Artificial Intelligence in Surgical Research: Accomplishments and Future Directions.

Mini-abstract: The study introduces various methods of performing conventional ML and their implementation in surgical areas, and the need to move beyond these traditional approaches given the advent of big data.

Objective: Investigate current understanding and future directions of machine learning applications, such as risk stratification, clinical data analytics, and decision support, in surgical practice.

Summary Background Data: The advent of the electronic health record, near unlimited computing, and open-source computational packages have created an environment for applying artificial intelligence, machine learning, and predictive analytic techniques to healthcare.

An immunoinformatics assessment of the cancer testis antigen, DDX53, as a potential early esophageal cancer antigen.

T-lymphocytes have been implicated in facilitating a pro-inflammatory, pro-tumorigenic microenvironment that worsens prognosis for esophageal carcinoma (ESCA). In this study, we identified tumor resident, T-cell receptor (TCR) complementarity determining region-3 (CDR3) amino acid sequences and employed an algorithm particularly suited to the big data setting to evaluate TCR CDR3-cancer testis antigen (CTA) chemical complementarities. Chemical complementarity of the ESCA TCR CDR3s and the cancer testis antigen DDX53 represented a disease-free survival (DFS) distinction, whereby the upper fiftieth percentile complementarity group correlated with worse DFS.

TRB CDR3 chemical complementarity with HBV epitopes correlates with increased hepatocellular carcinoma, disease-free survival.

The liver is a site of immune privilege, compared with the bladder and skin, for example. To study this attenuation of the immune response in the cancer setting, we compared quantities and features of adaptive immune receptor (IR) recombination reads obtained from hepatocellular carcinoma (HCC) and six other cancers. Of these cancers, HCC had the lowest numbers of IR recombination reads and was the only cancer with a greater number immunoglobulin rather than T-cell receptor recombination reads.

IGL CDR3 Hydropathy and Antigen Chemical Complementarity Associated with Greater Disease-Free Survival in Lung Adenocarcinoma: Implications for Gender Disparities.

With lung cancer remaining a challenging disease, new approaches to biomarker discovery and therapy development are needed. Recent immunogenomics, adaptive immune receptor approaches have indicated that it is very likely that B cells play an important role in mediating better overall outcomes. As such, we assessed physicochemical features of lung adenocarcinoma resident IGL complementarity determining region-3 (CDR3) amino acid (AA) sequences and determined that hydrophobic CDR3 AA sequences were associated with a better disease-free survival (DFS) probability.

Chemical Complementarity of Breast Cancer Resident, T-Cell Receptor CDR3 Domains and the Cancer Antigen, ARMC3, is Associated With Higher Levels of Survival and Granzyme Expression.

Introduction: One of the most pressing goals for cancer immunotherapy at this time is the identification of actionable antigens.

Methods: This study relies on the following considerations and approaches to identify potential breast cancer antigens: (i) the significant role of the adaptive immune receptor, complementarity determining region-3 (CDR3) in antigen binding, and the existence cancer testis antigens (CTAs); (ii) chemical attractiveness; and (iii) informing the relevance of the integration of items (i) and (ii) with patient outcome and tumor gene expression data.

Results: We have assessed CTAs for associations with survival, based on their chemical complementarity with tumor resident T-cell receptor (TCR), CDR3s.

Machine Learning Analysis of Postlaparoscopy Hernias and "I'm Leaving You to Close" Strategy.

Introduction: Contributing factors to postlaparoscopy hernia are unknown. We hypothesized that postlaparoscopy incisional hernias are increased when the index surgery was performed in teaching hospitals. Laparoscopic cholecystectomy was chosen as the archetype for open umbilical access.

Electrostatic Complementarities of Glioblastoma-Resident T-Cell Receptors and Cancer Testis Antigens Linked to Poor Outcomes and High Levels of Sphingosine Kinase-2 Expression.

Introduction: Glioblastoma (GBM) is the most aggressive primary brain tumor in adults. Despite a growing understanding of glioblastoma pathology, the prognosis remains poor.

Methods: In this study, we used a previously extensively benchmarked algorithm to retrieve immune receptor (IR) recombination reads from GBM exome files available from the cancer genome atlas.

Adaptive immune receptor features related to breast cancer tissue in Kenyan patients: high immunoglobulin gene expression and high levels of gamma-delta T-cells.

Background: Characterization of the breast cancer (BC) immune response may provide information for a point of intervention, such as application of immunotherapeutic treatments. In this study, we sought to recover and characterize the adaptive immune receptor (IR) recombination reads from genomics files representing Kenyan patients, to better understand the immune response specifically related to those patients.

Methods: We used a previously applied algorithm and software to obtain productive IR recombination reads from cancer and adjacent normal tissue samples representing 22 Kenyan BC patients.

Recipient Survival after Orthotopic Liver Transplantation: Interpretable Machine Learning Survival Tree Algorithm for Patient-Specific Outcomes.

Background: Elucidating contributors affecting liver transplant survival is paramount. Current methods offer crude global group outcomes. To refine patient-specific mortality probability estimation and to determine covariate interaction using recipient and donor data, we generated a survival tree algorithm, Recipient Survival After Orthotopic Liver Transplantation (ReSOLT), using United Network Organ Sharing (UNOS) transplant data.

Bacterial Sequencing Reads in Blood Exome Files from Melanoma and Cervical Cancer Patients are Associated with Cancer Recurrence.

Bacteremia poses great risk for morbidity and mortality for immunocompromised cancer patients. Although the presence of bacteria within solid tumors is gaining greater attention, few studies have analyzed species of bacteria in the blood and their effect on cancer clinical outcomes. Using the Kraken 2 taxonomic profiling tool, we classified bacteria present in blood and primary tumors of cervical cancer and melanoma cases.

Determining the value proposition of surgical care in CMS star rated hospitals.

Background: CMS Hospital Quality Star ratings reflect the quality of care given to patients. It is hypothesized that increased Star-rating is associated with higher cost and that the value proposition is diminished.

Methods: This study used the Florida AHCA inpatient dataset, CY2019.

Specific TCR V-J gene segment recombinations leading to the identification pan-V-J CDR3s associated with survival distinctions: diffuse large B-cell lymphoma.

In the diffuse large B-cell lymphoma (DLBCL) setting, we examined lymph node biopsy, T-cell receptor features, and the DLBLC patient human leukocyte antigen (HLA) alleles, to provide a basis for assessing survival distinctions represented by the National Cancer Institute Center for Cancer Research (NCICCR) dataset. While previous analyses of other cancer datasets have indicated that specific T-cell receptor (TCR) V or J gene segments, independently, can be associated with a survival distinction, we have here identified V-J recombinations, representing specific V and J gene segments associated with survival distinctions. As specific V-J recombinations represent relatively conserved complementarity determining region-3 (CDR3) amino acid sequences, we assessed the entire DLBCL NCICCR dataset for such conserved CDR3 features.

Extrinsic interactions in the microenvironment in vivo activate an antiapoptotic multidrug-resistant phenotype in CLL.

The Bcl-2 inhibitor venetoclax has yielded exceptional clinical responses in chronic lymphocytic leukemia (CLL). However, de novo resistance can result in failure to achieve negative minimal residual disease and predicts poor treatment outcomes. Consequently, additional proapoptotic drugs, such as inhibitors of Mcl-1 and Bcl-xL, are in development.