Advancing minimally invasive hepato-pancreato-biliary surgery: barriers to adoption and equitable access.

BACKGROUND: Despite a growing body of literature supporting the safety of robotic hepatopancreatobiliary (HPB) procedures, the adoption of minimally invasive techniques in HPB surgery has been slow compared to other specialties. We aimed to identify barriers to implementing robotic assisted surgery (RAS) in HPB and present a framework that highlights opportunities to improve adoption. METHODS: A modified nominal group technique guided by a 13-question framework was utilized. The meeting session was guided by senior authors, and field notes were also collected. Results were reviewed and free text responses were analyzed for major themes. A follow-up priority setting survey was distributed to all participants based on meeting results. RESULTS: Twenty three surgeons with varying robotic HPB experience from different practice settings participated in the discussion. The majority of surgeons identified operating room efficiency, having a dedicated operating room team, and the overall hospital culture and openness to innovation as important facilitators of implementing a RAS program. In contrast, cost, capacity building, disparities/risk of regionalization, lack of evidence, and time/effort were identified as the most significant barriers. When asked to prioritize the most important issues to be addressed, participants noted access and availability of the robot as the most important issue, followed by institutional support, cost, quality of supporting evidence, and need for robotic training. CONCLUSIONS: This study reports surgeons' perceptions of major barriers to equitable access and increased implementation of robotic HPB surgery. To overcome such barriers, defining key resources, adopting innovative solutions, and developing better methods of collecting long term data should be the top priorities.

Needs Assessment for the Development of a Sustainability Curriculum for Surgical Residents.

INTRODUCTION: The healthcare sector accounts for 8.5% of United States (U.S.) greenhouse gas emissions, of which one-third comes from operating rooms (ORs). As a result, there is great interest in decarbonizing the OR and surgical care. However, surgical residents are not routinely educated on the negative environmental impact of surgery or how to reduce it. In this paper, we present a formal needs assessment for a sustainability curriculum geared towards surgical residents. METHODS: Using Kern's Six-Step Framework for curriculum development, we conducted focus groups with surgical residents to perform a targeted needs assessment on 3 main topics: 1) the current state of surgical sustainability curricula; 2) resident knowledge regarding the environmental impact of surgery and barriers to sustainable practice; and 3) preferred educational methods and topics within sustainability education. We audio-recorded all focus groups and performed thematic analysis using anonymized transcripts. RESULTS: Fourteen residents participated in 3 focus groups, from which a qualitative analysis revealed 4 themes. First, surgery residents receive limited formal teaching on the negative environmental impact of surgical care or how to reduce this impact. Second, surgery residents have variable levels of prior education about and interest in sustainability in surgery. Third, several barriers prevent the implementation of sustainable changes in surgical practice, including a lack of institutional initiative, cultural inertia, concerns about workflow efficiency, and limited formal education. Finally, residents prefer to learn about practical ways to reduce waste, specifically through interactive approaches such as quality improvement initiatives. CONCLUSIONS: Given the increasing importance of sustainability in surgery, there is an urgent need for formal resident education on this topic. This needs assessment provides a valuable foundation for future sustainability curriculum development.

Effectiveness and Safety of Extended Treatment Apixaban Versus Low-Molecular-Weight Heparin in Cancer-Associated Venous Thromboembolism.

BACKGROUND: Limited real-world evidence is available comparing the safety and effectiveness of apixaban and low-molecular-weight heparins (LMWHs) for preventing recurrent venous thromboembolism (VTE) in patients with active cancer receiving anticoagulation in an extended treatment setting. This study evaluated the risk of bleeding and recurrent VTE in patients with cancer-associated VTE who were prescribed apixaban or LMWH for ≥3 months. METHODS: A US commercial claims database was used to identify adult patients with VTE and active cancer who initiated apixaban or LMWH 30 days following the first VTE diagnosis and had ≥3 months of continuous enrollment and 3 months of primary anticoagulation treatment. Patients were followed from the day after the end of primary anticoagulation treatment until the earliest of: date of disenrollment, discontinuation of index anticoagulant, switch to another anticoagulant, or end of the study period. Inverse-probability treatment weighting (IPTW) was used to balance treatment cohorts. Incidence rates (IRs) for the outcomes were calculated per 100 person-years (PY). Cox proportional hazard models were used to evaluate the adjusted risk of recurrent VTE, major bleeding (MB), and clinically relevant nonmajor bleeding (CRNMB). RESULTS: A total of 13,564 apixaban- and 2,808 LMWH-treated patients were analyzed. Post-IPTW, the treatment cohorts were balanced. Patients receiving apixaban had lower adjusted IRs for recurrent VTE (4.1 vs 9.6 per 100 PY), MB (6.3 vs 12.6), and CRNMB (26.1 vs 36.0) versus LMWH (P<.0001 for all comparisons) during the follow-up period. Patients on apixaban had a lower adjusted risk of recurrent VTE (hazard ratio [HR], 0.42; 95% CI, 0.34-0.53), MB (HR, 0.50; 95% CI, 0.41-0.61), and CRNMB (HR, 0.76; 95% CI, 0.68-0.85) versus LMWH. CONCLUSIONS: Extended anticoagulation treatment of ≥3 months with apixaban was associated with lower rates of recurrent VTE, MB, and CRNMB compared with LMWH in adults with cancer-associated VTE.

A Computer Vision Algorithm to Predict Superior Mesenteric Artery Margin Status for Patients with Pancreatic Ductal Adenocarcinoma.

OBJECTIVE: To evaluate the feasibility of developing a computer vision algorithm that uses preoperative computed tomography (CT) scans to predict superior mesenteric artery (SMA) margin status in patients undergoing Whipple for pancreatic ductal adenocarcinoma (PDAC), and to compare algorithm performance to that of expert abdominal radiologists and surgical oncologists. SUMMARY BACKGROUND DATA: Complete surgical resection is the only chance to achieve a cure for PDAC; however, current modalities to predict vascular invasion have limited accuracy. METHODS: Adult patients with PDAC who underwent Whipple and had preoperative contrast-enhanced CT scans were included (2010-2022). The SMA was manually annotated on the CT scans, and we trained a U-Net algorithm for SMA segmentation and a ResNet50 algorithm for predicting SMA margin status. Radiologists and surgeons reviewed the scans in a blinded fashion. SMA margin status per pathology reports was the reference. RESULTS: Two hundred patients were included. Forty patients (20%) had a positive SMA margin. For the segmentation task, the U-Net model achieved a Dice Similarity Coefficient of 0.90. For the classification task, all readers demonstrated limited sensitivity, although the algorithm had the highest sensitivity at 0.43 (versus 0.23 and 0.36 for the radiologists and surgeons, respectively). Specificity was universally excellent, with the radiologist and algorithm demonstrating the highest specificity at 0.94. Finally, the accuracy of the algorithm was 0.85 versus 0.80 and 0.76 for the radiologists and surgeons, respectively. CONCLUSIONS: We demonstrated the feasibility of developing a computer vision algorithm to predict SMA margin status using preoperative CT scans, highlighting its potential to augment the prediction of vascular involvement.

Gradient synchronization for multivariate functional data, with application to brain connectivity.

Quantifying the association between components of multivariate random curves is of general interest and is a ubiquitous and basic problem that can be addressed with functional data analysis. An important application is the problem of assessing functional connectivity based on functional magnetic resonance imaging (fMRI), where one aims to determine the similarity of fMRI time courses that are recorded on anatomically separated brain regions. In the functional brain connectivity literature, the static temporal Pearson correlation has been the prevailing measure for functional connectivity. However, recent research has revealed temporally changing patterns of functional connectivity, leading to the study of dynamic functional connectivity. This motivates new similarity measures for pairs of random curves that reflect the dynamic features of functional similarity. Specifically, we introduce gradient synchronization measures in a general setting. These similarity measures are based on the concordance and discordance of the gradients between paired smooth random functions. Asymptotic normality of the proposed estimates is obtained under regularity conditions. We illustrate the proposed synchronization measures via simulations and an application to resting-state fMRI signals from the Alzheimer's Disease Neuroimaging Initiative and they are found to improve discrimination between subjects with different disease status.

Interpretable artificial intelligence to optimise use of imatinib after resection in patients with localised gastrointestinal stromal tumours: an observational cohort study.

BACKGROUND: Current guidelines recommend use of adjuvant imatinib therapy for many patients with gastrointestinal stromal tumours (GISTs); however, its optimal treatment duration is unknown and some patient groups do not benefit from the therapy. We aimed to apply state-of-the-art, interpretable artificial intelligence (ie, predictions or prescription logic that can be easily understood) methods on real-world data to establish which groups of patients with GISTs should receive adjuvant imatinib, its optimal treatment duration, and the benefits conferred by this therapy. METHODS: In this observational cohort study, we considered for inclusion all patients who underwent resection of primary, non-metastatic GISTs at the Memorial Sloan Kettering Cancer Center (MSKCC; New York, NY, USA) between Oct 1, 1982, and Dec 31, 2017, and who were classified as intermediate or high risk according to the Armed Forces Institute of Pathology Miettinen criteria and had complete follow-up data with no missing entries. A counterfactual random forest model, which used predictors of recurrence (mitotic count, tumour size, and tumour site) and imatinib duration to infer the probability of recurrence at 7 years for a given patient under each duration of imatinib treatment, was trained in the MSKCC cohort. Optimal policy trees (OPTs), a state-of-the-art interpretable AI-based method, were used to read the counterfactual random forest model by training a decision tree with the counterfactual predictions. The OPT recommendations were externally validated in two cohorts of patients from Poland (the Polish Clinical GIST Registry), who underwent GIST resection between Dec 1, 1981, and Dec 31, 2011, and from Spain (the Spanish Group for Research in Sarcomas), who underwent resection between Oct 1, 1987, and Jan 30, 2011. FINDINGS: Among 1007 patients who underwent GIST surgery in MSKCC, 117 were included in the internal cohort; for the external cohorts, the Polish cohort comprised 363 patients and the Spanish cohort comprised 239 patients. The OPT did not recommend imatinib for patients with GISTs of gastric origin measuring less than 15·9 cm with a mitotic count of less than 11·5 mitoses per 5 mm2 or for those with small GISTs (<5·4 cm) of any site with a count of less than 11·5 mitoses per 5 mm2. In this cohort, the OPT cutoffs had a sensitivity of 92·7% (95% CI 82·4-98·0) and a specificity of 33·9% (22·3-47·0). The application of these cutoffs in the two external cohorts would have spared 38 (29%) of 131 patients in the Spanish cohort and 44 (35%) of 126 patients in the Polish cohort from unnecessary treatment with imatinib. Meanwhile, the risk of undertreating patients in these cohorts was minimal (sensitivity 95·4% [95% CI 89·5-98·5] in the Spanish cohort and 92·4% [88·3-95·4] in the Polish cohort). The OPT tested 33 different durations of imatinib treatment (<5 years) and found that 5 years of treatment conferred the most benefit. INTERPRETATION: If the identified patient subgroups were applied in clinical practice, as many as a third of the current cohort of candidates who do not benefit from adjuvant imatinib would be encouraged to not receive imatinib, subsequently avoiding unnecessary toxicity on patients and financial strain on health-care systems. Our finding that 5 years is the optimal duration of imatinib treatment could be the best source of evidence to inform clinical practice until 2028, when a randomised controlled trial with the same aims is expected to report its findings. FUNDING: National Cancer Institute.

Prostate Cancer Risk Stratification by Digital Histopathology and Deep Learning.

PURPOSE: Prostate cancer (PCa) represents a highly heterogeneous disease that requires tools to assess oncologic risk and guide patient management and treatment planning. Current models are based on various clinical and pathologic parameters including Gleason grading, which suffers from a high interobserver variability. In this study, we determine whether objective machine learning (ML)-driven histopathology image analysis would aid us in better risk stratification of PCa. MATERIALS AND METHODS: We propose a deep learning, histopathology image-based risk stratification model that combines clinicopathologic data along with hematoxylin and eosin- and Ki-67-stained histopathology images. We train and test our model, using a five-fold cross-validation strategy, on a data set from 502 treatment-naïve PCa patients who underwent radical prostatectomy (RP) between 2000 and 2012. RESULTS: We used the concordance index as a measure to evaluate the performance of various risk stratification models. Our risk stratification model on the basis of convolutional neural networks demonstrated superior performance compared with Gleason grading and the Cancer of the Prostate Risk Assessment Post-Surgical risk stratification models. Using our model, 3.9% of the low-risk patients were correctly reclassified to be high-risk and 21.3% of the high-risk patients were correctly reclassified as low-risk. CONCLUSION: These findings highlight the importance of ML as an objective tool for histopathology image assessment and patient risk stratification. With further validation on large cohorts, the digital pathology risk classification we propose may be helpful in guiding administration of adjuvant therapy including radiotherapy after RP.

Advancing minimally invasive hepato-pancreato-biliary surgery: ensuring safety with implementation.

BACKGROUND: Although minimally invasive hepato-pancreato-biliary (MIS HPB) surgery can be performed with good outcomes, there are currently no standardized requirements for centers or surgeons who wish to implement MIS HPB surgery. The aim of this study was to create a consensus statement regarding safe dissemination and implementation of MIS HPB surgical programs. METHODS: Sixteen key questions regarding safety in MIS HPB surgery were generated after a focused literature search and iterative review by three field experts. Participants for the working group were then selected using sequential purposive sampling and snowball techniques. Review of the 16 questions took place over a single 2-h meeting. The senior author facilitated the session, and a modified nominal group technique was used. RESULTS: Twenty three surgeons were in attendance. All participants agreed or strongly agreed that formal guidelines should exist for both institutions and individual surgeons interested in implementing MIS HPB surgery and that routine monitoring and reporting of institutional and surgeon technical outcomes should be performed. Regarding volume cutoffs, most participants (91%) agreed or strongly agreed that a minimum annual institutional volume cutoff for complex MIS HPB surgery, such as major hepatectomy or pancreaticoduodenectomy, should exist. A smaller proportion (74%) agreed or strongly agreed that a minimum annual surgeon volume requirement should exist. The majority of participants agreed or strongly agreed that surgeons were responsible for defining (100%) and enforcing (78%) guidelines to ensure the overall safety of MIS HPB programs. Finally, formal MIS HPB training, minimum case volume requirements, institutional support and infrastructure, and mandatory collection of outcomes data were all recognized as important aspects of safe implementation of MIS HPB surgery. CONCLUSIONS: Safe implementation of MIS HPB surgery requires a thoughtful process that incorporates structured training, sufficient volume and expertise, a proper institutional ecosystem, and monitoring of outcomes.

The association between population health management tools and clinician burnout in the United States VA primary care patient-centered medical home.

BACKGROUND: Technological burden and medical complexity are significant drivers of clinician burnout. Electronic health record(EHR)-based population health management tools can be used to identify high-risk patient populations and implement prophylactic health practices. Their impact on clinician burnout, however, is not well understood. Our objective was to assess the relationship between ratings of EHR-based population health management tools and clinician burnout. METHODS: We conducted cross-sectional analyses of 2018 national Veterans Health Administration(VA) primary care personnel survey, administered as an online survey to all VA primary care personnel (n = 4257, response rate = 17.7%), using bivariate and multivariate logistic regressions. Our analytical sample included providers (medical doctors, nurse practitioners, physicians' assistants) and nurses (registered nurses, licensed practical nurses). The outcomes included two items measuring high burnout. Primary predictors included importance ratings of 10 population health management tools (eg. VA risk prediction algorithm, recent hospitalizations and emergency department visits, etc.). RESULTS: High ratings of 9 tools were associated with lower odds of high burnout, independent of covariates including VA tenure, team role, gender, ethnicity, staffing, and training. For example, clinicians who rated the risk prediction algorithm as important were less likely to report high burnout levels than those who did not use or did not know about the tool (OR 0.73; CI 0.61-0.87), and they were less likely to report frequent burnout (once per week or more) (OR 0.71; CI 0.60-0.84). CONCLUSIONS: Burned-out clinicians may not consider the EHR-based tools important and may not be using them to perform care management. Tools that create additional technological burden may need adaptation to become more accessible, more intuitive, and less burdensome to use. Finding ways to improve the use of tools that streamline the work of population health management and/or result in less workload due to patients with poorly managed chronic conditions may alleviate burnout. More research is needed to understand the causal directional of the association between burnout and ratings of population health management tools.

Somatic Mutations in Surgically Treated Colorectal Liver Metastases: An Overview.

Colorectal cancer is the second most common cause of cancer death in the United States, and up to half of patients develop colorectal liver metastases (CRLMs). Notably, somatic genetic mutations, such as mutations in RAS, BRAF, mismatch repair (MMR) genes, TP53, and SMAD4, have been shown to play a prognostic role in patients with CRLM. This review summarizes and appraises the current literature regarding the most relevant somatic mutations in surgically treated CRLM by not only reviewing representative studies, but also providing recommendations for areas of future research. In addition, advancements in genetic testing and an increasing emphasis on precision medicine have led to a more nuanced understanding of these mutations; thus, more granular data for each mutation are reviewed when available. Importantly, such knowledge can pave the way for precision medicine with the ultimate goal of improving patient outcomes.

Machine learning improves prediction of postoperative outcomes after gastrointestinal surgery: a systematic review and meta-analysis.

BACKGROUND: Machine learning (ML) approaches have become increasingly popular in predicting surgical outcomes. However, it is unknown whether they are superior to traditional statistical methods such as logistic regression (LR). This study aimed to perform a systematic review and meta-analysis to compare the performance of ML vs LR models in predicting postoperative outcomes for patients undergoing gastrointestinal (GI) surgery. METHODS: A systematic search of Embase, MEDLINE, Cochrane, Web of Science, and Google Scholar was performed through December 2022. The primary outcome was the discriminatory performance of ML vs LR models as measured by the area under the receiver operating characteristic curve (AUC). A meta-analysis was then performed using a random effects model. RESULTS: A total of 62 LR models and 143 ML models were included across 38 studies. On average, the best-performing ML models had a significantly higher AUC than the LR models (ΔAUC, 0.07; 95% CI, 0.04-0.09; P < .001). Similarly, on average, the best-performing ML models had a significantly higher logit (AUC) than the LR models (Δlogit [AUC], 0.41; 95% CI, 0.23-0.58; P < .001). Approximately half of studies (44%) were found to have a low risk of bias. Upon a subset analysis of only low-risk studies, the difference in logit (AUC) remained significant (ML vs LR, Δlogit [AUC], 0.40; 95% CI, 0.14-0.66; P = .009). CONCLUSION: We found a significant improvement in discriminatory ability when using ML over LR algorithms in predicting postoperative outcomes for patients undergoing GI surgery. Subsequent efforts should establish standardized protocols for both developing and reporting studies using ML models and explore the practical implementation of these models.

Gait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches.

Differences in gait patterns of children with Duchenne muscular dystrophy (DMD) and typically developing (TD) peers are visible to the eye, but quantifications of those differences outside of the gait laboratory have been elusive. In this work, we measured vertical, mediolateral, and anteroposterior acceleration using a waist-worn iPhone accelerometer during ambulation across a typical range of velocities. Fifteen TD and fifteen DMD children from 3 to 16 years of age underwent eight walking/running activities, including five 25 m walk/run speed-calibration tests at a slow walk to running speeds (SC-L1 to SC-L5), a 6-min walk test (6MWT), a 100 m fast walk/jog/run (100MRW), and a free walk (FW). For clinical anchoring purposes, participants completed a Northstar Ambulatory Assessment (NSAA). We extracted temporospatial gait clinical features (CFs) and applied multiple machine learning (ML) approaches to differentiate between DMD and TD children using extracted temporospatial gait CFs and raw data. Extracted temporospatial gait CFs showed reduced step length and a greater mediolateral component of total power (TP) consistent with shorter strides and Trendelenberg-like gait commonly observed in DMD. ML approaches using temporospatial gait CFs and raw data varied in effectiveness at differentiating between DMD and TD controls at different speeds, with an accuracy of up to 100%. We demonstrate that by using ML with accelerometer data from a consumer-grade smartphone, we can capture DMD-associated gait characteristics in toddlers to teens.

Gait Event Detection and Travel Distance Using Waist-Worn Accelerometers across a Range of Speeds: Automated Approach.

Estimation of temporospatial clinical features of gait (CFs), such as step count and length, step duration, step frequency, gait speed, and distance traveled, is an important component of community-based mobility evaluation using wearable accelerometers. However, accurate unsupervised computerized measurement of CFs of individuals with Duchenne muscular dystrophy (DMD) who have progressive loss of ambulatory mobility is difficult due to differences in patterns and magnitudes of acceleration across their range of attainable gait velocities. This paper proposes a novel calibration method. It aims to detect steps, estimate stride lengths, and determine travel distance. The approach involves a combination of clinical observation, machine-learning-based step detection, and regression-based stride length prediction. The method demonstrates high accuracy in children with DMD and typically developing controls (TDs) regardless of the participant's level of ability. Fifteen children with DMD and fifteen TDs underwent supervised clinical testing across a range of gait speeds using 10 m or 25 m run/walk (10 MRW, 25 MRW), 100 m run/walk (100 MRW), 6-min walk (6 MWT), and free-walk (FW) evaluations while wearing a mobile-phone-based accelerometer at the waist near the body's center of mass. Following calibration by a trained clinical evaluator, CFs were extracted from the accelerometer data using a multi-step machine-learning-based process and the results were compared to ground-truth observation data. Model predictions vs. observed values for step counts, distance traveled, and step length showed a strong correlation (Pearson's r = -0.9929 to 0.9986, p < 0.0001). The estimates demonstrated a mean (SD) percentage error of 1.49% (7.04%) for step counts, 1.18% (9.91%) for distance traveled, and 0.37% (7.52%) for step length compared to ground-truth observations for the combined 6 MWT, 100 MRW, and FW tasks. Our study findings indicate that a single waist-worn accelerometer calibrated to an individual's stride characteristics using our methods accurately measures CFs and estimates travel distances across a common range of gait speeds in both DMD and TD peers.

Incidence of hypocortisolism with long-term budesonide irrigation for chronic rhinosinusitis.

BACKGROUND: Budesonide irrigations (BIs) are commonly used to control inflammation in chronic rhinosinusitis (CRS). In 2016 we reported an analysis of long-term BI with regard to hypothalamic-pituitary-adrenal axis function. We present a follow-up analysis in a larger cohort of patients with longer follow-up. METHODS: Patients were candidates for stimulated cortisol testing after regularly performing BI for CRS at least daily for ≥6 months. We retrospectively evaluated all patients who received stimulated cortisol testing at our center between 2012 and 2022. We correlated cortisol levels with the use of BI and other forms of corticosteroids. RESULTS: We analyzed 401 cortisol test results in 285 patients. The mean duration of use was 34 months. Overall, 21.8% of patients were hypocortisolemic (<18 ug/dL) at first test. In patients who used only BI, the rate of hypocortisolemia was 7.5%, whereas in patients who also used concurrent oral and inhaled corticosteroids, the rate was 40% to 50%. Lower cortisol levels were associated with male sex (p < 0.0001) and concomitant use of oral and inhaled steroids (p < 0.0001). Duration of BI use was not significantly associated with lower cortisol levels (p = 0.701), nor was greater dosing frequency (p = 0.289). CONCLUSION: Prolonged use of BI alone is not likely to cause hypocortisolemia in the majority of patients. However, concomitant use of inhaled and oral steroids and male sex may be associated with hypocortisolemia. Surveillance of cortisol levels may be considered in vulnerable populations who use BI regularly, particularly in patients using other forms of corticosteroids with known systemic absorption.

Is Precision Surgery Applicable to Colorectal Liver Metastases? A Systematic Review and Meta-analysis of Studies that Investigate the Association of Surgical Technique with Outcomes in the Context of Distinct Tumor Biology.

BACKGROUND: Although some data suggest that patients with mutRAS colorectal liver metastases (CRLM) may benefit from anatomic hepatectomy, this topic remains controversial. We performed a systematic review and meta-analysis to determine whether RAS mutation status was associated with prognosis relative to surgical technique [anatomic resection (AR) vs. nonanatomic resection (NAR)] among patients with CRLM. PATIENTS AND METHODS: A systematic review and meta-analysis of studies were performed to investigate the association of AR versus NAR with overall and liver-specific disease-free survival (DFS and liver-specific DFS, respectively) in the context of RAS mutation status. RESULTS: Overall, 2018 patients (831 mutRAS vs. 1187 wtRAS) were included from five eligible studies. AR was associated with a 40% improvement in liver-specific DFS [hazard ratio (HR) = 0.6, 95% confidence interval (CI) 0.44-0.81, p = 0.01] and a 28% improvement in overall DFS (HR = 0.72, 95% CI 0.54-0.95, p = 0.02) among patients with mutRAS tumors; in contrast, AR was not associated with any improvement in liver-specific DFS or overall DFS among wtRAS patients. These differences may have been mediated by the 40% decreased incidence in R1 resection among patients with mutRAS tumors who underwent AR versus NAR [relative risk (RR): 0.6, 95% CI 0.40-0.91, p = 0.02]. In contrast, the probability of an R1 resection was not decreased among wtRAS patients who underwent AR versus NAR (RR: 0.93, 95% CI 0.69-1.25, p = 0.62). CONCLUSIONS: The data suggest that precision surgery may be relevant to CRLM. Specifically, rather than a parenchymal sparing dogma for all patients, AR may have a role in individuals with mutRAS tumors.

Meta-Learned Models of Cognition.

Psychologists and neuroscientists extensively rely on computational models for studying and analyzing the human mind. Traditionally, such computational models have been hand-designed by expert researchers. Two prominent examples are cognitive architectures and Bayesian models of cognition. While the former requires the specification of a fixed set of computational structures and a definition of how these structures interact with each other, the latter necessitates the commitment to a particular prior and a likelihood function which - in combination with Bayes' rule - determine the model's behavior. In recent years, a new framework has established itself as a promising tool for building models of human cognition: the framework of meta-learning. In contrast to the previously mentioned model classes, meta-learned models acquire their inductive biases from experience, i.e., by repeatedly interacting with an environment. However, a coherent research program around meta-learned models of cognition is still missing to this day. The purpose of this article is to synthesize previous work in this field and establish such a research program. We accomplish this by pointing out that meta-learning can be used to construct Bayes-optimal learning algorithms, allowing us to draw strong connections to the rational analysis of cognition. We then discuss several advantages of the meta-learning framework over traditional methods and reexamine prior work in the context of these new insights.

A labeled data set of underwater images of fish and crab species from five mesohabitats in Puget Sound WA USA.

The sustainable management of fisheries and aquaculture requires an understanding of how these activities interact with natural fish populations. GoPro cameras were used to collect an underwater video data set on and around shellfish aquaculture farms in an estuary in the NE Pacific from June to August 2017 and June to August 2018 to better understand habitat use by the local fish and crab communities. Images extracted from these videos were labeled to produce a data set that is suitable for use in training computer vision models. The labeled data set contains 77,739 images sampled from the collected video; 67,990 objects (fishes and crustaceans) have been annotated in 30,384 images (the remainder have been annotated as "empty"). The metadata of the data set also indicates whether a physical magenta filter was used during video collection to counteract reduced visibility. These data have the potential to help researchers address system-level and in-depth regional shellfish aquaculture questions related to ecosystem services and shellfish aquaculture interactions.

An interpretable AI model for recurrence prediction after surgery in gastrointestinal stromal tumour: an observational cohort study.

Background: There are several models that predict the risk of recurrence following resection of localised, primary gastrointestinal stromal tumour (GIST). However, assessment of calibration is not always feasible and when performed, calibration of current GIST models appears to be suboptimal. We aimed to develop a prognostic model to predict the recurrence of GIST after surgery with both good discrimination and calibration by uncovering and harnessing the non-linear relationships among variables that predict recurrence. Methods: In this observational cohort study, the data of 395 adult patients who underwent complete resection (R0 or R1) of a localised, primary GIST in the pre-imatinib era at Memorial Sloan Kettering Cancer Center (NY, USA) (recruited 1982-2001) and a European consortium (Spanish Group for Research in Sarcomas, 80 sites) (recruited 1987-2011) were used to train an interpretable Artificial Intelligence (AI)-based model called Optimal Classification Trees (OCT). The OCT predicted the probability of recurrence after surgery by capturing non-linear relationships among predictors of recurrence. The data of an additional 596 patients from another European consortium (Polish Clinical GIST Registry, 7 sites) (recruited 1981-2013) who were also treated in the pre-imatinib era were used to externally validate the OCT predictions with regard to discrimination (Harrell's C-index and Brier score) and calibration (calibration curve, Brier score, and Hosmer-Lemeshow test). The calibration of the Memorial Sloan Kettering (MSK) GIST nomogram was used as a comparative gold standard. We also evaluated the clinical utility of the OCT and the MSK nomogram by performing a Decision Curve Analysis (DCA). Findings: The internal cohort included 395 patients (median [IQR] age, 63 [54-71] years; 214 men [54.2%]) and the external cohort included 556 patients (median [IQR] age, 60 [52-68] years; 308 men [55.4%]). The Harrell's C-index of the OCT in the external validation cohort was greater than that of the MSK nomogram (0.805 (95% CI: 0.803-0.808) vs 0.788 (95% CI: 0.786-0.791), respectively). In the external validation cohort, the slope and intercept of the calibration curve of the main OCT were 1.041 and 0.038, respectively. In comparison, the slope and intercept of the calibration curve for the MSK nomogram was 0.681 and 0.032, respectively. The MSK nomogram overestimated the recurrence risk throughout the entire calibration curve. Of note, the Brier score was lower for the OCT compared to the MSK nomogram (0.147 vs 0.564, respectively), and the Hosmer-Lemeshow test was insignificant (P = 0.087) for the OCT model but significant (P < 0.001) for the MSK nomogram. Both results confirmed the superior discrimination and calibration of the OCT over the MSK nomogram. A decision curve analysis showed that the AI-based OCT model allowed for superior decision making compared to the MSK nomogram for both patients with 25-50% recurrence risk as well as those with >50% risk of recurrence. Interpretation: We present the first prognostic models of recurrence risk in GIST that demonstrate excellent discrimination, calibration, and clinical utility on external validation. Additional studies for further validation are warranted. With further validation, these tools could potentially improve patient counseling and selection for adjuvant therapy. Funding: The NCI SPORE in Soft Tissue Sarcoma and NCI Cancer Center Support Grants.

Development of hybrid scaffolds with biodegradable polymer composites and bioactive hydrogels for bone tissue engineering.

The development of treatments for critical-sized bone defects has been considered an important topic in the biomedical field because of the high demand for transplantable bone grafts. Following the concept of tissue engineering, implantation of biocompatible porous scaffolds carrying cells and regulating factors is the most efficient strategy to stimulate clinical bone regeneration. With the advancement in the development of 3D-printing techniques, scaffolds with highly controllable architectures can be fabricated to further improve healing efficacies. However, challenges such as the limited biocompatibility of resin materials and poor cell-carrying capacities still exist in the application of current scaffolds. In this study, a novel biodegradable polymer, poly (ethylene glycol)-co-poly (glycerol sebacate) acrylate (PEGSA), was synthesized and blended with hydroxyapatite (HAP) nanoparticles to produce osteoinductive and photocurable resins for 3D printing. The composites were optimized and applied in the fabrication of gyroid scaffolds with biomimetic characteristics and high permeability, followed by the combination of bioactive hydrogels containing Wharton's jelly-derived mesenchymal stem cells (WJMSC) to increase the efficiency of cell delivery. The promotion of osteogenesis from 3D-printed scaffolds was confirmed in-vivo while the hybrid scaffolds were proven to be great platforms for WJMSC culture and differentiation in-vitro. These results indicate that the proposed hybrid systems, combining osteoinductive 3D-printed scaffolds and cell-laden hydrogels, have great potential for bone tissue engineering and are expected to be applied in the treatment of bone defects based on active tissue regeneration.