Explainable machine learning predicts survival of retroperitoneal liposarcoma: A study based on the SEER database and external validation in China.

OBJECTIVE: We have developed explainable machine learning models to predict the overall survival (OS) of retroperitoneal liposarcoma (RLPS) patients. This approach aims to enhance the explainability and transparency of our modeling results. METHODS: We collected clinicopathological information of RLPS patients from The Surveillance, Epidemiology, and End Results (SEER) database and allocated them into training and validation sets with a 7:3 ratio. Simultaneously, we obtained an external validation cohort from The First Affiliated Hospital of Naval Medical University (Shanghai, China). We performed LASSO regression and multivariate Cox proportional hazards analysis to identify relevant risk factors, which were then combined to develop six machine learning (ML) models: Cox proportional hazards model (Coxph), random survival forest (RSF), ranger, gradient boosting with component-wise linear models (GBM), decision trees, and boosting trees. The predictive performance of these ML models was evaluated using the concordance index (C-index), the integrated cumulative/dynamic area under the curve (AUC), and the integrated Brier score, as well as the Cox-Snell residual plot. We also used time-dependent variable importance, analysis of partial dependence survival plots, and the generation of aggregated survival SHapley Additive exPlanations (SurvSHAP) plots to provide a global explanation of the optimal model. Additionally, SurvSHAP (t) and survival local interpretable model-agnostic explanations (SurvLIME) plots were used to provide a local explanation of the optimal model. RESULTS: The final ML models are consisted of six factors: patient's age, gender, marital status, surgical history, as well as tumor's histopathological classification, histological grade, and SEER stage. Our prognostic model exhibits significant discriminative ability, particularly with the ranger model performing optimally. In the training set, validation set, and external validation set, the AUC for 1, 3, and 5 year OS are all above 0.83, and the integrated Brier scores are consistently below 0.15. The explainability analysis of the ranger model also indicates that histological grade, histopathological classification, and age are the most influential factors in predicting OS. CONCLUSIONS: The ranger ML prognostic model exhibits optimal performance and can be utilized to predict the OS of RLPS patients, offering valuable and crucial references for clinical physicians to make informed decisions in advance.

Survival nomogram and risk classification system for patients with adrenocortical carcinoma: a study based on the SEER database and external validation in China.

Background: Adrenocortical carcinoma (ACC) is an extremely rare and highly invasive malignant tumor. However, there is currently no reliable method to predict the prognosis of ACC. Our objective is to construct a nomogram and a risk classification system to predict the 1-year, 3-year, and 5-year overall survival (OS) of ACC. Methods: We retrieved clinicopathological data of patients diagnosed with ACC in The Surveillance, Epidemiology, and End Results (SEER) database and divided them into training and validation cohorts with a 7:3 ratio. Simultaneously, we collected an external validation cohort from The First Affiliated Hospital of Naval Medical University (Shanghai, China). Univariate and multivariate Cox analyses were performed to identify relevant risk factors, which were then combined to develop a correlation nomogram. The predictive performance of the nomogram was evaluated using the concordance index (C-index), receiver-operating characteristic curve (ROC), and calibration curves. Decision curve analysis (DCA) was applied to assess the clinical utility of the nomogram. In addition, Kaplan-Meier survival curves were generated to demonstrate the variation in OS between groups. Results: The final nomogram consisted of five factors: age, T, N, M, and history of chemotherapy. Our prognostic model demonstrated significant discriminative ability, with C-index and the area under the receiver operating characteristic (AUC) values exceeding 0.70. Additionally, DCA validated the clinical utility of the nomogram. In the entire cohort, the median OS for patients in the low- and high-risk groups was 70 and 10 months, respectively. Conclusions: A nomogram and a corresponding risk classification system were developed in order to predict the OS of patients diagnosed with ACC. These tools have the potential to provide valuable support for patient counseling and assist in the decision-making process related to treatment options.

Establishment of bladder cancer spheroids and cultured in microfluidic platform for predicting drug response.

Cisplatin-containing combination chemotherapy has been used as the standard treatment for bladder cancer patients at advanced stage. However, nearly 50% of patients are nonresponders. To guide the selection of more effective chemotherapeutic agents, a bladder cancer spheroids microfluidic drug sensitivity analysis system was established in this study. Bladder cancer spheroids were established and successfully cultured in a customized microfluidic device to assess their response to different chemotherapeutic agents. The in vitro drug sensitivity results were also compared to patient-derived xenograft (PDX) models and clinical responses of patients. As a result, bladder cancer spheroids faithfully recapitulate the histopathological and genetic features of their corresponding parental tumors. Furthermore, the in vitro drug sensitivity outcomes of spheroids (n = 8) demonstrated a high level of correlation with the PDX (n = 2) and clinical response in patients (n = 2). Our study highlights the potential of combining bladder cancer spheroids and microfluidic devices as an efficient and accurate platform for personalized selection of chemotherapeutic agents.

Patients With Muscle-Invasive Bladder Cancer With Lymphovascular Invasion in Transurethral Resection Specimen Benefits Most From Platinum-Based Neoadjuvant Chemotherapy.

PURPOSE: The survival benefit of neoadjuvant chemotherapy (NAC) before definitive radical cystectomy (RC) varied among patients, suggesting proper selection of patients for NAC to maximize the survival benefit. This study aimed to investigate the role of lymphovascular invasion (LVI) in transurethral resection (TUR) specimens in selecting patients with MIBC for NAC. METHODS: Two retrospective cohorts of patients with cT2-4aN0 MIBC who underwent RC from 2004 to 2015 provided by Lund University were included. Inverse probability weighting was applied to make the NAC-treated (NAC) and untreated (non-NAC) cohorts comparable. Survival benefits were estimated with Kaplan-Meier curves and Cox proportional hazards models. The primary endpoint was cancer-specific survival (CSS). LVI in TUR specimens and molecular taxonomies (BASE47, UNC, and LundTax) were examined, and bulk RNA-seq datasets were explored for LVI-relevant signatures. RESULTS: A total of 341 patients with cT2-4aN0 MIBC were included. The NAC cohort included 125 patients, whereas the non-NAC cohort included 216 patients. The 3-year CSS benefit of NAC was 7.1%. For patients with positive LVI in TUR specimens, the 3-year CSS benefit of NAC was 26.2% (48.1% vs. 74.3%), with a risk reduction of 56% (HR = 0.44, P = .03). A sensitivity analysis confirmed a significant interaction between LVI and NAC. This study failed to identify the molecular subtypes that maximized the survival benefit of NAC. Exploration of LVI-relevant signatures remains inconclusive. CONCLUSIONS: LVI in TUR specimens could help identify patients with MIBC who would derive maximal survival benefit from NAC. Further prospective validation is necessary.

Comprehensive identification of onco-exaptation events in bladder cancer cell lines revealed L1PA2-SYT1 as a prognosis-relevant event.

Transposable elements (TEs) can provide ectopic promoters to drive the expression of oncogenes in cancer, a mechanism known as onco-exaptation. Onco-exaptation events have been extensively identified in various cancers, with bladder cancer showing a high frequency of onco-exaptation events (77%). However, the effect of most of these events in bladder cancer remains unclear. This study identified 44 onco-exaptation events in 44 bladder cancer cell lines in 137 RNA-seq datasets from six publicly available cohorts, with L1PA2 contributing the most events. L1PA2-SYT1, L1PA2-MET, and L1PA2-XCL1 had the highest frequency not only in cell lines but also in TCGA-BLCA samples. L1PA2-SYT1 showed significant tumor specificity and was found to be activated by CpG island demethylation in its promoter. The upregulation of L1PA2-SYT1 enhances the in vitro invasion of bladder cancer and is an independent risk factor for patient's overall survival, suggesting L1PA2-SYT1 being an important event that promotes the development of bladder cancer.

Value of digital rectal examination in patients with suspected prostate cancer: a prospective cohort analysis study.

Background: Digital rectal examination (DRE) is a straightforward, cost-effective, practical, and time-honored physical examination method that plays a valuable role in the detection of prostate cancer (PCa). Nevertheless, with the advent of the prostate-specific antigen (PSA) era, the necessity of performing DRE has become a subject of debate. Our aim was to investigate the diagnostic efficacy and adjunctive role of DRE in a population (Prostate Imaging Reporting and Data System (PI-RADS), PI-RADS ≥3 or PSA ≥4 ng/mL) suspected of PCa. Methods: Five hundred and ninety-seven patients with suspected PCa requiring referral for biopsy were prospectively enrolled consecutively from February 2020 to May 2021. All patients received DRE and corresponding clinical diagnosis by a urologist before biopsy. According to the collected clinical and pathological information, the diagnostic performance of DRE in different PSA stratifications, and its association with tumor location and Gleason score (GS) were statistically analyzed. Results: Among patients with suspected cancer, the diagnostic accuracy of DRE was 63.45%. Compared with central zone or transition zone tumors, the recall rate of peripheral zone PCa with DRE-positive results was higher (65.50% vs. 34.55%). DRE-positive results were significantly correlated with GS ≥7 PCa (P<0.001), and the average GS of DRE-positive PCa patients was significantly higher than that of DRE-negative (7.92 vs. 7.11, P<0.001). Conclusions: DRE may help physicians further judge the necessity of biopsy in patients with elevated PSA, and preliminarily estimate the location and invasiveness of the tumor. However, it is still necessary to explore the value of DRE in a normal PSA population.

Association between testosterone and cancers risk in women: a two-sample Mendelian randomization study.

OBJECTIVE: Previous observational studies have explored the correlation between testosterone and cancer risk. However, the causal association between testosterone and various cancer types in women remains inconclusive. The objective of this Mendelian randomization study is to evaluate the causal links between total testosterone (TT) and bioavailable testosterone (BT) with cancer risk in females. METHODS: Initially, a rigorous quality control process was employed to identify suitable instrumental single nucleotide polymorphisms (SNPs) associated with the exposure under investigation that exhibited a significant association. The genetic causal relationship between female testosterone levels and the risk of developing cancers was examined through a two-sample Mendelian randomization. Various analytical methods, including inverse-variance weighted (IVW), MR-Egger, weighted median, simple mode, and weighted mode, were applied in the investigation. Key findings were primarily based on the results obtained via IVW (random effects), and sensitivity analyses were conducted to assess the reliability of the obtained results. Furthermore, maximum likelihood, penalized weighted median, and IVW (fixed effects) methods were utilized to further validate the robustness of the results. RESULTS: Based on the results of IVW analysis, our study indicated a positive causal relationship between BT and breast cancer (OR = 1.1407, 95%CI: 1.0627-1.2244, P = 0.0015) and endometrial cancer (OR = 1.4610, 95%CI: 1.2695-1.6813, P = 1.22E-06). Moreover, our findings also showed a positive causal association between TT and breast cancer (OR = 1.1764, 95%CI: 1.0846-1.2761, P = 0.0005), cervical cancer(OR = 1.0020, 95%CI: 1.0007-1.0032, P = 0.0077), and endometrial cancer(OR = 1.4124, 95%CI: 1.2083-1.6511, P = 0.0001). Additionally, our results demonstrated a negative causal relationship between BT and ovarian cancer (OR = 0.8649, 95%CI: 0.7750-0.9653, P = 0.0320). However, no causal relationship was found between BT, TT and other types of cancer (corrected P > 0.05). CONCLUSIONS: This study elucidates the role of testosterone on the development of breast cancer, endometrial cancer, ovarian cancer, and cervical cancer. It also hints at a potential but fragile link between testosterone and bladder cancer, as well as thyroid cancer. Nonetheless, it's worth noting that no statistically significant relationship between testosterone and various other types of cancer in females was identified.

The natural course of bacillus Calmette-Guérin induced bladder lesions: A long-term follow-up study and systematic review.

Objective: Bacillus Calmette-Guérin (BCG) instillation is the standard adjuvant treatment for intermediate- and high-risk non-muscle-invasive bladder cancer after transurethral resection. Nevertheless, its toxicity often causes bladder complications. On follow-up cystoscopy, post-BCG bladder lesions can be pathologically benign, urothelial carcinoma recurrence, or other types of bladder malignancy. Only a small number of case reports have been published on post-BCG bladder lesions. Their clinical features, natural course, and management remain unknown. Methods: We retrospectively studied cystoscopic videos and medical records of BCG-treated bladder cancer patients at our center. During a long-term follow-up, we took biopsies on tumor-like lesions and described their changes. In addition, we summarized previous studies on post-BCG bladder lesions by systematic literature searching and review. Results: We described a series of three cases with post-BCG bladder lesions mimicking tumor recurrence from a total of 38 cases with follow-up data for more than 5 years. Those lesions could last, grow, or disappear spontaneously, and remain pathological benign for years. In systematic review, we identified and analyzed a total of 15 cases with post-BCG bladder lesions with detailed clinical information. Eleven of the 15 were benign and have a good prognosis with nephrogenic adenoma being the most common pathological type. Conclusion: Based on previous studies and our experience, benign lesions after BCG instillation cannot distinguish with cancer recurrence by cystoscopy alone, even under narrow band imaging mode. Nonetheless, given most of them have a good prognosis, random biopsy or transurethral resection might be spared in the patients with long-term negative biopsy and urine cytology.

Preoperative urine sediment chromosomal instability level predicts urothelial cancer prognosis.

PURPOSE: Urothelial carcinomas (UCs) are often characterized by frequent recurrences after surgery, making UC one of the costliest cancers. Chromosomal instability (CIN) has been proven to be a hallmark of UCs and is related to the prognosis of many cancer types. In this study, we evaluated CIN of urine sediments as a prognostic indicator for UCs. METHODS: Patients with UC were prospectively recruited. Preoperative urine samples were collected for whole genome sequencing and urine cytology tests. Patients underwent standard-of-care treatment and were followed up until disease relapse or study ended. Concordance and accuracy of CIN alone or in combination with cytology in predicting disease relapse were assessed. The value of CIN combined with European Organization for Research and Treatment of Cancer (EORTC) model were also analyzed. RESULTS: A total of 137 patients with UCs were included in this study. Median follow-up was 44.2 months and 41.61% patients suffered from cancer relapse. Patients with CIN-high indicated higher relapse rate, and this distinction was significant for patients underwent transurethral resection of bladder tumor (57.89% vs. 34.29%, P = 0.016). Combination of cytology and CIN result could further classified patients into subgroups with distinct relapse risks. Meanwhile, the combination of CIN and EORTC model significantly improved the prediction accuracy compared with EORTC alone (Harrel's C-index: 0.71 vs. 0.65). CONCLUSION: CIN level of preoperative urine exfoliated cells had robust prognostic value for bladder cancer patients underwent TURBT. The prognostic model by combining CIN and EORTC may help in stratifying patients to optimize follow-up regimen.

Knockdown of kinesin family member 4A inhibits cell proliferation, migration, and invasion while promoting apoptosis of urothelial bladder carcinoma cells.

BACKGROUND: Kinesin family member 4A (KIF4A) is upregulated in a variety of cancers. However, its expression and potential downstream targets in urothelial bladder carcinoma (UBC) remain unclear. METHODS: Expression data of KIF4A in UBC and noncancerous tissues were downloaded from the GEPIA database. Cell proliferation, migration, invasion, and apoptosis of T24 and 5637 UBC cells were examined using wound healing, transwell, colony formation, CCK-8, and flow cytometry assays. KIF4A and potential downstream genes were analyzed using qRT-PCR, western blot analysis, and immunohistochemistry. RESULTS: In UBC samples, KIF4A expression was significantly higher than in corresponding noncancerous samples. UBC patients with high KIF4A expression had poor cancer-specific survival and overall survival. Knockdown of KIF4A significantly inhibited proliferation and promoted apoptosis of UBC cells, accompanied by dephosphorylation of AKT and increased the protein level of proapoptotic factors. Additionally, knockdown of KIF4A reduced migration and invasion of UBC cells whereas overexpression of KIF4A exhibited opposite effects, along with altered protein level in epithelial-mesenchymal transition-related genes. Furthermore, overexpression of YAP1 promoted KIF4A expression whereas knockdown of YAP1 suppressed KIF4A expression in UBC cells. Alternatively, KIF4A knockdown reduced YAP1 nuclear protein level whereas KIF4A overexpression suppressed YAP1 phosphorylation and facilitated YAP1 nuclear translocation. CONCLUSIONS: KIF4A upregulation correlates with poor prognosis of UBC. Knockdown of KIF4A inhibits proliferation, migration, and invasion of UBC cells while inducing apoptosis possibly through dephosphorylation of AKT, changes in EMT-related genes, and interaction with YAP1.

Identification and validation of immunohistochemical marker panels to predict the prognosis of muscle invasive bladder cancer.

Background: Currently, the treatment regimen of bladder cancer depends on the stage and grade. Yet, patients with similar histopathological characteristics may have distinct prognosis. Luminal/basal subtyping had proved to be a satisfactory subtyping method. Here we intended to evaluate immunohistochemistry, a more clinically-practical method, in luminal/basal classification and further risk-stratification. Methods: Patients diagnosed with urothelial carcinoma of the bladder in Changhai Hospital were retrospectively recruited and corresponding formalin-fixed paraffin embedded blocks were acquired. Tissue microarrays (TMAs) of these patients were established followed by immunohistochemical (IHC) staining of 14 markers. Patients were classified into luminal or basal subtype according to CK5/6, CK14, CK20 and GATA3 expression. Further subtyping of luminal and basal tumors was performed according to the expression of other markers. Results: A total of 236 patients were included: 163 and 73 patients were assigned to training and validation cohorts, respectively. Patients with basal tumor were related with poorer prognosis compared to those with luminal tumor (P=0.025 and 0.008 in training and validation cohorts, respectively). We further revealed luminal muscle invasive bladder cancer (MIBC) patients could be further categorized into subgroups with different risks. Cytoplasmic YAP1 and CCNB1 were selected as classifier, patients with low expression of cytoplasmic YAP1 or CCNB1 were independent risk factor for poorer prognosis (hazard ratio =2.19, P=0.04). Conclusions: Molecular subtyping into luminal/basal subtype and risk stratification method using a 2-marker method by immunohistochemistry can be an economical, clinically practical method to predict patient prognosis and could help to develop treatment strategy and follow-up schedule in clinical practice.

Fatty Acid Synthase Is the Key Regulator of Fatty Acid Metabolism and Is Related to Immunotherapy in Bladder Cancer.

Fatty acid metabolism (FAM) genes are potentially useful for predicting prognosis and immunotherapy response in bladder cancer (BC). To examine this, we constructed a prognostic model and identified key FAM genes in BC. Using transcriptional expression profiles and clinical data of BC patients from public datasets and Changhai (CH) hospital, we built and validated a risk-score model based on 13 prognostic FAM genes. Differential gene expression identified fatty acid synthase (FASN) as central to fatty acid metabolism in BC. FASN was differentially expressed between normal and tumor tissue, and was related to survival. In the CH dataset, FASN independently predicted muscle-invasive BC. FASN differential expression was significantly related to immune-cell infiltration and patients with low FASN expression responded better to immune checkpoint inhibitor (ICI) treatment. SREBF1 was predicted as the most significant transcription factor for FASN. Competing endogenous RNA network analysis suggested that lncRNA AC107027.3 may upregulate FASN by competitively binding miR-27A-3p, thereby regulating the immunotherapy response in BC. Dasatinib and temsirolimus are potential FASN-targeting drugs. Our model efficiently predicted prognosis in BC. FASN is central to fatty acid metabolism, and a potential indicator and regulator of ICI treatment.

Identifying the grade of bladder cancer cells using microfluidic chips based on impedance.

Quantification of tumor cell heterogeneity is critical for clinical diagnostic and therapeutic applications, including evaluation of the cancerous stage of tumors. In this work, we presented a novel method to effectively distinguish the grade of bladder cancer at a single-cell level in both cell line and clinical cell samples. This was achieved by taking advantage of microdroplets and microelectrodes, which can encapsulate and then trap single cells for measuring their impedance in a label-free and non-invasive manner. These findings suggested that this impedance analysis device based on droplet microfluidics is promising in the fields of clinical and point-of-care diagnostics.

A Prospective Study Comparing Cancer Detection Rates of Transperineal Prostate Biopsies Performed by Junior Urologists versus a Senior Consultant in a Real-World Setting.

INTRODUCTION: Prostate biopsy (PB) is a typical daily practice method for the diagnosis of prostate cancer (PCa). This study aimed to compare the PCa detection rates and peri- and postoperative complications of PB among 3 residents and a consultant. PATIENTS AND METHODS: A total of 343 patients who underwent PB between August 2018 and July 2019 were involved in this study. Residents were systematically trained for 2 weeks by a consultant for performing systematic biopsy (SB) and targeted biopsy (TB). And then, 3 residents and the consultant performed PB independently every quarter due to routine rotation in daily practice. The peri- and postoperative data were collected from a prospectively maintained database (www.pc-follow.cn). The primary outcome and secondary outcome were to compare the PCa detection rates and complications between the residents and consultant, respectively. RESULTS: There was no significant difference between the residents and consultant in terms of overall PCa detection rates of SB and TB or further stratified by prostate-specific antigen value and prostate imaging reporting and data system (PI-RADS) scores. We found the consultant had more TB cores (175 cores vs. 86-114 cores, p = 0.043) and shorter procedural time (mean 16 min vs. 19.7-20.1 min, p < 0.001) versus the residents. The complication rate for the consultant was 6.7% and 5%-8.2% for the residents, respectively (p = 0.875). CONCLUSIONS: The residents could get similar PCa detection and complication rates compared with that of the consultant after a 2-week training. However, the residents still need more cases to shorten the time of the biopsy procedure.