A nomogram for predicting bowel obstruction in preoperative colorectal cancer patients with clinical characteristics

Comparison of deep learning models to traditional Cox regression in predicting survival of colon cancer: Based on the SEER database

BACKGROUND AND AIM

In this study, a deep learning algorithm was used to predict the survival rate of colon cancer (CC) patients, and compared its performance with traditional Cox regression.

METHODS

In this population-based cohort study, we used the characteristics of patients diagnosed with CC between 2010 and 2015 from the Surveillance, Epidemiology and End Results (SEER) database. The population was randomized into a training set (n = 10 596, 70%) and a test set (n = 4536, 30%). Brier scores, area under the (AUC) receiver operating characteristic curve and calibration curves were used to compare the performance of the three most popular deep learning models, namely, artificial neural networks (ANN), deep neural networks (DNN), and long-short term memory (LSTM) neural networks with Cox proportional hazard (CPH) model.

RESULTS

In the independent test set, the Brier values of ANN, DNN, LSTM and CPH were 0.155, 0.149, 0.148, and 0.170, respectively. The AUC values were 0.906 (95% confidence interval [CI] 0.897-0.916), 0.908 (95% CI 0.899-0.918), 0.910 (95% CI 0.901-0.919), and 0.793 (95% CI 0.769-0.816), respectively. Deep learning showed superior promising results than CPH in predicting CC specific survival.

CONCLUSIONS

Deep learning showed potential advantages over traditional CPH models in terms of prognostic assessment and treatment recommendations. LSTM exhibited optimal predictive accuracy and has the ability to provide reliable information on individual survival and treatment recommendations for CC patients.

Endoscopic obstruction predominantly occurs in right-side colon cancer and endoscopic obstruction with tumor size ≤ 5 cm seems poor prognosis in colorectal cancer

Background

Endoscopic obstruction (eOB) is associated with a poor prognosis in colorectal cancer (CRC). Our study aimed to investigate the association between tumor location and eOB, as well as the prognostic differences among non-endoscopic obstruction (N-eOB), eOB with tumor size ≤ 5 cm, and eOB with tumor size > 5 cm in non-elderly patients.

Methods

We retrospectively reviewed the clinicopathological variables of 230 patients with CRC who underwent curative surgery. The multivariable logistic regression model was used to identify risk factors for eOB. The association between eOB with tumor size ≤ 5 cm and disease-free survival (DFS) was evaluated using multivariate cox regression analysis.

Results

A total of 87 patients had eOB while 143 had N-eOB. In multivariate analysis, preoperative carcinoembryonic antigen (p = 0.014), tumor size (p = 0.010), tumor location (left-side colon; p = 0.033; rectum; p < 0.001), and pT stage (T3, p = 0.009; T4, p < 0.001) were significant factors of eOB. The DFS rate for eOB with tumor size ≤ 5 cm was significantly lower (p < 0.001) in survival analysis. The eOB with tumor size ≤ 5 cm (p = 0.012) was an unfavorable independent factor for DFS.

Conclusions

The patients with eOB were significantly associated with right-side colon cancer as opposed to left-side colon cancer and rectal cancer. The eOB with tumor size ≤ 5 cm was an independent poor prognostic factor. Further studies are needed to target these high-risk groups.

A nomogram for predicting the recurrence of small bowel obstruction after gastrectomy in patients with gastric cancer

BACKGROUND

This study aimed to create a nomogram for predicting the recurrence of small bowel obstruction (SBO) after gastrectomy in patients with gastric cancer (GC) in order to provide better guidance for its diagnosis and treatment.

METHODS

A total of 173 patients undergone gastrectomy and developed SBO from January 2015 to October 2022 were admitted into this case-control study. The risk factors of postoperative recurrent SBO were analyzed by univariate and multivariate regression, and a nomogram for predicting the recurrent SBO after gastrectomy was developed using R Studio.

RESULTS

Thirty-nine cases of postoperative recurrent SBO occurred among the 173 GC patients who underwent radical gastrectomy, and the percentage of recurrent SBO was 22.54% (39/173). Age [odds ratio (OR) = 0.938, p = 0.026], WBC count (OR = 1.547, p < 0.001), tumor size (OR = 1.383, p = 0.024), postoperative metastasis (OR = 11.792, p = 0.030), and the interval from gastrectomy to first SBO (OR = 1.057, p < 0.001) were all identified as independent risk factors for postoperative recurrent SBO by logistic regression analysis. The receiver operating characteristic curve, the calibration curve, the model consistency index, and the decision curve analysis showed that the nomogram had good predictive performance.

CONCLUSION

Based on these factors, we created a nomogram to predict the occurrence of postoperative recurrent SBO. This novel nomogram could serve as a crucial early warning indicator that would guide doctors to make informed decisions while managing patients with gastric cancer.

Development and validation of a nomogram for preoperative prediction of tumor deposits in colorectal cancer

BACKGROUND

Based on the clinical data of colorectal cancer (CRC) patients who underwent surgery at our institution, a model for predicting the formation of tumor deposits (TDs) in this patient population was established.

AIM

To establish an effective model for predicting TD formation, thus enabling clinicians to identify CRC patients at high risk for TDs and implement personalized treatment strategies.

METHODS

CRC patients (n = 645) who met the inclusion criteria were randomly divided into training (n = 452) and validation (n = 193) cohorts using a 7:3 ratio in this retrospective analysis. Least absolute shrinkage and selection operator regression was employed to screen potential risk factors, and multivariable logistic regression analysis was used to identify independent risk factors. Subsequently, a predictive model for TD formation in CRC patients was constructed based on the independent risk factors. The discrimination ability of the model, its consistency with actual results, and its clinical applicability were evaluated using receiver-operating characteristic curves, area under the curve (AUC), calibration curves, and decision curve analysis (DCA).

RESULTS

Thirty-four (7.5%) patients with TDs were identified in the training cohort based on postoperative pathological specimens. Multivariate logistic regression analysis identified female sex, preoperative intestinal obstruction, left-sided CRC, and lymph node metastasis as independent risk factors for TD formation. The AUCs of the nomogram models constructed using these variables were 0.839 and 0.853 in the training and validation cohorts, respectively. The calibration curve demonstrated good consistency, and the training cohort DCA yielded a threshold probability of 7%-78%.

CONCLUSION

This study developed and validated a nomogram with good predictive performance for identifying TDs in CRC patients. Our predictive model can assist surgeons in making optimal treatment decisions.

New Personal Model for Forecasting the Outcome of Patients with Histological Grade III-IV Colorectal Cancer Based on Regional Lymph Nodes

Background

Metastases at regional lymph nodes could easily occur in patients with high-histological-grade colorectal cancer (CRC). However, few models were built on the basis of lymph nodes to predict the outcome of patients with histological grades III-IV CRC.

Methods

Data in the Surveillance, Epidemiology, and End Results databases were used. Univariate and multivariate analyses were performed. A personalized prediction model was built in accordance with the results of the analyses. A nomogram was tested in two datasets and assessed using a calibration curve, a consistency index (C-index), and an area under the curve (AUC).

Results

A total of 14,039 cases were obtained from the database. They were separated into two groups (9828 cases for constructing the model and 4211 cases for validation). Logistic and Cox regression analyses were then conducted. Factors such as log odds of positive lymph nodes (LODDS) were utilized. Then, a personalized prediction model was established. The C-index in the construction and validation groups was 0.770. The 1-, 3-, and 5-year AUCs were 0793, 0.828, and 0.830 in the construction group, respectively, and 0.796, 0.833, and 0.832 in the validation group, respectively. The calibration curves showed well consistency in the 1-, 3- and 5-year OS between prediction and reality in both groups.

Conclusion

The nomogram built based on LODDS exhibited considerable reliability and accuracy.

Novel nomogram for predicting risk of early postoperative small bowel obstruction after right colectomy for cancer

Background

Early postoperative small bowel obstruction (EPSBO) is a common complication after colorectal cancer surgery. Few studies have specifically studied risk factors for early small bowel obstruction after right colectomy, especially in establishing predictive models. The purpose of the current study was to establish an effective nomogram to predict the incidence of EPSBO after right colectomy.

Methods

The current study retrospectively analyzed data from a total of 424 patients who underwent right colectomy in a local hospital from January 2014 to March 2021. A logistic regression model was used to identify potential risk factors for EPSBO after right colectomy. A nomogram was established by independent risk factors, and the prediction performance of the model was evaluated using an area under the receiver operating characteristic (ROC) curve and calibration chart.

Results

A total of 45 patients (10.6%) developed early small bowel obstruction after right colectomy. Male sex, history of abdominal surgery, open surgery, long operative time, anastomotic leakage, and preoperative albumin were closely related to EPSBO. Analysis of postoperative rehabilitation indices showed that EPSBO remarkably slowed the postoperative rehabilitation speed of patients. Multivariate logistic regression analysis showed that male sex, open surgery, operative time, and anastomotic leakage were independent risk factors (P < 0.05), and the operation time had the greatest impact on EPSBO. On the basis of multivariate logistic regression, a nomogram was constructed, which showed moderate accuracy in predicting EPSBO, with a C-statistic of 0.716. The calibration chart showed good consistency between the predicted probability and ideal probability.

Conclusion

The current study constructed a nomogram based on the clinical data of patients who underwent right colectomy, which had moderate predictability and could provide reference value for clinicians to evaluate the risk of EPSBO.

CLCA4 and MS4A12 as the significant gene biomarkers of primary colorectal cancer

Background: Primary colorectal cancer (PCRC) is a common digestive tract cancer in the elderly. However, the treatment effect of PCRC is still limited, and the long-term survival rate is low. Therefore, further exploring the pathogenesis of PCRC, and searching for specific molecular targets for diagnosis are the development trends of precise medical treatment, which have important clinical significance.

Methods: The public data were downloaded from Gene Expression Omnibus (GEO) database. Verification for repeatability of intra-group data was performed by Pearson’s correlation test and principal component analysis. Differentially expressed genes (DEGs) between normal and PCRC were identified, and the protein–protein interaction (PPI) network was constructed. Significant module and hub genes were found in the PPI network. A total of 192 PCRC patients were recruited between 2010 and 2019 from the Fourth Hospital of Hebei Medical University. RT-PCR was used to measure the relative expression of CLCA4 and MS4A12. Furthermore, the study explored the effect of expression of CLCA4 and MS4A12 for overall survival.

Results: A total of 53 DEGs were identified between PCRC and normal colorectal tissues. Ten hub genes concerned to PCRC were screened, namely CLCA4, GUCA2A, GCG, SST, MS4A12, PLP1, CHGA, PYY, VIP, and GUCA2B. The PCRC patients with low expression of CLCA4 and MS4A12 has a worse overall survival than high expression of CLCA4 and MS4A12 (P<0.05).

Conclusion: The research of DEGs in PCRC (53 DEGs, 10 hub genes, especially CLCA4 and MS4A12) and related signaling pathways is conducive to the differential analysis of the molecular mechanism of PCRC.

Construction and validation a nomogram to predict overall survival for colorectal signet ring cell carcinoma

To construct and validate a nomogram to predict the overall survival (OS) of colorectal signet ring cell carcinoma (SRCC). The potentially eligible cases were obtained against the SEER database from 2004 to 2015. Log-rank test and Cox analysis were conducted to identify the independent prognostic factors for predicting OS. The identified prognostic factors were later integrated for the construction of an OS prediction nomogram. Altogether 2904 eligible cases were identified, and the median survival time was 18 (range: 0–155) months. As suggested by multivariate analysis, age, primary site, grade, tumor size, T stage, N stage, M stage, surgery, lymph node dissection and chemotherapy were identified as the independent factors for predicting OS. Afterwards, the above variables were incorporated into the nomogram. The C-index indicated better discriminatory ability of the nomogram than AJCC 8th TNM staging and SEER summary stage systems (both P < 0.001). Calibration plots further showed good consistency between the nomogram prediction and actual observation. The time independent area under the curves (tAUCs) for 3-year and 5-year OS in nomogram were larger than AJCC and SEER summary stage system. The constructed nomogram could potentially predict the survival of colorectal SRCC individuals.

Superior survival in right-sided versus left-sided colon signet ring cell carcinoma

This study aimed to explore the association of tumor sidedness with the prognosis of patients with colon signet ring cell carcinoma (SRCC). Eligible patients were retrieved from the Surveillance, Epidemiology, and End Results database between 2004 and 2015. Cancer-specific survival (CSS) and overall survival (OS) were compared between patients with left-sided colon SRCC and those with right-sided lesions. A total of 2660 patients were included, among them, 1983 (74.5%) had right-sided colon SRCC. Compared to patients with left-sided colon SRCC, those who had the right-sided colon SRCC showed higher proportion of white race, female, aged ≥ 65 years, receiving total colectomy and ≥ 4 regional lymph node dissection; while had lower proportion of advanced AJCC stage. Besides, right-sided patients exhibited superior 5-year CSS (32.74% vs. 25.89%, P = 0.001) and OS (27.38% vs. 23.02%, P = 0.024) rates compared with left-sided ones. Multivariate analysis revealed that tumor sidedness was an independent prognostic factor. To be specific, patients with right-sided colon SRCC showed better CSS (HR: 0.873; 95% CI 0.777–0.981; P = 0.023) and OS (HR: 0.838; 95% CI 0.753–0.965; P = 0.002). Moreover, subgroup analysis demonstrated superior CSS and OS for right-sided patients in most subgroups. Tumor sidedness was an independent prognostic indicator for colon SRCC. Besides, patients with right-sided colon SRCC have superior prognosis than those with left-sided lesions.

Clinicopathological characteristics and survival in colorectal signet ring cell carcinoma: a population-based study

We aimed to reveal clinicopathological features and explore survival-related factors of colorectal signet ring cell carcinoma (SRCC). A population-based study was carried out to investigate colorectal SRCC by using data extracted from the surveillance, epidemiology and end results (SEER) database between 2004 and 2015. In total, 3,278 patients with colorectal SRCC were identified, with a median age of 63 (12–103) years old. The lesions of most patients (60.49%) were located in the cecum–transverse colon. In addition, 81.27% patients had advanced clinical stage (stage III/IV), and 76.69% patients had high pathological grade. The 3–, 5–year cancer‐specific survival and overall survival rate was 35.76%, 29.32% and 32.32%, 25.14%. Multivariate analysis revealed that primary site in cecum–transverse colon, married, received surgery, lymph node dissections ≥ 4 regional lymph nodes were independent favorable prognostic. Meanwhile, aged ≥ 65 years, higher grade, tumor size ˃5 cm and advanced AJCC stage were associated with poor prognosis. Patient age, tumor grade, marital status, tumor size, primary tumor location, AJCC stage, surgery and number of dissected lymph node had significant correlation with prognosis of colorectal SRCC.

Preoperative anxiety in Chinese colorectal cancer patients: The role of social support, self-esteem and coping styles

BACKGROUND

Relatively little is known about preoperative anxiety and its associated factors with colorectal cancer, which is one of the most prevalent cancers. We aimed to investigate preoperative anxiety and its associated social, psychological and coping factors based on the disclosure/nondisclosure of cancer diagnosis.

METHODS

A cross-sectional study was conducted in consecutive colorectal cancer inpatients (N = 434), whose anxiety was assessed based on semi-structured interview, demographic-clinical variables, social support, self-esteem and coping styles (acceptance-resignation, confrontation, avoidance). Hierarchical regression analyses were conducted to explore the relationships between social, psychological, coping factors and preoperative anxiety.

RESULTS

There was no significant difference in preoperative anxiety (χ² = 1.031, p = .31) between the disclosure and nondisclosure groups. Social, psychological and coping factors together accounted for an additional variance of preoperative anxiety (disclosure: 22%; nondisclosure: 20.8%). Social support (β = -0.17, p = .004), self-esteem (β = -0.22, p = .001) and coping styles (acceptance-resignation: β = 0.32, p < .001; confrontation: β = 0.13, p = .06; avoidance: β = -0.17, p = .04) were associated with preoperative anxiety in the nondisclosure group. For the disclosure group, acceptance-resignation was the only significantly associated factor of preoperative anxiety (β = 0.37, p < .001).

CONCLUSIONS

Coping styles, such as acceptance-resignation and confrontation, could aggravate preoperative anxiety. Avoidance, social support and self-esteem might be helpful in preventing preoperative anxiety. These findings highlight the importance of providing psychological interventions for cancer patients by integrating social support, self-esteem and coping styles when disclosing a cancer diagnosis.