A novel data-driven prognostic model for staging of colorectal cancer

Constructing a nomogram to predict overall survival of colon cancer based on computed tomography characteristics and clinicopathological factors

BACKGROUND

The colon cancer prognosis is influenced by multiple factors, including clinical, pathological, and non-biological factors. However, only a few studies have focused on computed tomography (CT) imaging features. Therefore, this study aims to predict the prognosis of patients with colon cancer by combining CT imaging features with clinical and pathological characteristics, and establishes a nomogram to provide critical guidance for the individualized treatment.

AIM

To establish and validate a nomogram to predict the overall survival (OS) of patients with colon cancer.

METHODS

A retrospective analysis was conducted on the survival data of 249 patients with colon cancer confirmed by surgical pathology between January 2017 and December 2021. The patients were randomly divided into training and testing groups at a 1:1 ratio. Univariate and multivariate logistic regression analyses were performed to identify the independent risk factors associated with OS, and a nomogram model was constructed for the training group. Survival curves were calculated using the Kaplan–Meier method. The concordance index (C-index) and calibration curve were used to evaluate the nomogram model in the training and testing groups.

RESULTS

Multivariate logistic regression analysis revealed that lymph node metastasis on CT, perineural invasion, and tumor classification were independent prognostic factors. A nomogram incorporating these variables was constructed, and the C-index of the training and testing groups was 0.804 and 0.692, respectively. The calibration curves demonstrated good consistency between the actual values and predicted probabilities of OS.

CONCLUSION

A nomogram combining CT imaging characteristics and clinicopathological factors exhibited good discrimination and reliability. It can aid clinicians in risk stratification and postoperative monitoring and provide important guidance for the individualized treatment of patients with colon cancer.

Machine learning-based classifiers to predict metastasis in colorectal cancer patients

BACKGROUND

The increasing prevalence of colorectal cancer (CRC) in Iran over the past three decades has made it a key public health burden. This study aimed to predict metastasis in CRC patients using machine learning (ML) approaches in terms of demographic and clinical factors.

METHODS

This study focuses on 1,127 CRC patients who underwent appropriate treatments at Taleghani Hospital, a tertiary care facility. The patients were divided into training and test datasets in an 80:20 ratio. Various ML methods, including Naive Bayes (NB), random rorest (RF), support vector machine (SVM), neural network (NN), decision tree (DT), and logistic regression (LR), were used for predicting metastasis in CRC patients. Model performance was evaluated using 5-fold cross-validation, reporting sensitivity, specificity, the area under the curve (AUC), and other indexes.

RESULTS

Among the 1,127 patients, 183 (16%) had experienced metastasis. In the predictionof metastasis, both the NN and RF algorithms had the highest AUC, while SVM ranked third in both the original and balanced datasets. The NN and RF algorithms achieved the highest AUC (100%), sensitivity (100% and 100%, respectively), and accuracy (99.2% and 99.3%, respectively) on the balanced dataset, followed by the SVM with an AUC of 98.8%, a sensitivity of 97.5%, and an accuracy of 97%. Moreover, lower false negative rate (FNR), false positive rate (FPR), and higher negative predictive value (NPV) can be confirmed by these two methods. The results also showed that all methods exhibited good performance in the test datasets, and the balanced dataset improved the performance of most ML methods. The most important variables for predicting metastasis were the tumor stage, the number of involved lymph nodes, and the treatment type. In a separate analysis of patients with tumor stages I-III, it was identified that tumor grade, tumor size, and tumor stage are the most important features.

CONCLUSION

This study indicated that NN and RF were the best among ML-based approaches for predicting metastasis in CRC patients. Both the tumor stage and the number of involved lymph nodes were considered the most important features.

Evaluating the Clinical Performance of a Dual-Target Stool DNA Test for Colorectal Cancer Detection

Previous work indicated that the dual-target stool DNA test, iColocomf, showed potential utility for colorectal cancer (CRC) detection, but its clinical accuracy was not validated on larger groups. This study aimed to evaluate the performance of iColocomf in a multicenter clinical trial. In this double-blinded case-control study, we enrolled 1164 participants from three independent hospitals, including 320 CRC patients, 148 adenomas, 396 interfering diseases, and 300 healthy controls. The primary indicators of sensitivity, specificity, and accuracy were estimated. Stool samples of participants were collected and tested by the assay. The test results were then verified by Sanger sequencing and retesting of resected participants. The sensitivity and specificity for CRC detection were 95.31% and 96.67%, respectively, with an accuracy of 90.29%. When combining the interfering diseases, the specificity was 88.39%. No statistically significant variations of positive detection rates were observed for the test in different patients' clinical features. For advanced adenomas (n = 38) and nonadvanced adenomas (n = 110), the sensitivities were 63.16% and 33.64%, respectively. The average accuracy was 99.62% for the methylation status of 375 samples verified by Sanger sequencing, and 94.12% for 34 participants who received the test second after surgical resection. The iColocomf test showed robust performance for the early detection of colorectal cancer and potential monitoring ability in clinical practice.

Interventions and Outcomes for Neoadjuvant Treatment of T4 Colon Cancer: A Scoping Review

While adjuvant treatment of colon cancers that penetrate the serosa (T4) have been well-established, neoadjuvant strategies have yet to be formally evaluated. Our objective was to perform a scoping review of eligibility criteria, treatment regimens, and primary outcomes for neoadjuvant approaches to T4 colon cancer. A librarian-led, systematic search of MEDLINE, Embase, Cochrane Library, Web of Science, and CINAHL up to 11 February 2020 was performed. Primary research evaluating neoadjuvant treatment in T4 colon cancer were included. Screening and data abstraction were performed in duplicate; analyses were descriptive or thematic. A total of twenty studies were included, most of which were single-arm, single-center, and retrospective. The primary objectives of the literature to date has been to evaluate treatment feasibility, tumor response, disease-free survival, and overall survival in healthy patients. Conventional XELOX and FOLFOX chemotherapy were the most commonly administered interventions. Rationale for selecting a specific regimen and for treatment eligibility criteria were poorly documented across studies. The current literature on neoadjuvant strategies for T4 colon cancer is overrepresented by single-center, retrospective studies that evaluate treatment feasibility and efficacy in healthy patients. Future studies should prioritize evaluating clear selection criteria and rationale for specific neoadjuvant strategies. Validation of outcomes in multi-center, randomized trials for XELOX and FOLFOX have the most to contribute to the growing evidence for this poorly managed disease.

Development of a Gene-Based Prediction Model for Recurrence of Colorectal Cancer Using an Ensemble Learning Algorithm

It is difficult to determine which patients with stage I and II colorectal cancer are at high risk of recurrence, qualifying them to undergo adjuvant chemotherapy. In this study, we aimed to determine a gene signature using gene expression data that could successfully identify high risk of recurrence among stage I and II colorectal cancer patients. First, a synthetic minority oversampling technique was used to address the problem of imbalanced data due to rare recurrence events. We then applied a sequential workflow of three methods (significance analysis of microarrays, logistic regression, and recursive feature elimination) to identify genes differentially expressed between patients with and without recurrence. To stabilize the prediction algorithm, we repeated the above processes on 10 subsets by bagging the training data set and then used support vector machine methods to construct the prediction models. The final predictions were determined by majority voting. The 10 models, using 51 differentially expressed genes, successfully predicted a high risk of recurrence within 3 years in the training data set, with a sensitivity of 91.18%. For the validation data sets, the sensitivity of the prediction with samples from two other countries was 80.00% and 91.67%. These prediction models can potentially function as a tool to decide if adjuvant chemotherapy should be administered after surgery for patients with stage I and II colorectal cancer.

Impact factors of lymph node retrieval on survival in locally advanced rectal cancer with neoadjuvant therapy

BACKGROUND

Conventional clinical guidelines recommend that at least 12 lymph nodes should be removed during radical rectal cancer surgery to achieve accurate staging. The current application of neoadjuvant therapy has changed the number of lymph node dissection.

AIM

To investigate factors affecting the number of lymph nodes dissected after neoadjuvant chemoradiotherapy in locally advanced rectal cancer and to evaluate the relationship of the total number of retrieved lymph nodes (TLN) with disease-free survival (DFS) and overall survival (OS).

METHODS

A total of 231 patients with locally advanced rectal cancer from 2015 to 2017 were included in this study. According to the American Joint Committee on Cancer (AJCC)/Union for International Cancer Control (UICC) tumor-node-metastasis (TNM) classification system and the NCCN guidelines for rectal cancer, the patients were divided into two groups: group A (TLN ≥ 12, n = 177) and group B (TLN < 12, n = 54). Factors influencing lymph node retrieval were analyzed by univariate and binary logistic regression analysis. DFS and OS were evaluated by Kaplan-Meier curves and Cox regression models.

RESULTS

The median number of lymph nodes dissected was 18 (range, 12-45) in group A and 8 (range, 2-11) in group B. The lymph node ratio (number of positive lymph nodes/total number of lymph nodes) (P = 0.039) and the interval between neoadjuvant therapy and radical surgery (P = 0.002) were independent factors of the TLN. However,TLN was not associated with sex, age, ASA score, clinical T or N stage, pathological T stage, tumor response grade (Dworak), downstaging, pathological complete response, radiotherapy dose, preoperative concurrent chemotherapy regimen, tumor distance from anal verge, multivisceral resection, preoperative carcinoembryonic antigen level, perineural invasion, intravascular tumor embolus or degree of differentiation. The pathological T stage (P < 0.001) and TLN (P < 0.001) were independent factors of DFS, and pathological T stage (P = 0.011) and perineural invasion (P = 0.002) were independent factors of OS. In addition, the risk of distant recurrence was greater for TLN < 12 (P = 0.009).

CONCLUSION

A shorter interval to surgery after neoadjuvant chemoradiotherapy for rectal cancer under indications may cause increased number of lymph nodes harvested. Tumor shrinkage and more extensive lymph node retrieval may lead to a more favorable prognosis.

Selecting the number of categories of the lymph node ratio in cancer research: A bootstrap-based hypothesis test

The high impact of the lymph node ratio as a prognostic factor is widely established in colorectal cancer, and is being used as a categorized predictor variable in several studies. However, the cut-off points as well as the number of categories considered differ considerably in the literature. Motivated by the need to obtain the best categorization of the lymph node ratio as a predictor of mortality in colorectal cancer patients, we propose a method to select the best number of categories for a continuous variable in a logistic regression framework. Thus, to this end, we propose a bootstrap-based hypothesis test, together with a new estimation algorithm for the optimal location of the cut-off points called BackAddFor, which is an updated version of the previously proposed AddFor algorithm. The performance of the hypothesis test was evaluated by means of a simulation study, under different scenarios, yielding type I errors close to the nominal errors and good power values whenever a meaningful difference in terms of prediction ability existed. Finally, the methodology proposed was applied to the CCR-CARESS study where the lymph node ratio was included as a predictor of five-year mortality, resulting in the selection of three categories.

Real-world study of a novel prognostic scoring system: for a more precise prognostication and better clinical treatment guidance in stages II and III colon cancer

PURPOSE

This study aimed to improve the American Joint Committee on Cancer (AJCC) Tumor Node Metastases (TNM) staging system and demonstrate the improvement in prognostic accuracy and clinical management guidance in colon cancer using the novel prognostic score (P score).

METHODS

Eligible patients were identified using the Surveillance, Epidemiology, and End Results database. A P score (based on age, tumor size, and tumor grade) was assigned to each patient. The Cox proportional hazards regression analyses were performed to identify independent factors associated with prognosis. The Kaplan-Meier survival curves were used to analyze the prognosis of patients with colon cancer with different P scores. The TNM staging system was compared with the P score in stages I-IV by calculating the concordance index.

RESULTS

The multivariate Cox analysis indicated that a higher P score was independently associated with a higher risk of cancer-specific mortality. The Kaplan-Meier survival curves showed that the survival benefit gradually increased as the P score decreased. The concordance index rose from 0.5, 0.593, 0.633, and 0.551 of AJCC TNM staging system to 0.709, 0.651, 0.691, and 0.623 of P score in stages I-IV, respectively.

CONCLUSIONS

The P score was an independent prognostic factor of colon cancer and had a much better prognostic accuracy than the AJCC TNM staging system in all patients with colon cancer. It may help in identifying patients with high-risk stage II colon cancer who were candidates for adjuvant therapy and differentiating patients with stage III colon cancer for adjuvant therapy.

Predictors of one and two years' mortality in patients with colon cancer: A prospective cohort study

Background

Tools to aid in the prognosis assessment of colon cancer patients in terms of risk of mortality are needed. Goals of this study are to develop and validate clinical prediction rules for 1- and 2-year mortality in these patients.

Methods

This is a prospective cohort study of patients diagnosed with colon cancer who underwent surgery at 22 hospitals. The main outcomes were mortality at 1 and 2 years after surgery. Background, clinical parameters, and diagnostic tests findings were evaluated as possible predictors. Multivariable multilevel logistic regression and survival models were used in the analyses to create the clinical prediction rules. Models developed in the derivation sample were validated in another sample of the study.

Results

American Society of Anesthesiologists Physical Status Classification System (ASA), Charlson comorbidity index (> = 4), age (>75 years), residual tumor (R2), TNM stage IV and log of lymph nodes ratio (> = -0.53) were predictors of 1-year mortality (C-index (95% CI): 0.865 (0.792–0.938)). Adjuvant chemotherapy was an additional predictor. Again ASA, Charlson Index (> = 4), age (>75 years), log of lymph nodes ratio (> = -0.53), TNM, and residual tumor were predictors of 2-year mortality (C-index:0.821 (0.766–0.876). Chemotherapy was also an additional predictor.

Conclusions

These clinical prediction rules show very good predictive abilities of one and two years survival and provide clinicians and patients with an easy and quick-to-use decision tool for use in the clinical decision process while the patient is still in the index admission.

Combining statistical techniques to predict postsurgical risk of 1-year mortality for patients with colon cancer

Introduction

Colorectal cancer is one of the most frequently diagnosed malignancies and a common cause of cancer-related mortality. The aim of this study was to develop and validate a clinical predictive model for 1-year mortality among patients with colon cancer who survive for at least 30 days after surgery.

Methods

Patients diagnosed with colon cancer who had surgery for the first time and who survived 30 days after the surgery were selected prospectively. The outcome was mortality within 1 year. Random forest, genetic algorithms and classification and regression trees were combined in order to identify the variables and partition points that optimally classify patients by risk of mortality. The resulting decision tree was categorized into four risk categories. Split-sample and bootstrap validation were performed. ClinicalTrials.gov Identifier: NCT02488161.

Results

A total of 1945 patients were enrolled in the study. The variables identified as the main predictors of 1-year mortality were presence of residual tumor, American Society of Anesthesiologists Physical Status Classification System risk score, pathologic tumor staging, Charlson Comorbidity Index, intraoperative complications, adjuvant chemotherapy and recurrence of tumor. The model was internally validated; area under the receiver operating characteristic curve (AUC) was 0.896 in the derivation sample and 0.835 in the validation sample. Risk categorization leads to AUC values of 0.875 and 0.832 in the derivation and validation samples, respectively. Optimal cut-off point of estimated risk had a sensitivity of 0.889 and a specificity of 0.758.

Conclusion

The decision tree was a simple, interpretable, valid and accurate prediction rule of 1-year mortality among colon cancer patients who survived for at least 30 days after surgery.

Lymph Node Metastasis in Colorectal Cancer

Pathologic examination of lymph nodes in patients with cancer remains crucial for postoperative treatment and prognosis prediction. In this article, the authors aim to review several important and challenging issues regarding lymph node metastasis in colorectal cancer using the AJCC staging manual, College of American Pathologists cancer protocol, as well as the literature. These topics include lymph node staging, the definition and controversies in tumor deposits, isolated tumor cells in lymph node and micrometastasis, lymph node ratio as a prognostic stratification factor, and neoadjuvant treatment effect in rectal cancer. Updates from the most recent AJCC 8th edition are included.

The American Society of Colon and Rectal Surgeons Clinical Practice Guidelines for the Treatment of Colon Cancer

The American Society of Colon and Rectal Surgeons is dedicated to ensuring high-quality patient care by advancing the science, prevention, and management of disorders and diseases of the colon, rectum, and anus. The Clinical Practice Guidelines Committee is composed of society members who are chosen because they have demonstrated expertise in the specialty of colon and rectal surgery. This committee was created to lead international efforts in defining quality care for conditions related to the colon, rectum, and anus. This is accompanied by developing Clinical Practice Guidelines based on the best available evidence. These guidelines are inclusive and not prescriptive. Their purpose is to provide information on which decisions can be made, rather than to dictate a specific form of treatment. These guidelines are intended for the use of all practitioners, health care workers, and patients who desire information about the management of the conditions addressed by the topics covered in these guidelines. It should be recognized that these guidelines should not be deemed inclusive of all proper methods of care or exclusive of methods of care reasonably directed to obtaining the same results. The ultimate judgment regarding the propriety of any specific procedure must be made by the physician in light of all the circumstances presented by the individual patient.

Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach

We developed and independently validated a rheumatoid arthritis (RA) mortality prediction model using the machine learning method Random Survival Forests (RSF). Two independent cohorts from Madrid (Spain) were used: the Hospital Clínico San Carlos RA Cohort (HCSC-RAC; training; 1,461 patients), and the Hospital Universitario de La Princesa Early Arthritis Register Longitudinal study (PEARL; validation; 280 patients). Demographic and clinical-related variables collected during the first two years after disease diagnosis were used. 148 and 21 patients from HCSC-RAC and PEARL died during a median follow-up time of 4.3 and 5.0 years, respectively. Age at diagnosis, median erythrocyte sedimentation rate, and number of hospital admissions showed the higher predictive capacity. Prediction errors in the training and validation cohorts were 0.187 and 0.233, respectively. A survival tree identified five mortality risk groups using the predicted ensemble mortality. After 1 and 7 years of follow-up, time-dependent specificity and sensitivity in the validation cohort were 0.79–0.80 and 0.43–0.48, respectively, using the cut-off value dividing the two lower risk categories. Calibration curves showed overestimation of the mortality risk in the validation cohort. In conclusion, we were able to develop a clinical prediction model for RA mortality using RSF, providing evidence for further work on external validation.

The prognostic value of lymph node ratio in colon cancer is independent of resection length

BACKGROUND

Lymph node ratio (LNR), the ratio of tumor-positive lymph nodes (+LN) to the total number of resected lymph nodes (rLN), predicts recurrence and survival in colon cancer. Variations in colonic resection length (RL) may influence rLN, +LN, or both, thereby potentially impacting LNR and its prognostic value in colon cancer.

METHODS

All colon cancer patients treated surgically at our center from 2004 to 2011 were included in an institutional review board-approved data repository (n = 1,039).

RESULTS

Larger RL was associated with increased rLN (ρ = .22; P < .001) but not with +LN (P = .21). In node-positive patients (n = 411), RL-adjusted LNR had weaker correlations with death (ρ = .338 vs .373, both P < .001) or metastatic disease (ρ = .303 vs .345; both P < .001) and a smaller area under the curve (death: .695 vs .715, metastasis: .675 vs .699). Findings were similar in segmental, extended segmental, and total colectomy subgroups.

CONCLUSIONS

Provided that resections are performed following standard oncologic principles, our analysis shows that RL does not significantly impact the prognostic value of LNR in colon cancer. Correcting LNR for RL seems redundant and may even act as noise distorting LNR values.

Effect of High-Grade Disease on Outcomes of Surgically Treated Colon Cancer

INTRODUCTION

Tumor grade is one of the cardinal pathological characteristics of colon cancer. Despite a large body of evidence on disease grade in general, the exact impact of high-grade disease in the context of the simplified high/low-grade dichotomy that is based on glandular formation rate has yet to be quantified.

METHODS

Patients with sporadic colon cancer treated surgically at our center (2004-2011) were included in an institutional review board-approved database. We measured the rates of distant and nodal disease spread in baseline pathology and the multivariable hazard radio (mHR) of recurrence and overall- and disease-specific mortality.

RESULTS

Among 922 patients with specified tumor grade in baseline surgical pathology, 175 (19.0 %) had high-grade disease. These patients were at far higher risk of lymph node metastasis (63.8 vs. 39.6 %; P < 0.001) and metastatic presentation (31.4 vs. 15.8 %; P < 0.001). These baseline differences also led to significantly worse outcomes, including disease recurrence (17.1 vs. 10.6 %; mHR = 1.83; P = 0.026), overall mortality (57.7 vs. 33.3 %; mHR = 1.65; P < 0.001), and colon cancer-specific mortality (39.4 vs. 16.9 %; mHR = 1.57; P = 0.004). Most significantly, in stage II patients (n = 294), those with high-grade disease (16.0 %) had an mHR of 2.84 (P < 0.001) for mortality.

CONCLUSIONS

High-grade disease on baseline surgical pathology is associated with a considerably higher rate of nodal and distant metastasis in colon cancer. As a result, the colon cancer-related mortality doubles for patients with high-grade disease. These findings were independent of baseline staging and confirm that the high-/low-grade tumor dichotomy is an important prognostic factor greatly influencing colon cancer outcomes across stages.

Whole-exome sequencing enhances prognostic classification of myeloid malignancies

PURPOSE

To date the standard nosology and prognostic schemes for myeloid neoplasms have been based on morphologic and cytogenetic criteria. We sought to test the hypothesis that a comprehensive, unbiased analysis of somatic mutations may allow for an improved classification of these diseases to predict outcome (overall survival).

EXPERIMENTAL DESIGN

We performed whole-exome sequencing (WES) of 274 myeloid neoplasms, including myelodysplastic syndrome (MDS, N=75), myelodysplastic/myeloproliferative neoplasia (MDS/MPN, N=33), and acute myeloid leukemia (AML, N=22), augmenting the resulting mutational data with public WES results from AML (N=144). We fit random survival forests (RSFs) to the patient survival and clinical/cytogenetic data, with and without gene mutation information, to build prognostic classifiers. A targeted sequencing assay was used to sequence predictor genes in an independent cohort of 507 patients, whose accompanying data were used to evaluate performance of the risk classifiers.

RESULTS

We show that gene mutations modify the impact of standard clinical variables on patient outcome, and therefore their incorporation hones the accuracy of prediction. The mutation-based classification scheme robustly predicted patient outcome in the validation set (log rank P=6.77 × 10(-21); poor prognosis vs. good prognosis categories HR 10.4, 95% CI 3.21-33.6). The RSF-based approach also compares favorably with recently-published efforts to incorporate mutational information for MDS prognosis.

CONCLUSION

The results presented here support the inclusion of mutational information in prognostic classification of myeloid malignancies. Our classification scheme is implemented in a publicly available web-based tool (http://myeloid-risk.

CASE

edu/).

Severe Jaundice Increases Early Severe Morbidity and Decreases Long-Term Survival after Pancreaticoduodenectomy for Pancreatic Adenocarcinoma

BACKGROUND

The influence of jaundice on outcomes after pancreaticoduodenectomy (PD) for pancreatic ductal adenocarcinoma (PDAC) is debated. This study aimed to determine, in a large multicentric series, the influence of severe jaundice (serum bilirubin level ≥250 μmol/L and 300 μmol/L) on early severe morbidity and survival after PD.

STUDY DESIGN

From 2004 to 2009, twelve hundred patients (median age 66 years, 57% male) with resectable PDAC underwent PD. Patients who received preoperative biliary drainage for neoadjuvant treatment or cholangitis were excluded. Pre- and intraoperative data were collected by a standardized form. Serum bilirubin level and creatinine clearance were analyzed as categorical variables. Predictive factors of severe complications and poor survival (Kaplan-Meier method) were identified by univariate and multivariate analysis.

RESULTS

Median follow-up was 21 months (95% CI, 19-23). Operative mortality was 3.9% (n = 47), with no predictive factors in multivariate analysis. Severe complications (Dindo-Clavien grade III to IV) occurred in 22% (n = 268), with male sex (p = 0.025), America Society of Anesthesiologists score 3 to 4 (p = 0.022), serum bilirubin level ≥300 μmol/L (p = 0.034), and creatinine clearance <60 mL/min/1.73 m(2) (p = 0.013) identified as predictive factors in multivariate analysis. Overall 3-year survival rate was 41% (95% CI, 37-45%). In multivariate analysis, serum bilirubin level ≥300 μmol/L (p = 0.048), low-volume center (p < 0.001), venous resection (p = 0.014), N1 status (p < 0.01), R1 status (p < 0.001), and absence of adjuvant treatment (p < 0.001) negatively impacted survival. There was a negative relationship between survival at 12 months or later and higher rates of bilirubin. Presence of a biliary stent did not influence early or long-term results.

CONCLUSIONS

In this multicentric study, serum bilirubin level ≥300 μmol/L increased severe morbidity and decreased long-term survival after PD for PDAC. These findings suggest that biliary stenting is appropriately indicated before PD in patients with PDAC and severe jaundice.

The Association between Survival and the Pathologic Features of Periampullary Tumors Varies over Time

Introduction. Several histopathologic features of periampullary tumors have been shown to be correlated with prognosis. We evaluated their association with mortality at multiple time points. Methods. A retrospective chart review identified 207 patients with periampullary adenocarcinomas who underwent pancreaticoduodenectomy between January 1, 2001 and December 31, 2009. Clinicopathologic features were assessed, and the data were analyzed using univariate and multivariate methods. Results. In univariate analysis, perineural invasion had a strong association with 1-year mortality (OR 3.03, CI 1.42–6.47), and one lymph node (LN) increase in the LN ratio (LNR) equated with a 5-fold increase in mortality. In contrast, LN status (OR 6.42, CI 3.32–12.41) and perineural invasion (OR 5.44, CI 2.81–10.52) had the strongest associations with mortality at 3 years. Using Cox proportional hazards, perineural invasion (HR 2.61, CI 1.77–3.85) and LN status (HR 2.69, CI 1.84–3.95) had robust associations with overall mortality. Recursive partitioning analysis identified LNR as the most important risk factor for mortality at 1 and 3 years. Conclusions. Overall mortality was closely related to the LNR within the first year, while longer follow-up periods demonstrated a stronger association with perineural invasion and overall LN status. Therefore, the current staging for periampullary tumors may need to be updated to include the LNR.

Machine-learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry

OBJECTIVES

Using the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes.

SETTING

A regional cancer centre in Australia.

PARTICIPANTS

Disease-specific data from a purpose-built cancer registry (Evaluation of Cancer Outcomes (ECO)) from 869 patients were used to predict survival at 6, 12 and 24 months. The model was validated with data from a further 94 patients, and results compared to the assessment of five specialist oncologists. Machine-learning prediction using ECO data was compared with that using EAR and a model combining ECO and EAR data.

PRIMARY AND SECONDARY OUTCOME MEASURES

Survival prediction accuracy in terms of the area under the receiver operating characteristic curve (AUC).

RESULTS

The ECO model yielded AUCs of 0.87 (95% CI 0.848 to 0.890) at 6 months, 0.796 (95% CI 0.774 to 0.823) at 12 months and 0.764 (95% CI 0.737 to 0.789) at 24 months. Each was slightly better than the performance of the clinician panel. The model performed consistently across a range of cancers, including rare cancers. Combining ECO and EAR data yielded better prediction than the ECO-based model (AUCs ranging from 0.757 to 0.997 for 6 months, AUCs from 0.689 to 0.988 for 12 months and AUCs from 0.713 to 0.973 for 24 months). The best prediction was for genitourinary, head and neck, lung, skin, and upper gastrointestinal tumours.

CONCLUSIONS

Machine learning applied to information from a disease-specific (cancer) database and the EAR can be used to predict clinical outcomes. Importantly, the approach described made use of digital data that is already routinely collected but underexploited by clinical health systems.

Prognostic value of lymph node ratios in node positive rectal cancer treated with preoperative chemoradiation

BACKGROUND

To investigate the impact of the lymph node ratio (LNR) on the prognosis of patients with locally advanced rectal cancer undergoing pre-operative chemoradiation.

METHODS

Clinicopathologic and follow up data of 128 patients with stage III rectal cancer who underwent curative resection from 1996 to 2007 were reviewed. The patients were divided into two groups according to the lymph node ratio: LNR ≤ 0.2 (n=28), and >0.2 (n=100). Kaplan-Meier and the Cox proportional hazard regression models were used to evaluate the prognostic effects according to LNR.

RESULTS

Median numbers of lymph nodes examined and lymph nodes involved by tumour were 10.3 (range 2-28) and 5.8 (range 1-25), respectively, and the median LNR was 0.5 (range, 0-1.6). The 5-year survival rate significantly differed by LNR (≤ 0.2, 69%; >0.2, 19%; Log-rank p value < 0.001). LNR was also a significant prognostic factor of survival adjusted for age, sex, post-operative chemotherapy, total number of examined lymph nodes, metastasis and local recurrence (≤ 0.2, HR=1; >0.2, HR=4.8, 95%CI=2.1-11.1) and a significant predictor of local recurrence and distant metastasis during follow-up independently of total number of examined lymph node.

CONCLUSIONS

Total number of examined lymph nodes and LNR were significant prognostic factors for survival in patients with stage III rectal cancer undergoing pre-operative chemoradiotherapy.

What is the optimal means of staging colon cancer?

Although staging for colon cancer has become more complex over time, it is not clear that this complexity has improved prognostic assessment. Even with revisions in the 7th edition of the AJCC staging system, a clear rank order of prognosis from substage to substage has not been established. Improved staging models will need to be developed, and attempts at further identifying those high-risk patients within each stage may be clinically useful. Through improved quality measures with lymph node yield, advances in colon cancer staging accuracy have been made over the last decade. Determining how to incorporate ultrastaging and molecular techniques will be the challenge for future staging models.

[Predictive value of intraepithelial (CD3) T-lymphocyte infiltration in resected colorectal cancer]

INTRODUCTION

Colorectal cancer (CRC) can induce an anti-tumoral immune response mediated by T-lymphocytes, which express CD3.

OBJECTIVES

To analyze the prognostic value of tissue expression of intraepithelial CD3 (CD3I) both overall and in the early tumoral stages.

METHODS

We revised 251 patients with resected CRC and favorable clinical course. CD3I expression was analyzed by immunohistochemistry. Multivariate analysis was used to analyze the variables independently associated with survival. We analyzed CD3I(+) expression in relation to survival and tumoral progression, both overall and in patients with pTNM(I-II) stage tumors. The sensitivity, specificity, positive and negative predictive values and diagnostic accuracy of CD3I expression were analyzed.

RESULTS

A total of 25.9% of patients with CRC were CD3I(+). After a mean follow-up of 74 months, CD3I(+) expression showed a favorable prognostic value for survival in the multivariate analysis (p=0.045). Survival curves and absence of tumoral progression were more favorable in CD3I(+) cases, both overall (p=0.009 and p=0.004, respectively), and in stages I-II (p=0.029 and p=0.015). The specificity and positive predictive value of CD3I(+) were as follows: Survival: overall: specificity =0.89; positive predictive value =0.91. Stage (I-II): specificity =0.94; positive predictive value =0.98. Absence of tumoral progression: overall: specificity=0.89; positive predictive value =0.88. Stage (I-II): specificity =0.92; positive predictive value =0.96.

CONCLUSIONS

CD3I expression has an favorable independent prognostic value, with statistically significantly higher percentages of survival and absence of tumoral progression. This more favorable outcome is maintained in the less advanced stages (I-II). CD3I expression shows high specificity and positive predictive value.