A CT-based deep learning model predicts overall survival in patients with muscle invasive bladder cancer after radical cystectomy: a multicenter retrospective cohort study

BACKGROUND

Muscle invasive bladder cancer (MIBC) has a poor prognosis even after radical cystectomy (RC). Postoperative survival stratification based on radiomics and deep learning (DL) algorithms may be useful for treatment decision-making and follow-up management. This study was aimed to develop and validate a DL model based on preoperative computed tomography (CT) for predicting postcystectomy overall survival (OS) in patients with MIBC.

METHODS

MIBC patients who underwent RC were retrospectively included from four centers, and divided into the training, internal validation, and external validation sets. A DL model incorporated the convolutional block attention module (CBAM) was built for predicting OS using preoperative CT images. The authors assessed the prognostic accuracy of the DL model and compared it with classic handcrafted radiomics model and clinical model. Then, a deep learning radiomics nomogram (DLRN) was developed by combining clinicopathological factors, radiomics score (Rad-score) and deep learning score (DL-score). Model performance was assessed by C-index, KM curve, and time-dependent ROC curve.

RESULTS

A total of 405 patients with MIBC were included in this study. The DL-score achieved a much higher C-index than Rad-score and clinical model (0.690 vs. 0.652 vs. 0.618 in the internal validation set, and 0.658 vs. 0.601 vs. 0.610 in the external validation set). After adjusting for clinicopathologic variables, the DL-score was identified as a significantly independent risk factor for OS by the multivariate Cox regression analysis in all sets (all P <0.01). The DLRN further improved the performance, with a C-index of 0.713 (95% CI: 0.627-0.798) in the internal validation set and 0.685 (95% CI: 0.586-0.765) in external validation set, respectively.

CONCLUSIONS

A DL model based on preoperative CT can predict survival outcome of patients with MIBC, which may help in risk stratification and guide treatment decision-making and follow-up management.

The top 100 most-cited papers in incisional hernia: a bibliometric analysis from 2003 to 2023

PURPOSE

Incisional hernia (IH) is one of the most common complications after abdominal surgeries and may bring great suffering to patients. This study aims to evaluate the global trends in IH research from 2003 to 2023 and visualize the frontiers using bibliometric analysis.

METHODS

The literature search was conducted on the Web of Science for IH studies published from 2003 to 2023 and sorted by citation frequency. The top 100 most-cited articles were analyzed by the annual publication number, prolific countries and institutions, influential author and journal, and the number of citations through descriptive statistics and visualization.

RESULTS

The top paper was cited 1075 times and the median number of citations was 146. All studies were published between 2003 and 2019 and the most prolific year was 2003 with 14 articles. Jeekel J and Rosen M were regarded as the most productive authors with ten articles each and acquired 2738 and 2391 citations, respectively. The top three institutions with the most productive articles were Erasmus Mc, Carolinas Med Ctr, and Univ Utah, while the top three countries were the United States, Netherlands and Germany. The most frequent keyword was "incisional hernia" with 55 occurrences, followed by "mesh repair", "randomized controlled trial", and "polypropylene".

CONCLUSION

The 100 most-cited papers related to IH were published predominantly by USA and European countries, with randomized controlled trial (RCT) and observational study designs, addressing topics related to risk factors, complications, mesh repair, and mesh components.

The causal association between body fat distribution and risk of abdominal wall hernia: a two-sample Mendelian randomization study

PURPOSE

Obesity and a high body mass index (BMI) are considered as risk factors for abdominal wall hernia (AWH). However, anthropometric measures of body fat distribution (BFD) seem to be better indicators in the hernia field. This Mendelian randomization analysis aimed to generate more robust evidence for the impact of waist circumstance (WC), body, trunk, arm, and leg fat percentages (BFP, TFP, AFP, LFP) on AWH.

METHODS

A univariable MR design was employed and the summary statistics allowing for assessment were obtained from the genome-wide association studies (GWASs). An inverse variance weighted (IVW) method was applied as the primary analysis, and the odds ratio value was used to evaluate the causal relationship between BFD and AWH.

RESULTS

None of the MR-Egger regression intercepts deviated from null, indicating no evidence of horizontal pleiotropy (p > 0.05). The Cochran Q test showed heterogeneity between the genetic IVs for WC (p = 0.005; p = 0.005), TFP (p < 0.001; p < 0.001), AFP-L (p = 0.016; p = 0.015), LFP-R (p = 0.012; p = 0.009), and LFP-L (p < 0.001; p < 0.001). Taking the IVW random-effects model as gold standard, each standard deviation increment in genetically determined WC, BFP, TFP, AFP-R, AFP-L, LFP-R, and LFP-L raised the risk of AWH by 70.9%, 70.7%, 56.5%, 69.7%, 78.3%, 87.7%, and 72.5%, respectively.

CONCLUSIONS

This study proves the causal relationship between AWH and BFD, attracting more attention from BMI to BFD. It provides evidence-based medical evidence that healthy figure management can prevent AWH.

Risk factors for incisional hernia after gastrointestinal surgeries in non-tumor patients

PURPOSE

Incisional hernia (IH) is a common secondary ventral hernia after abdominal incisions and there is still little reliable evidence to predict and prevent IH. This study aimed to estimate risk factors of its incidence, especially concentrating on blood results.

METHODS

96 patients received midline laparotomy for gastrointestinal benign diseases and suffered from IH were enrolled in the IH group. A control group of 192 patients were randomly selected from patients underwent midline laparotomy for gastrointestinal benign diseases without IH.

RESULTS

Patients in the IH group exhibited higher age (P < 0.001), BMI (P < 0.001), hernia history (P = 0.001) and laparotomy history (P < 0.001). Rate of coronary heart disease (P = 0.046), hypertension (P < 0.001), diabetes (P = 0.008), incisional infection (P = 0.004) and emergency surgery (P = 0.041) were also higher in the IH group. Patients with IH had lower levels of Hb (P = 0.002), TP (P = 0.013), ALB (P < 0.001), A/G (P = 0.019), PA (P < 0.001), HDL-C (P = 0.008) and ApoA1 (P = 0.005). Meanwhile, patients in the control group bore lower levels of LDH (P = 0.008), GLU (P = 0.007), BUN (P = 0.048), UA (P = 0.021), TG (P = 0.011), TG/HDL-C (P = 0.002), TC/HDL-C (P = 0.013), ApoB/ApoA1 (P = 0.001) and Lp(a) (P = 0.001). A multivariate logistic regression revealed that high BMI, laparotomy history, incisional infection, decreased PA, elevated levels of UA, Lp(a) and ApoB/ApoA1 were independent risk factors of IH.

CONCLUSION

This is the first study to reveal the relationship between IH and serum biochemical levels, and give a prediction through the nomograph model. These results will help surgeons identify high-risk patients, and take measures to prevent IH during the perioperative period.

Development and validation of a CT-based deep learning radiomics nomogram to predict muscle invasion in bladder cancer

Objective

This study aimed to develop a nomogram combining CT-based handcrafted radiomics and deep learning (DL) features to preoperatively predict muscle invasion in bladder cancer (BCa) with multi-center validation.

Methods

In this retrospective study, 323 patients underwent radical cystectomy with pathologically confirmed BCa were enrolled and randomly divided into the training cohort (n = 226) and internal validation cohort (n = 97). And fifty-two patients from another independent medical center were enrolled as an independent external validation cohort. Handcrafted radiomics and DL features were constructed from preoperative nephrographic phase CT images. Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in train cohort. Multivariate logistic regression was used to develop the predictive model and a deep learning radiomics nomogram (DLRN) was constructed. The predictive performance of models was evaluated by area under the curves (AUC) in the three cohorts. The calibration and clinical usefulness of DLRN were estimated by calibration curve and decision curve analysis.

Results

The nomogram that incorporated radiomics signature and DL signature demonstrated satisfactory predictive performance for differentiating non-muscle invasive bladder cancer (NMIBC) from muscle invasive bladder cancer (MIBC), with an AUC of 0.884 (95 % CI: 0.813-0.953) in internal validation cohort and 0.862 (95 % CI: 0.756-0.968) in external validation cohort, respectively. Decision curve analysis confirmed the clinical usefulness of the nomogram.

Conclusions

A CT-based deep learning radiomics nomogram exhibited a promising performance for preoperative prediction of muscle invasion in bladder cancer, and may be helpful in the clinical decision-making process.

Validity of a multiphase CT-based radiomics model in predicting the Leibovich risk groups for localized clear cell renal cell carcinoma: an exploratory study

OBJECTIVE

To develop and validate a multiphase CT-based radiomics model for preoperative risk stratification of patients with localized clear cell renal cell carcinoma (ccRCC).

METHODS

A total of 425 patients with localized ccRCC were enrolled and divided into training, validation, and external testing cohorts. Radiomics features were extracted from three-phase CT images (unenhanced, arterial, and venous), and radiomics signatures were constructed by the least absolute shrinkage and selection operator (LASSO) regression algorithm. The radiomics score (Rad-score) for each patient was calculated. The radiomics model was established and visualized as a nomogram by incorporating significant clinical factors and Rad-score. The predictive performance of the radiomics model was evaluated by the receiver operating characteristic curve, calibration curve, and decision curve analysis (DCA).

RESULTS

The AUC of the triphasic radiomics signature reached 0.862 (95% CI: 0.809-0.914), 0.853 (95% CI: 0.785-0.921), and 0.837 (95% CI: 0.714-0.959) in three cohorts, respectively, which were higher than arterial, venous, and unenhanced radiomics signatures. Multivariate logistic regression analysis showed that Rad-score (OR: 4.066, 95% CI: 3.495-8.790) and renal vein invasion (OR: 12.914, 95% CI: 1.118-149.112) were independent predictors and used to develop the radiomics model. The radiomics model showed good calibration and discrimination and yielded an AUC of 0.872 (95% CI: 0.821-0.923), 0.865 (95% CI: 0.800-0.930), and 0.848 (95% CI: 0.728-0.967) in three cohorts, respectively. DCA showed the clinical usefulness of the radiomics model in predicting the Leibovich risk groups.

CONCLUSIONS

The radiomics model can be used as a non-invasive and useful tool to predict the Leibovich risk groups for localized ccRCC patients.

CRITICAL RELEVANCE STATEMENT

The triphasic CT-based radiomics model achieved favorable performance in preoperatively predicting the Leibovich risk groups in patients with localized ccRCC. Therefore, it can be used as a non-invasive and effective tool for preoperative risk stratification of patients with localized ccRCC.

KEY POINTS

• The triphasic CT-based radiomics signature achieves better performance than the single-phase radiomics signature. • Radiomics holds prospects in preoperatively predicting the Leibovich risk groups for ccRCC. • This study provides a non-invasive method to stratify patients with localized ccRCC.

Study on self-management of real-time and individualized support in stroke patients based on resilience: a protocol for a randomized controlled trial

BACKGROUND

The transitional period from hospital to home is vital for stroke patients, but it poses serious challenges. Good self-management ability can optimize disease outcomes. However, stroke patients in China have a low level of self-management ability during the transitional period, and a lack of effective support may be the reason. With the rapid development of technology, using wearable monitors to achieve real-time and individualized support may be the key to solving this problem. This study uses a randomized controlled trial design to assess the efficacy of using wearable technology to realize real-time and individualized self-management support in stroke patients' self-management behavior during the transitional period following discharge from hospital.

METHODS

This parallel-group randomized controlled trial will be conducted in two hospitals and patients' homes. A total of 183 adult stroke patients will be enrolled in the study and randomly assigned to three groups in a 1:1:1 ratio. The smartwatch intervention group (n = 61) will receive Real-time and Individualized Self-management Support (RISS) program + routine care, the wristband group (n = 61) will wear a fitness tracker (self-monitoring) + routine care, and the control group (n = 61) will receive routine stroke care. The intervention will last for 6 months. The primary outcomes are neurological function status, self-management behavior, quality of life, biochemical indicators, recurrence rate, and unplanned readmission rate. Secondary outcomes are resilience, patient activation, psychological status, and caregiver assessments. The analysis is intention-to-treat. The intervention effect will be evaluated at baseline (T0), 2 months after discharge (T1), 3 months after discharge (T2), and 6 months after discharge (T3).

DISCUSSION

The cloud platform designed in this study not only has the function of real-time recording but also can push timely solutions when patients have abnormal conditions, as well as early warnings or alarms. This study could also potentially help patients develop good self-management habits through resilience theory, wearable devices, and individualized problem-solution library of self-management which can lay the foundation for long-term maintenance and continuous improvement of good self-management behavior in the future.

TRIAL REGISTRATION

The ethics approval has been granted by the Ethics Committee of West China Hospital, Sichuan University (2022-941). All patients will be informed of the study details and sign a written informed consent form before enrollment. The research results will be reported in conferences and peer-reviewed publications. The trial registration number is ChiCTR2300070384 . Registered on 11 April 2023.

Development of a 7-miRNA prognostic signature for patients with bladder cancer

BACKGROUND

Bladder carcinoma (BC) represents one of the most prevalent malignant cancers, while predicting its clinical outcomes using traditional indicators is difficult. This study aimed to develop a miRNA signature for the prognostic prediction of patients with BC.

MATERIALS AND METHODS

MiRNAs that expressed differentially were identified between 413 BC and 19 non-tumor patients, whose prognostic values were evaluated using univariate and multivariate Cox regression analyses. The independent prognostic factors were screened out and were used to establish a signature. The risk score of the signature was calculated. Receiver operating characteristic (ROC) curves and Kaplan-Meier curves were used to verify the predictive performance of the miRNA signature and the risk score. A nomogram was constructed which integrated with the miRNA signature and clinical parameters. Experiments were performed.

RESULTS

7 prognosis related miRNAs were selected as independent risk factors, and a 7-miRNA signature was constructed, with an area under ROC (AUC) of 0.721. The 7-miRNA-signature based risk score acts as an independent prognostic factor, with satisfactory predictive performance (AUC = 0.744). Increased miR-337-3p expressions were detected in tumor samples and BC cell lines than in non-tumorigenic tissues and cell lines. Experiments suggested that miR-337-3p induces the proliferation, migration, and invasion of BC cells.

CONCLUSION

The constructed 7-miRNA signature is a promising biomarker for predicting the prognosis of patients with BC, and miR-337-3p may act as a candidate therapeutic target in BC treatments.

A Novel Nomogram Integrated with Systemic Inflammation Markers and Traditional Prognostic Factors for Adverse Events' Prediction in Patients with Chronic Heart Failure in the Southwest of China

Objective

Inflammation contributes to the pathogenesis and progression of heart failure (HF). This study aimed to construct a nomogram based on systemic inflammatory markers and traditional prognostic factors to assess the risk of adverse outcomes (cardiovascular readmission and all-cause death) in patients with chronic heart failure (CHF).

Methods

Data were retrospectively collected from patients with HF admitted to the Department of Cardiovascular Medicine at the First Affiliated Hospital of Chongqing Medical University from January 2018 to April 2020, and each patient had complete follow-up information. The follow-up duration was from June 2018 to May 31, 2022. 550 patients were included and randomly assigned to the derivation and validation cohorts with a ratio of 7:3, and prognostic risk factors of CHF were identified by Cox regression analysis. The nomogram chart scoring model was constructed.

Results

The Cox multivariate regression analysis showed that traditional prognostic factors such as age (P=0.011), BMI (P=0.048), NYHA classification (P<0.001), creatinine (P<0.001), and systemic inflammatory markers including LMR (P=0.001), and PLR (P=0.015) were independent prognostic factors for CHF patients. Integrated with traditional and inflammatory prognostic factors, a nomogram was established, which yielded a C-index value of 0.739 (95% CI: 0.714-0.764) in the derivation cohort and 0.713 (95% CI: 0.668-0.758) in the validation cohort, respectively. The calibration curves exhibited good performance of the nomogram in predicting the adverse outcomes for patients with CHF. In subgroups (HFrEF, HFmrEF, and HFpEF groups), the systematic inflammatory markers-based nomograms proved to be effective prediction tools for patients' adverse overcomes, as well.

Conclusion

The nomogram combining systemic inflammatory markers and traditional risk factors has satisfactory predictive performance for adverse outcomes (mortality and readmission) in patients with CHF.

Associations of systemic inflammatory markers with the risks of chronic heart failure: A case-control study

OBJECTIVE

As a greater proportion of patients survived their initial cardiac insult, Chronic Heart Failure (CHF) is becoming a major cause of worldwide morbidity and mortality. However, the mechanism underlying the inflammation in patients with CHF has not yet been elaborated. This study aims to explore the associations between inflammation and CHF patients, and the predictive performance of inflammatory indicators in identifying patients with CHF.

METHODS

A matched case-control study was conducted by recruiting 385 patients who were diagnosed with CHF from January 2018 to December 2019 in The First Affiliated Hospital of Chongqing Medical University. Each CHF patient was matched against one control subject without CHF on the criteria of age, sex, Body Mass Index (BMI), smoking status, and comorbidities. The clinical data and systemic inflammatory indicators were compared between the two groups, independent risk factors of CHF were identified by multivariate regression analysis, and the predictive values of systemic inflammatory indicators for CHF were analyzed by Receiver Operating Characteristic (ROC) curve analysis.

RESULTS

After processed in the univariate and multivariate regression analysis models, three systemic inflammatory indicators (hs-CRP [high sensitivity C Reactive Protein], LMR [lymphocyte-to-monocyte ratio], and Monocyte-to-High-density-lipoprotein Ratio [MHR]) were considered as independent predictors of CHF, among which the hs-CRP exhibited the best predictive performance (AUC = 0.752, 95%CI 0.717‒0.786, p < 0.001), followed by LMR (AUC = 0.711, 95% CI 0.675‒0.747, p < 0.001) and MHR (AUC = 0.673, 95% CI 0.635‒0.710, p < 0.001). The three-indicator combination showed an improved diagnostic performance (AUC = 0.757, 95% CI 0.724‒0.791, p < 0.001). In addition, the results of subgroup comparisons demonstrated that hs-CRP and MHR were associated with the severity of CHF (p < 0.001).

CONCLUSIONS

The systemic inflammatory indicators such as hs-CRP, LMR, and MHR were independently correlated with the attack of CHF and might be the complementary markers of the diagnosis of CHF.

A CT-Based Radiomics Nomogram Integrated With Clinic-Radiological Features for Preoperatively Predicting WHO/ISUP Grade of Clear Cell Renal Cell Carcinoma

Objective

This study aims to develop and validate a CT-based radiomics nomogram integrated with clinic-radiological factors for preoperatively differentiating high-grade from low-grade clear cell renal cell carcinomas (CCRCCs).

Methods

370 patients with complete clinical, pathological, and CT image data were enrolled in this retrospective study, and were randomly divided into training and testing sets with a 7:3 ratio. Radiomics features were extracted from nephrographic phase (NP) contrast-enhanced images, and then a radiomics model was constructed by the selected radiomics features using a multivariable logistic regression combined with the most suitable feature selection algorithm determined by the comparison among least absolute shrinkage and selection operator (LASSO), recursive feature elimination (RFE) and ReliefF. A clinical model was established using clinical and radiological features. A radiomics nomogram was constructed by integrating the radiomics signature and independent clinic-radiological features. Performance of these three models was assessed using receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA).

Results

Using multivariate logistic regression analysis, three clinic-radiological features including intratumoral necrosis (OR=3.00, 95% CI=1.30-6.90, p=0.049), intratumoral angiogenesis (OR=3.28, 95% CI=1.22-8.78, p=0.018), and perinephric metastasis (OR=2.90, 95% CI=1.03-8.17, p=0.044) were found to be independent predictors of WHO/ISUP grade in CCRCC. Incorporating the above clinic-radiological predictors and radiomics signature constructed by LASSO, a CT-based radiomics nomogram was developed, and presented better predictive performance than clinic-radiological model and radiomics signature model, with an AUC of 0.891 (95% CI=0.832-0.962) and 0.843 (95% CI=0.718-0.975) in the training and testing sets, respectively. DCA indicated that the nomogram has potential clinical usefulness.

Conclusion

The CT-based radiomics nomogram is a promising tool to predict WHO/ISUP grade of CCRCC preoperatively and noninvasively.

Machine learning-based CT radiomics approach for predicting WHO/ISUP nuclear grade of clear cell renal cell carcinoma: an exploratory and comparative study

Purpose

To investigate the predictive performance of machine learning-based CT radiomics for differentiating between low- and high-nuclear grade of clear cell renal cell carcinomas (CCRCCs).

Methods

This retrospective study enrolled 406 patients with pathologically confirmed low- and high-nuclear grade of CCRCCs according to the WHO/ISUP grading system, which were divided into the training and testing cohorts. Radiomics features were extracted from nephrographic-phase CT images using PyRadiomics. A support vector machine (SVM) combined with three feature selection algorithms such as least absolute shrinkage and selection operator (LASSO), recursive feature elimination (RFE), and ReliefF was performed to determine the most suitable classification model, respectively. Clinicoradiological, radiomics, and combined models were constructed using the radiological and clinical characteristics with significant differences between the groups, selected radiomics features, and a combination of both, respectively. Model performance was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses.

Results

SVM-ReliefF algorithm outperformed SVM-LASSO and SVM-RFE in distinguishing low- from high-grade CCRCCs. The combined model showed better prediction performance than the clinicoradiological and radiomics models (p < 0.05, DeLong test), which achieved the highest efficacy, with an area under the ROC curve (AUC) value of 0.887 (95% confidence interval [CI] 0.798–0.952), 0.859 (95% CI 0.748–0.935), and 0.828 (95% CI 0.731–0.929) in the training, validation, and testing cohorts, respectively. The calibration and decision curves also indicated the favorable performance of the combined model.

Conclusion

A combined model incorporating the radiomics features and clinicoradiological characteristics can better predict the WHO/ISUP nuclear grade of CCRCC preoperatively, thus providing effective and noninvasive assessment.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-021-01107-1.