoembolization combined with microwave ablation

OBJECTIVES

To develop a prognostic nomogram based on the albumin-bilirubin (ALBI) grade for prediction of the long-term survival of patients with intermediate-stage hepatocellular carcinoma (HCC) after transarterial chemoembolization combined with microwave ablation (TACE-MWA).

METHODS

We retrospectively studied 546 consecutive patients with intermediate-stage HCC according to the Barcelona Clinic Liver Cancer guidelines who underwent TACE-MWA between January 2000 and December 2016. Overall survival (OS) and progression-free survival (PFS) were analyzed. The predictive value of the ALBI grade was investigated. The prognostic nomogram was constructed using the independent predictors assessed by the multivariate Cox proportional hazards model.

RESULTS

After a median follow-up of 35.0 months (range, 4.0-221.0 months), 380 patients had died. The median OS was 35.0 months (95% confidence interval (CI), 30.84-39.16 months), and the median PFS was 6.5 months (95% CI, 6.13-6.87 months). The ALBI grade was validated as an independent predictor of OS (p < 0.001). Multivariate analyses showed that Eastern Cooperative Oncology Group performance status score more than 0, presence of liver cirrhosis, a-fetoprotein level above 400 ng/mL, tumor size greater than 5 cm, tumor number more than 3, advanced ALBI grade, and treatment sessions of TACE or MWA fewer than 3 were independently associated with overall mortality. The prognostic nomogram incorporating these eight predictors achieved good calibration and discriminatory abilities with a concordance index of 0.770 (95% CI, 0.746-0.795).

CONCLUSIONS

The prognostic nomogram based on the ALBI grade resulted in reliable efficacy for prediction of individualized OS in patients with intermediate-stage HCC after TACE-MWA.

KEY POINTS

• TACE-MWA was associated with a median overall survival of 35.0 months for patients with intermediate-stage HCC. • A prognostic nomogram was built to predict individualized survival of patients with intermediate-stage HCC after TACE-MWA. • The prognostic nomogram incorporating eight predictors achieved good calibration and discriminatory abilities with a concordance index of 0.770.