Feasibility of machine learning-based modeling and prediction using multiple centers data to assess intrahepatic cholangiocarcinoma outcomes

Current applications of indocyanine green (ICG) in abdominal, gynecologic and urologic surgery: a meta-review and quality analysis with use of the AMSTAR 2 instrument

BACKGROUND

Indocyanine green (ICG) is an injectable fluorochrome that has recently gained popularity as a means of assisting intraoperative visualization during laparoscopic and robotic surgery. Many systematic reviews and meta-analyses have been published. We conducted a meta-review to synthesize the findings of these studies.

METHODS

PubMed and Embase were searched to identify systematic reviews and meta-analyses coping with the uses of ICG in abdominal operations, including Metabolic Bariatric Surgery, Cholecystectomy, Colorectal, Esophageal, Gastric, Hepato-Pancreato-Biliary, Obstetrics and Gynecology (OG), Pediatric Surgery, Surgical Oncology, Urology, (abdominal) Vascular Surgery, Adrenal and Splenic Surgery, and Interdisciplinary tasks, until September 2023. We submitted the retrieved meta-analyses to qualitative analysis based on the AMSTAR 2 instrument.

RESULTS

We identified 116 studies, 41 systematic reviews (SRs) and 75 meta-analyses (MAs), spanning 2013-2023. The most thoroughly investigated (sub)specialties were Colorectal (6 SRs, 25 MAs), OG (9 SRs, 15 MAs), and HPB (4 SRs, 12 MAs). Interestingly, there was high heterogeneity regarding the administered ICG doses, routes, and timing. The use of ICG offered a clear benefit regarding anastomotic leak prevention, particularly after colorectal and esophageal surgery. There was no clear benefit regarding sentinel node detection after OG. According to the AMSTAR 2 tool, most meta-analyses ranked as "critically low" (34.7%) or "low" (58.7%) quality. There were only five meta-analyses (6.7%) that qualified as "moderate" quality, whereas there were no "high" quality reviews.

CONCLUSIONS

Regardless of the abundance of pertinent literature and reviews, surgeons should be cautious when interpreting their results on ICG use in abdominal surgery. Future reviews should focus on ensuring methodological vigor; establishing clear protocols of ICG dose, route of administration, and timing; and improving reporting quality. Other sources of data (e.g., registries) and novel methods of data analysis (e.g., machine learning) might also contribute to an enhanced role of ICG as a decision-making tool in surgery.

Application of AI on cholangiocarcinoma

Cholangiocarcinoma, classified as intrahepatic, perihilar, and extrahepatic, is considered a deadly malignancy of the hepatobiliary system. Most cases of cholangiocarcinoma are asymptomatic. Therefore, early detection of cholangiocarcinoma is significant but still challenging. The routine screening of a tumor lacks specificity and accuracy. With the application of AI, high-risk patients can be easily found by analyzing their clinical characteristics, serum biomarkers, and medical images. Moreover, AI can be used to predict the prognosis including recurrence risk and metastasis. Although they have some limitations, AI algorithms will still significantly improve many aspects of cholangiocarcinoma in the medical field with the development of computing power and technology.

The Effectiveness of Metabolic Bariatric Surgery in Preventing Gynecologic Cancer - from Pathophysiology to Clinical Outcomes

Obesity and cancer represent two pandemics of current civilization, the progression of which has followed parallel trajectories. To time, thirteen types of malignancies have been recognized as obesity-related cancers, including breast (in postmenopausal women), endometrial, and ovarian cancer. Pathophysiologic mechanisms that connect the two entities include insulin resistance, adipokine imbalance, increased peripheral aromatization and estrogen levels, tissue hypoxia, and disrupted immunity in the cellular milieu. Beyond the connection of obesity to carcinogenesis at a molecular and cellular level, clinicians should always be cognizant of the fact that obesity might have secondary impacts on the diagnosis and treatment of gynecologic cancer, including limited access to effective screening programs, resistance to chemotherapy and targeted therapies, persisting lymphedema, etc. Metabolic bariatric surgery represents an attractive intervention not only for decreasing the risk of carcinogenesis in high-risk women living with obesity but most importantly as a measure to improve disease-specific and overall survival in patients with diagnosed obesity-related gynecologic malignancies. The present narrative review summarizes current evidence on the underlying pathophysiologic mechanisms, the clinical data, and the potential applications of metabolic bariatric surgery in all types of gynecologic cancer, including breast, endometrial, ovarian, cervical, vulvar, and vaginal.

Deep Learning for the Prediction of the Survival of Midline Diffuse Glioma with an H3K27M Alteration

BACKGROUND

The prognosis of diffuse midline glioma (DMG) patients with H3K27M (H3K27M-DMG) alterations is poor; however, a model that encourages accurate prediction of prognosis for such lesions on an individual basis remains elusive. We aimed to construct an H3K27M-DMG survival model based on DeepSurv to predict patient prognosis.

METHODS

Patients recruited from a single center were used for model training, and patients recruited from another center were used for external validation. Univariate and multivariate Cox regression analyses were used to select features. Four machine learning models were constructed, and the consistency index (C-index) and integrated Brier score (IBS) were calculated. We used the receiver operating characteristic curve (ROC) and area under the receiver operating characteristic (AUC) curve to assess the accuracy of predicting 6-month, 12-month, 18-month and 24-month survival rates. A heatmap of feature importance was used to explain the results of the four models.

RESULTS

We recruited 113 patients in the training set and 23 patients in the test set. We included tumor size, tumor location, Karnofsky Performance Scale (KPS) score, enhancement, radiotherapy, and chemotherapy for model training. The accuracy of DeepSurv prediction is highest among the four models, with C-indexes of 0.862 and 0.811 in the training and external test sets, respectively. The DeepSurv model had the highest AUC values at 6 months, 12 months, 18 months and 24 months, which were 0.970 (0.919-1), 0.950 (0.877-1), 0.939 (0.845-1), and 0.875 (0.690-1), respectively. We designed an interactive interface to more intuitively display the survival probability prediction results provided by the DeepSurv model.

CONCLUSION

The DeepSurv model outperforms traditional machine learning models in terms of prediction accuracy and robustness, and it can also provide personalized treatment recommendations for patients. The DeepSurv model may provide decision-making assistance for patients in formulating treatment plans in the future.

Dissecting the tumor ecosystem of liver cancers in the single-cell era

Primary liver cancers (PLCs) are a broad class of malignancies that include HCC, intrahepatic cholangiocarcinoma, and combined hepatocellular and intrahepatic cholangiocarcinoma. PLCs are often associated with a poor prognosis due to their high relapse and low therapeutic response rates. Importantly, PLCs exist within a dynamic and complex tumor ecosystem, which includes malignant, immune, and stromal cells. It is critical to dissect the PLC tumor ecosystem to uncover the underlying mechanisms associated with tumorigenesis, relapse, and treatment resistance to facilitate the discovery of novel therapeutic targets. Single-cell and spatial multi-omics sequencing techniques offer an unprecedented opportunity to elucidate spatiotemporal interactions among heterogeneous cell types within the complex tumor ecosystem. In this review, we describe the latest advances in single-cell and spatial technologies and review their applications with respect to dissecting liver cancer tumor ecosystems.

A Paradigm Shift in Primary Liver Cancer Therapy Utilizing Genomics, Molecular Biomarkers, and Artificial Intelligence

Primary liver cancer is the sixth most common cancer worldwide and the third leading cause of cancer-related death. Conventional therapies offer limited survival benefit despite improvements in locoregional liver-directed therapies, which highlights the underlying complexity of liver cancers. This review explores the latest research in primary liver cancer therapies, focusing on developments in genomics, molecular biomarkers, and artificial intelligence. Attention is also given to ongoing research and future directions of immunotherapy and locoregional therapies of primary liver cancers.