Development and validation of a deep learning model for predicting postoperative survival of patients with gastric cancer.

BACKGROUND: Deep learning (DL), a specialized form of machine learning (ML), is valuable for forecasting survival in various diseases. Its clinical applicability in real-world patients with gastric cancer (GC) has yet to be extensively validated. METHODS: A combined cohort of 11,414 GC patients from the Surveillance, Epidemiology and End Results (SEER) database and 2,846 patients from a Chinese dataset were utilized. The internal validation of different algorithms, including DL model, traditional ML models, and American Joint Committee on Cancer (AJCC) stage model, was conducted by training and testing sets on the SEER database, followed by external validation on the Chinese dataset. The performance of the algorithms was assessed using the area under the receiver operating characteristic curve, decision curve, and calibration curve. RESULTS: DL model demonstrated superior performance in terms of the area under the curve (AUC) at 1, 3, and, 5 years post-surgery across both datasets, surpassing other ML models and AJCC stage model, with AUCs of 0.77, 0.80, and 0.82 in the SEER dataset and 0.77, 0.76, and 0.75 in the Chinese dataset, respectively. Furthermore, decision curve analysis revealed that the DL model yielded greater net gains at 3 years than other ML models and AJCC stage model, and calibration plots at 3 years indicated a favorable level of consistency between the ML and actual observations during external validation. CONCLUSIONS: DL-based model was established to accurately predict the survival rate of postoperative patients with GC.

Colonization of Fusobacterium nucleatum is an independent predictor of poor prognosis in gastric cancer patients with venous thromboembolism: a retrospective cohort study.

BACKGROUND: Fusobacterium nucleatum (F. nucleatum) often colonizes cancerous gastric tissues and is characterized by the promotion of platelet aggregation and the development of visceral thrombosis. Venous thromboembolism (VTE) leads to a significant increase in the mortality of gastric cancer (GC) patients. However, the relationship between the colonization of F. nucleatum and the prognosis of GC patients is still unknown. AIM: The aim of this study was to explore whether the colonization of F. nucleatum is related to the prognosis of GC patients complicated with VTE and to explore other potential risk factors. METHODS: From 2017-2021, the data of 304 patients with new VTEs during the treatment of GC at the Affiliated Cancer Hospital of Zhengzhou University were collected. Fluorescence in situ hybridization of F. nucleatum was performed on pathological sections of cancer tissues from the patients. Survival analysis methods, including the Kaplan‒Meier method and Cox proportional hazard model, were performed. RESULTS: F. nucleatum colonization was significantly associated with splanchnic vein thrombosis, higher platelet-lymphocyte ratio (PLR), and lower absolute lymphocyte count. In the multivariable Cox model, F. nucleatum colonization was found to be an independent risk factor for the prognosis of GC, with an adjusted HR of 1.77 (95% CI, 1.17 to 2.69 [P = 0.007]). In addition, patients with high PLR (HR: 2.65, P = 0.004) or VTE occurring during four cycles of chemotherapy (HR: 2.32, P = 0.012) exhibited shorter survival. Conversely, those experiencing VTE later (HR per month from diagnosis of GC: 0.95, P = 0.006) or using IVC filters (HR: 0.27, P = 0.011) had longer survival. CONCLUSION: Colonization of F. nucleatum in GC tissues was associated with lower absolute lymphocyte count and higher PLR in GC patients with VTE. F. nucleatum colonization also appeared to be associated with the development of VTE in specific sites, in particular the splanchnic vein. Colonization of F. nucleatum may potentially represent an independent predictor of poor prognosis in GC patients. Additional research is necessary to validate these findings.

The effect of ambient PM2.5 exposure on survival of lung cancer patients after lobectomy.

Exposure to fine particulate matter (PM2.5) is linked to lung cancer incidence and mortality. However, the impact of PM2.5 exposure on lung cancer patients after lobectomy, which remains the primary treatment for early-stage lung cancer, is unknown. Therefore, we investigated the correlation between PM2.5 exposure and the survival of lung cancer patients after lobectomy. This study included 3,327 patients with lung cancer who underwent lobectomy procedures. We converted residential addresses into coordinates and estimated individual patients' daily PM2.5 and O3 exposure levels. A Cox multivariate regression model was used to analyze the specific monthly association between PM2.5 exposure and lung cancer survival. Every 10 µg/m3 increase in monthly PM2.5 concentration in the first and second months after lobectomy increased the risk of death (hazard ratio [HR]: 1.043, 95% confidence interval [CI]: 1.019-1.067 and HR: 1.036, 95% CI: 1.013-1.060, respectively). Non-smokers, younger patients, and patients with longer hospitalization durations had worse survival rates when exposed to greater concentrations of PM2.5. High postoperative PM2.5 exposure immediately after lobectomy reduced the survival of patients with lung cancer. Patients living in areas with high PM2.5 should be offered the opportunity to transfer to areas with better air quality after undergoing lobectomies, to prolong their survival times.

Pretreatment CD8 + PD-1 + to CD4 + PD-1 + ratio is associated with the prognosis of advanced melanoma patients treated with PD-1 inhibitors.

The aim of this study was to determine whether the pretreatment CD8 + PD-1 + to CD4 + PD-1 + (PERLS) ratio is an independent risk prognostic factor of advanced melanoma patients. We retrospectively analyzed the efficacy and flow cytometry data from advanced melanoma patients who received PD-1 inhibitor as monotherapy between January 1, 2018 and January 26, 2022. Fifty-nine patients were enrolled, the PERLS cutoff was 1.125. PERLS did not correlate with clinical characteristics but were significantly associated with baseline CD8 + , CD4 + , and CD8 + PD-1 + T cells. The mean overall survival and the progression-free survival were 45.8 and 17.1 months for the low PERLS group (n = 39), compared with 29.9 ( P  = 0.001) and 9.7 ( P  = 0.003) months for the high PERLS group ( n  = 20), respectively. Pretreatment PERLS might contribute to selecting patients before receiving anti-PD-1 therapy.

Combination therapy using low-dose anlotinib and immune checkpoint inhibitors for extensive-stage small cell lung cancer.

Background: This study evaluated the efficacy and safety of low-dose anlotinib combined with immune checkpoint inhibitors as second-line or later treatment for extensive-stage small cell lung cancer (ES-SCLC). Methods: The study included 42 patients with ES-SCLC who were treated with low-dose anlotinib combined with programmed cell death protein 1/programmed cell death-ligand 1 inhibitors at Henan Cancer Hospital between March 2019 and August 2022. We retrospectively analyzed the efficacy and safety data for these patients. Indicators assessed included progression-free survival (PFS), overall survival (OS), the overall response rate (ORR), the disease control rate (DCR), and adverse events (AEs). Prognostic factors were identified in univariate and multivariate analyses. Results: Median PFS was 11.0 months (95% CI: 7.868-14.132) and median OS was 17.3 months (95% CI: 11.517-23.083). The ORR was 28.5% and the DCR was 95.2%. Treatment-related AEs were noted in 27 patients (64.3%), the most common of which was thyroid dysfunction (26.2%). Grade 3/4 treatment-related AEs were observed in two patients (4.8%). Conclusions: A combination of low-dose anlotinib and immune checkpoint inhibitors as second-line or later treatment for ES-SCLC may achieve longer PFS and OS and have manageable AEs.

Corrigendum: Delayed diagnosis and treatment of cancer patients during the COVID-19 pandemic in Henan, China: An interrupted time series analysis.

[This corrects the article DOI: 10.3389/fpubh.2022.881718.].

Delayed Diagnosis and Treatment of Cancer Patients During the COVID-19 Pandemic in Henan, China: An Interrupted Time Series Analysis.

Objective: To investigate the possible impact of lockdown policies on the diagnosis and treatment of cancer patients in Henan, China. Design Setting and Participants: We collected data from the Henan Cancer Hospital, affiliated with Zhengzhou University. The monthly numbers of inpatient admissions from January 2014 to December 2019 were used to forecast the number of inpatient admissions in 2020, which was then compared to the actual number of patients admitted during the pandemic to evaluate how the actual number diverges from this forecast. We conducted an interrupted time series analysis using the autoregressive integrated moving average (ARIMA) model. Main Outcomes and Measures: For specific diagnoses, treatment modalities, and age groups, we compared the changes in monthly admissions after the pandemic with the forecasted changes from the model. Results: The observed overall monthly number of inpatient admissions decreased by 20.2% [95% confidence interval (CI), 11.7-27.2%], 78.9% (95% CI, 77.3-80.4%), and 40.9% (95% CI, 35.6-45.5%) in January, February, and March 2020, respectively, as compared with those predicted using the ARIMA model. After the lockdown, visits for all treatment modalities decreased sharply. However, apparent compensation and recovery of the backlog appeared in later surgeries. As a result, the number of patients who underwent surgery in 2020 (30,478) was close to the number forecasted by the ARIMA model (30,185). In the same period, patients who received other treatments or underwent examinations were 106,074 and 36,968, respectively; the respective numbers that were forecasted by ARIMA were 127,775 and 60,025, respectively. These findings depict a decrease of 16.9 and 38.4% in patients who received other treatments or underwent examinations only, respectively. Regarding diagnosis, the reported incidence of various cancers decreased dramatically in February, with varying extent and speed of recovery. Conclusion and Relevance: The COVID-19 pandemic has significantly delayed the diagnosis and treatment of cancer in Henan, China. Long-term research should be conducted to assess the future effects of lockdown policies.

Concurrent neoadjuvant chemoradiotherapy could improve survival outcomes for patients with esophageal cancer: a meta-analysis based on random clinical trials.

BACKGROUND: The long-term survival benefit of concurrent neoadjuvant chemoradiotherapy in patients with resectable esophageal cancer remains controversial. In the present study, we conducted a meta-analysis to assess these effectiveness. METHODS: We searched for most relevant studies published up to the end of August 2016, using Pubmed and web of knowledge. And additional articles were identified from previous meta-analysis. The hazard ratio (HR, for overall survival and progression free survival) or risk ratio (RR, for R0 resection) with its corresponding 95 % confidence interval (CI) were used to assess the pooled effect. RESULTS: Twelve articles including 1756 patients were included in the meta-analysis. Concurrent neoadjuvant chemoradiotherapy followed by surgery was associated with significantly improved overall survival (HR=0.76 , 95% CI= 0.68-0.86), progression survival (HR =0.69, 95% CI= 0.59-0.81), and R0 resection rate(RR =1.17, 95% CI= 1.03-1.33). Subgroup analysis suggested that concurrent neoadjuvant chemoradiotherapy could improve overall survival outcome for squamous cell carcinoma (HR=0.73, 95%CI=0.61-0.88) but not those for adenocarcinoma (HR=0.72, 95%CI=0.48-1.04). CONCLUSION: Our findings suggested that concurrent neoadjuvant chemoradiotherapy was associated with a significant survival benefit in patients with esophageal cancer.

Chemoprevention of prostate cancer in men with high-grade prostatic intraepithelial neoplasia (HGPIN): a systematic review and adjusted indirect treatment comparison.

BACKGROUND: High-grade prostatic intraepithelial neoplasia (HGPIN) is the precursor or premalignant form of prostate cancer. At least 30% patients with a confirmed HGPIN will develop prostate cancer within 1 year after repeated biopsy. HGPIN patients are the appropriate at-risk population for chemoprevention strategies investigation against prostate cancer. However the commonly used chemoprevention agents that targeted on hormonal imbalance or lifestyle-related factors showed varied results in HGPIN patients. METHODS: Literature searches were conducted in PubMed, EMBASE and Cochrane library according to Cochrane guidelines before January 31st, 2017. Direct meta-analysis were performed to summarize the efficacy of candidate chemopreventative agents Dutasteride, Flutamide, Toremifene, Selenium, Green tea components, Lycopene and natural food products combination. Adjusted indirect meta-analyses were employed to compare the relative efficacy of these candidate chemoprevention agents head-to-head. RESULTS: The overall incidence of prostate cancer in HGPIN was slightly decreased by chemoprevention agents (25.7% vs 31.5%, RR = 0.92, 95% CI: 0.83-1.03, P = 0.183), with minor heterogeneity (I2 = 22.3%, 𝟀2 = 15.08, P = 0.237), but without statistical significance. Subgroup analysis showed that green tea catechins significantly decreased prostate cancer in HGPIN patients (7.60% vs 23.1%, RR = 0.39, 95% CI: 0.16-10.97, P P = 0.044), with moderate heterogeneity (I2 = 47.9%, 𝟀2 = 1.92, P = 0.166). The adjusted indirect meta-analysis favored green tea catechins over other chemoprevention agents, and significantly when compared to natural food products combination (RR = 0.355, 95% CI: 0.134-0.934). CONCLUSION: The overall efficacy of chemoprevention agents in HGPIN patients is limited. But Green tea catechins showed the superiority to decrease prostate cancer in HGPIN patients.