Application of the convolution neural network in determining the depth of invasion of gastrointestinal cancer: a systematic review and meta-analysis.

BACKGROUND: With the development of endoscopic technology, endoscopic submucosal dissection (ESD) has been widely used in the treatment of gastrointestinal tumors. It is necessary to evaluate the depth of tumor invasion before the application of ESD. The convolution neural network (CNN) is a type of artificial intelligence that has the potential to assist in the classification of the depth of invasion in endoscopic images. This meta-analysis aimed to evaluate the performance of CNN in determining the depth of invasion of gastrointestinal tumors. METHODS: A search on PubMed, Web of Science, and SinoMed was performed to collect the original publications about the use of CNN in determining the depth of invasion of gastrointestinal neoplasms. Pooled sensitivity and specificity were calculated using an exact binominal rendition of the bivariate mixed-effects regression model. I2 was used for the evaluation of heterogeneity. RESULTS: A total of 17 articles were included; the pooled sensitivity was 84% (95% CI, 0.81-0.88), specificity was 91% (95% CI, 0.85-0.94), and the area under the curve (AUC) was 0.93 (95% CI, 0.90-0.95). The performance of CNN was significantly better than that of endoscopists (AUC: 0.93 vs 0.83, respectively; P = .0005). CONCLUSION: Our review revealed that CNN is one of the most effective methods of endoscopy to evaluate the depth of invasion of early gastrointestinal tumors, which has the potential to work as a remarkable tool for clinical endoscopists to make decisions on whether the lesion is feasible for endoscopic treatment.

[Regarding the selection of individualized therapy after neoadjuvant therapy for gastrointestinal tumors].

Gastrointestinal tumors have been widely concerned because of increasing morbidity and mortality. In the process of exploring the therapeutic patterns of gastrointestinal tumors, patients treated with neoadjuvant therapies have good effect of tumor regression and favorable prognosis. Thus, neoadjuvant therapy strategies are recommended by major guidelines of gastrointestinal tumors in the world. Meanwhile, they have a great impact on the traditional methods of surgery, the influence mainly involves the reduction of the surgical margin and the scope of lymph node dissection in gastric cancer, while involves performing organ preservation and watch & wait in selective patients with colorectal cancer. These effects and changes were based on effective control of local recurrence by neoadjuvant therapies, and the advantages of neoadjuvant therapy in terms of tumor regression and survival supported by many studies. It is also based on the patient's desire for organ preservation and non-surgical treatment. Meanwhile, application of neoadjuvant therapy strategies increase surgical difficulty and postoperative complications, but the overall impact on patient prognosis is weak. Therefore, the selection of an appropriate treatment model after neoadjuvant therapy requires an effective overall post-treatment evaluation. In particular, it is necessary to pay attention to the evaluation of imaging, endoscopy, etc., while effectively performing monitoring and follow-up, and finally establishing an appropriate salvage treatment. This article will review the status and problems of individualized treatment after neoadjuvant therapy of gastrointestinal tumor.

Prognostic impact of positive microscopic margins (R1 resection) in patients with GIST (gastrointestinal stromal tumours): Results of a multicenter European study.

BACKGROUND: Although several prognostic factors in GIST have been well studied such as tumour size, mitotic rate, or localization, the influence of microscopic margins or R1 resection remains controversial. The aim of this study was to evaluate the influence of R1 resection on the prognosis of GIST in a large multicentre retrospective series of patients. METHODS: From 2001 to 2013, 1413 patients who underwent surgery for any site of GIST were identified from 61 European centers. 1098 patients were included, excluding synchronous metastases, concurrent malignancies, R2 resection or GIST recurrence. Tumour rupture (TR) was reclassified according to the Oslo sarcoma classification. Cox proportional hazards ratio and Kaplan-Meier survival estimates were used to analyse 5-year recurrence-free survival (RFS). RESULTS: Of 1098 patients, 38 (3%) underwent R1 resection with a risk of TR of 11%. The 5-year RFS was 89.6% with a median follow-up of 81 months [range: 31.2-152 months]. On univariate analysis, lower RFS was significantly associated with R1 resection [HR = 2.13; p = 0.04], high risk score according to the modified NIH classification, administration of adjuvant therapy [HR = 2.24; p < 0.001] and intraoperative complications [HR = 2.82; p < 0.001]. Only intraoperative complications [HR = 1.79; p = 0.02] and high risk according to the modified NIH classification including the updated definition of TR [HR = 3.43; p = 0.04] remained significant on multivariate analysis. CONCLUSION: This study shows that positive microscopic margins are not an independent predictive factor for RFS in GIST when taking into account the up-dated classification of TR. R1 resection may be considered a reasonable alternative to avoid major functional sequelae and should not lead to reoperation.

Comparing gastrointestinal stromal tumor outcomes between geriatric and non-geriatric patients: A population-based analysis.

BACKGROUND: Gastrointestinal Stromal Tumors (GISTs) are the most common mesenchymal tumors of the GI tract. SEER is an extensive cancer database which proves useful in analyzing population trends. This analysis investigated GIST outcomes between geriatric & non-geriatric patients. METHODS: SEER*STAT 8.4.0.1 was used to extract relevant GIST data from 2000 to 2019. Geriatric age was defined as ≥70 years. Variables included age, sex, surgery, cancer-specific death, and overall survival. Statistical tests included univariate analysis using KM survival estimate (95% confidence interval) to calculate 5-year survival (5YS). Log-Rank tests determined statistical significance. Multivariable Cox's PH regression estimated the geriatric hazard death ratio adjusted for sex, stage, and surgery. RESULTS: The number of patients included was 13,579, yielding overall 5YS of 68.6% (95% CI 67.7-69.5). Cancer-specific death was 39.11% in 2000 & 3.33% in 2019. Non-geriatric & geriatric patient data yielded 5YS of 77.4% (76.4%-78.3%) and 53.3% (51.7%-54.8%) respectively (p < 0.0001). For no surgery/surgery, younger patient data yielded 5YS of 48.7% (45.8%-51.4%) and 83.7% (82.7%-84.7%) respectively (p < 0.0001); geriatric data yielded 5YS of 29.3% (26.5%-32.1%) and 62.8% (60.8%-64.6%) respectively (p < 0.0001). Multivariable analysis yielded a geriatric hazard death of 2.56 (2.42-2.70) (p < 0.0001). CONCLUSIONS: Cancer-specific death decreased since 2000, indicating an improvement in survival & treatment methods. Observed lower survival rates overall in the geriatric group. Surgery appeared to enhance survival rates in both groups, suggesting that surgery is an important factor in GIST survival regardless of age. Large prospective studies will help define clinical management for geriatric patients.

[Malnutrition in advanced gastrointestinal cancer patients and nutritional support therapy].

The advancement of comprehensive treatment has allowed an increasing number of patients with gastrointestinal tumor to achieve long-term survival. In current clinical practice, there is a growing population of patients with advanced gastrointestinal tumor. Due to various factors, such as tumor burden, treatments including chemotherapy and radiation therapy, as well as underlying diseases, patients with advanced gastrointestinal tumor often experience malnutrition, which negatively impacts their clinical outcomes. The mechanism of malnutrition in patients with advanced gastrointestinal tumor is complex, and conventional nutritional support therapy has shown limited effectiveness. With the continuous progress in the concept and technique of nutritional support therapy, the diversification of treatment strategies, and the strengthening of multidisciplinary collaboration, the nutritional management for patients with advanced gastrointestinal tumor tends to be standardized and rational, leading to effective improvement in patients' nutritional status and clinical outcomes. Based on the latest evidence-based medicine, combined with the author's practical experience and insights, this article aims to explore nutritional support therapy for patients with advanced gastrointestinal tumor.

Tumor neuroectodérmico maligno del tracto gastrointestinal: a propósito de un caso / Malignant neuroectodermal tumor of the gastrointestinal tract: case report

El tumor neuroectodérmico maligno del tracto gastrointestinal es una neoplasia rara con pocos casos reportados en la literatura, especialmente en América Latina. Descrito por primera vez en 2003, se trata de una entidad sin tratamiento estandarizado y de pobre pronóstico. Se presenta el caso de una paciente de 22 años de edad que acude a la consulta por dolor abdominal, anemia y masa abdominal palpable. Luego de estudios pertinentes se decide la conducta resectiva y el posterior tratamiento oncológico. (AU)

Malignant gastrointestinal neuroectodermal tumor (GNET), formerly known as clear cell sarcoma of the gastrointestinal tract, is an extremely rare tumor of mesenchymal origin, which presents great microscopic and molecular similarity to clear cell sarcoma found in other parts of the body, such as tendons and aponeurosis. It is characterized by its rapid evolution, high recurrence rate and frequent diagnosis as metastatic disease.1,2 (AU)

The GIST of it all: management of gastrointestinal stromal tumors (GIST) from the first steps to tailored therapy. A bibliometric analysis.

PURPOSE: Improvement of patient care is associated with increasing publication numbers in biomedical research. However, such increasing numbers of publications make it challenging for physicians and scientists to screen and process the literature of their respective fields. In this study, we present a comprehensive bibliometric analysis of the evolution of gastrointestinal stromal tumor (GIST) research, analyzing the current state of the field and identifying key open questions going beyond the recent advantages for future studies to assess. METHODS: Using the Web of Science Core Collection, 5040 GIST-associated publications in the years 1984-2022 were identified and analyzed regarding key bibliometric variables using the Bibliometrix R package and VOSviewer software. RESULTS: GIST-associated publication numbers substantially increased over time, accentuated from year 2000 onwards, and being characterized by multinational collaborations. The main topic clusters comprise surgical management, tyrosine kinase inhibitor (TKI) development/treatment, diagnostic workup, and molecular pathophysiology. Within all main topic clusters, a significant progress is reflected by the literature over the years. This progress ranges from conventional open surgical techniques over minimally invasive, including robotic and endoscopic, resection techniques to increasing identification of specific functional genetic aberrations sensitizing for newly developed TKIs being extensively investigated in clinical studies and implemented in GIST treatment guidelines. However, especially in locally advanced, recurrent, and metastatic disease stages, surgery-related questions and certain specific questions concerning (further-line) TKI treatment resistance were infrequently addressed. CONCLUSION: Increasing GIST-related publication numbers reflect a continuous progress in the major topic clusters of the GIST research field. Especially in advanced disease stages, questions related to the interplay between surgical approaches and TKI treatment sensitivity should be addressed in future studies.

Association of pathologic factors with postoperative venous thromboembolism after gastrointestinal cancer surgery.

BACKGROUND: Venous thromboembolism (VTE) chemoprophylaxis is the standard of care after gastrointestinal (GI) cancer surgery; however, variation in risk based on pathologic factors (eg, stage and histology) is unclear. This study aimed to evaluate the association of pathologic factors with VTE after GI cancer surgery. METHODS: The American College of Surgeons National Surgical Quality Improvement Program procedure targeted datasets were queried for patients who underwent colorectal, pancreatic, primary hepatic, and esophageal cancer surgery between 2017 and 2020. Disease-specific and pathologic factors associated with postoperative VTE were evaluated using multivariable logistic regression. RESULTS: Among 70,934 patients who underwent GI cancer surgery, the incidence rates of 30-day postoperative VTE were 3.3% for pancreatic cancer, 3.2% for esophageal cancer, 2.7% for primary hepatic, and 1.3% for colorectal cancer. T stage was associated with VTE for colorectal cancer (T4 vs T1; odds ratio [OR], 1.79; 95% CI, 1.24-2.60), pancreatic cancer (all T stages vs T1; P < .05), and primary hepatic cancer (T4 vs T1; OR, 2.80; 95% CI, 1.55-5.08). N stage was associated with VTE for colorectal cancer (N2 vs N0; OR, 1.33; 95% CI, 1.04-1.68) and pancreatic cancer (N2 vs N0; OR, 1.36; 95% CI, 1.03-1.81). M stage was associated with VTE for colorectal cancer (OR, 1.47; 95% CI, 1.17-1.85) and esophageal cancer (OR, 2.54; 95% CI, 1.24-5.19). Histologic subtype was not associated with VTE, except for pancreatic neuroendocrine tumors vs adenocarcinoma (OR, 1.34; 95% CI, 1.03-1.74). CONCLUSION: Pathologic factors were associated with higher 30-day VTE risk after GI cancer surgery. Acknowledging the association of pathologic factors on VTE is an important first step to considering a more tailored approach to chemoprophylaxis.

Disparities in clinical trial enrollment among patients with gastrointestinal cancer relative to minority-serving and safety-netting hospitals.

BACKGROUND: For results to be generalizable to all patients with cancer, clinical trials need to include a diverse patient demographic that is representative of the general population. We sought to characterize the effect of receiving care at a minority-serving hospital (MSH) and/or safety-net hospital on clinical trial enrollment among patients with gastrointestinal (GI) malignancies. METHODS: Adult patients with GI cancer who underwent oncologic surgery and were enrolled in institutional-/National Cancer Institute-funded clinical trials between 2012 and 2019 were identified in the National Cancer Database. Multivariable regression was used to assess the relationship between MSH and safety-net status relative to clinical trial enrollment. RESULTS: Among 1,112,594 patients, 994,598 (89.4%) were treated at a non-MSH, whereas 117,996 (10.6%) were treated at an MSH. Only 1857 patients (0.2%) were enrolled in a clinical trial; most patients received care at a non-MSH (1794 [96.6%]). On multivariable analysis, the odds of enrollment in a clinical trial were markedly lower among patients treated at an MSH vs non-MSH (odds ratio [OR], 0.32; 95% CI, 0.22-0.46). In addition, even after controlling for receipt of care at MSH, Black patients remained at lower odds of enrollment in a clinical trial than White patients (OR, 0.57; 95% CI, 0.45-0.73; both P < .05). CONCLUSION: Overall, clinical trial participation among patients with GI cancer was extremely low. Patients treated at an MSH and high safety-net burden hospitals and Black individuals were much less likely to be enrolled in a clinical trial. Efforts should be made to improve trial enrollment and address disparities in trial representation.

Quality of life following perioperative optimization with nutritional supplements in patients undergoing gastrointestinal surgery for cancer: A randomized, placebo-controlled feasibility clinical trial.

BACKGROUND: Up to two thirds of patients presenting for abdominal cancer surgery are malnourished pre-operatively. Perioperative nutritional supplementation has been proposed to improve surgical outcomes, though its effect on quality of life (QoL) is not yet understood. METHODS: A randomized controlled feasibility trial for perioperative nutrition among patients undergoing major abdominal cancer surgery was conducted. Participants in the intervention group received supplements for 30 days before surgery. Participants completed two QoL questionnaires (EORTC-QLQ-C-30 and FACT-G) at baseline, then 4 and 12 weeks postoperatively. Participants were compared between and within groups at baseline, Weeks 4, and 12 using t tests. Minimal clinically important differences (MCIDs) were considered as a 10-point worsening from baseline. RESULTS: Sixty-six participants were available for analysis in this study, including 33 in the intervention and 30 in the control arms. Baseline demographics were balanced between groups except for different rates of pancreas cancer (36% intervention vs. 9% control) and colorectal cancer (19% intervention vs. 34% control). At baseline, participants in the intervention group had lower overall QoL (59% vs. 77%, p = 0.01), role functioning (72% vs 88%, p = 0.045), and cognitive functioning (79% vs 90%, p = 0.047). Following surgery, role and physical functioning worsened in the control group, without significant differences between groups. Role functioning was persistently worsened at 12 weeks in the control group. The rates of MCIDs were similar between both intervention and control groups. DISCUSSION: Perioperative nutrition was associated with preservation of QoL in the postoperative period following major abdominal cancer surgery compared to placebo. SUMMARY: Among patients undergoing surgery for cancer, the majority present at high risk for malnutrition. In this placebo-controlled randomized trial among patients undergoing major abdominal surgery for cancer, preoperative nutrition supplementation was associated with the preservation of QoL in the postoperative period.

Risk factors for positive resection margins after endoscopic resection for gastrointestinal neuroendocrine tumors.

BACKGROUND: In recent years, the incidence of gastrointestinal neuroendocrine tumors (GI-NETs) has remarkably increased due to the widespread use of screening gastrointestinal endoscopy. Currently, the most common treatments are surgery and endoscopic resection. Compared to surgery, endoscopic resection possesses a higher risk of resection margin residues for the treatment of GI-NETs. METHODS: A total of 315 patients who underwent surgery or endoscopic resection for GI-NETs were included. We analyzed their resection modality (surgery, ESD, EMR), margin status, Preoperative marking and Prognosis. RESULTS: Among 315 patients included, 175 cases underwent endoscopic resection and 140 cases underwent surgical treatment. A total of 43 (43/175, 24.57%) and 10 (10/140, 7.14%) patients exhibited positive resection margins after endoscopic resection and surgery, respectively. Multivariate regression analysis suggested that no preoperative marking and endoscopic treatment methods were risk factors for resection margin residues. Among the patients with positive margin residues after endoscopic resection, 5 patients underwent the radical surgical resection and 1 patient underwent additional ESD resection. The remaining 37 patients had no recurrence during a median follow-up of 36 months. CONCLUSIONS: Compared with surgery, endoscopic therapy has a higher margin residual rate. During endoscopic resection, preoperative marking may reduce the rate of lateral margin residues, and endoscopic submucosal dissection may be preferred than endoscopic mucosal resection. Periodical follow-up may be an alternative method for patients with positive margin residues after endoscopic resection.

Precision Oncology in Gastrointestinal and Colorectal Cancer Surgery.

Precision medicine is used to treat gastrointestinal malignancies including esophageal, gastric, small bowel, colorectal, and pancreatic cancers. Cutting-edge assays to detect and treat these cancers are active areas of research and will soon become standard of care. Colorectal cancer is a prime example of precision oncology as disease site is no longer the final determinate of treatment. Here, the authors describe how leveraging an understanding of tumor biology translates to individualized patient care using evidence-based practices.

Survival benefit of surgery for second primary esophageal cancer following gastrointestinal cancer: a population-based study.

BACKGROUND: The incidence of second primary malignancy is increasing. However, although there is some information on second primary esophageal cancer (SPEC) itself, there is no study or guideline on the use of surgery for SPEC after gastrointestinal cancer (SPEC-GC). Thus, this study aimed to gather evidence for the benefits of surgery by analyzing a national cohort and determining the prognostic factors and clinical treatment decisions for SPEC-GC. METHODS: Data for patients with SPEC-GC were obtained from the Surveillance, Epidemiology, and End Results (SEER) database between 2000 and 2019. The prognostic factors of SPEC-GC were investigated by stepwise Cox proportional hazards regression and Kaplan-Meier analyses for overall survival and cancer-specific survival. RESULTS: A total of 8308 patients with SPEC were selected, including 582 patients with SPEC-GC. Multivariate analysis revealed that surgery, year of diagnosis, scope of regional lymph node surgery, tumor differentiation grade, SEER historic stage, and triple therapy were significant predictors of survival outcomes (P < .05). Surgery seemed to improve the prognosis of patients with SPEC-GC significantly compared with no surgery and chemoradiotherapy (P < .001). CONCLUSIONS: Surgery should be considered as the main treatment for SPEC-GC. Surgery, year of diagnosis, scope of regional lymph node surgery, tumor differentiation grade, SEER historic stage, and triple therapy were found to be independent prognostic factors for these patients. These factors should be considered in the clinical diagnosis and treatment of SPEC-GC.

Optimal time to initiate early oral feeding in postoperative patients with upper gastrointestinal malignancy: A network meta-analysis.

BACKGROUND: With the development of enhanced recovery after surgery, early oral feeding is likely to become the preferred mode of nutrition after surgery for upper gastrointestinal tract malignancies. However, the optimal time to initiate early oral feeding remains unknown. OBJECTIVE: We aimed to compare the effects of different introduction times of early oral feeding in patients with upper gastrointestinal malignancies in terms of safety, tolerance, and effectiveness and to identify the optimal time for early oral feeding after surgery. METHODS: A random-effects meta-analysis was performed to identify evidence from relevant randomized controlled trials. Ten electronic databases were searched for randomized controlled trials from their earliest records to May 2023. Data were analyzed using the Stata 16.0 software. RESULTS: A total of 22 randomized controlled trials including 2510 patients and seven time points for oral feeding after surgery were considered. Regarding safety, oral feeding initiated on postoperative day 3 may be the safest (high-quality evidence) compared with other times. Regarding tolerance, oral feeding initiated on postoperative day 5 may be the most well-tolerated (moderate-quality evidence) compared with other times. Regarding effectiveness, oral feeding initiated on postoperative day 3 may be the most effective (moderate-quality evidence) compared with other times. CONCLUSIONS: Early oral feeding is safe, tolerable, and effective in postoperative patients with upper gastrointestinal malignancies. The optimal time to initiate early oral feeding after surgery was most likely postoperative day 3. The results of this meta-analysis provide evidence-based guidelines for clinical decision-making.

Liver transplantation meets gastrointestinal cancer.

Liver transplantation (LT) has emerged as a standard of care for patients with end-stage liver disease, providing a life-saving intervention for patients with severely compromised liver function in both the acute and chronic setting. While LT has also become a routine procedure for early-stage hepatocellular carcinoma (HCC), offering a potential cure by treating both the tumor and the underlying liver disease, its relevance in the context of other malignancies such as cholangiocellular carcinoma (CCA), combined hepatocellular-cholangiocarcinoma (cHCC-CCA) or liver metastases is still the subject of intense debate and no definite recommendations have yet been established. This review summarizes the current therapeutic standards in the context of LT for gastrointestinal malignancies and provides a reflection and outlook on current scientific and clinical developments.

Factors impacting early mobilization according to the Enhanced Recovery After Surgery guideline following gastrointestinal surgery: A prospective study.

AIM: Evidence shows that early mobilization according to the Enhanced Recovery After Surgery guideline promotes postoperative recovery in gastrointestinal cancer patients undergoing gastrointestinal surgery. However, compliance with the guideline in clinical settings remains low. This study aimed to investigate the factors influencing early mobilization after surgery. METHODS: A prospective research design was used. Data from 470 patients with gastrointestinal cancer who underwent gastrointestinal surgery between February 2021 and July 2022 were collected. RESULTS: More than half (53.6%) of the patients met the criteria for early mobilization. Females (odds ratio [OR], 1.53; 95% confidence interval [CI], 1.02-2.29), age 〉70 years (OR, 1.76; 95% CI, 1.09-2.86), low level of education (OR, 1.98; 95% CI, 1.12-3.95), and ≥4 catheters (OR, 1.86; 95% CI, 1.25-2.76) were barriers to early mobilization. CONCLUSIONS: Sex, age, education, and the number of catheters were found to be significant factors associated with non-early mobilization after gastrointestinal surgery. Geriatr Gerontol Int 2024; 24: 234-239.

Malignant Gastrointestinal Neuroectodermal Tumor of Small Intestine Showing DOG1 Expression: A Case Report and Review of Literature.

Malignant gastrointestinal neuroectodermal tumor (GNET), also referred to as clear cell sarcoma-like tumor of the GI tract is a rare mesenchymal tumor of the gastrointestinal tract. It has to be distinguished from various mimickers including gastrointestinal stromal tumor (GIST) due to its aggressive course and different natural history and therapeutic approach. Here we report a case of GNET arising in the small intestine with aberrant DOG1 expression posing a diagnostic challenge. In this context, the combination of clinical, histomorphological, immunohistochemical, and molecular features helped to establish a proper diagnosis.