Decision-making based on 3D printed models in laparoscopic liver resections with intraoperative ultrasound: a prospective observational study.

OBJECTIVES: The aim of this study was to evaluate impact of 3D printed models on decision-making in context of laparoscopic liver resections (LLR) performed with intraoperative ultrasound (IOUS) guidance. METHODS: Nineteen patients with liver malignances (74% were colorectal cancer metastases) were prospectively qualified for LLR or radiofrequency ablation in a single center from April 2017 to December 2018. Models were 3DP in all cases based on CT and facilitated optical visualization of tumors' relationships with portal and hepatic veins. Planned surgical extent and its changes were tracked after CT analysis and 3D model inspection, as well as intraoperatively using IOUS. RESULTS: Nineteen patients were included in the analysis. Information from either 3DP or IOUS led to changes in the planned surgical approach in 13/19 (68%) patients. In 5/19 (26%) patients, the 3DP model altered the plan of the surgery preoperatively. In 4/19 (21%) patients, 3DP independently changed the approach. In one patient, IOUS modified the plan post-3DP. In 8/19 (42%) patients, 3DP model did not change the approach, whereas IOUS did. In total, IOUS altered surgical plans in 9 (47%) cases. Most of those changes (6/9; 67%) were caused by detection of additional lesions not visible on CT and 3DP. CONCLUSIONS: 3DP can be helpful in planning complex and major LLRs and led to changes in surgical approach in 26.3% (5/19 patients) in our series. 3DP may serve as a useful adjunct to IOUS. KEY POINTS: • 3D printing can help in decision-making before major and complex resections in patients with liver cancer. • In 5/19 patients, 3D printed model altered surgical plan preoperatively. • Most surgical plan changes based on intraoperative ultrasonography were caused by detection of additional lesions not visible on CT and 3D model.

Holographically-Guided Endovascular Aneurysm Repair.

Purpose: To demonstrate the feasibility of augmented reality visualization in planning and navigating endovascular aortic repair. Technique: A 77-year-old patient with abdominal aortic aneurysm was treated with endovascular repair. An augmented reality head-mounted display was used during the procedure. The aneurysm and bones were projected as 3-dimensional holograms. The operator controlled the device with gestures and voice commands (movement, rotation, cutting through, and zooming). Moreover, the hologram was placed in front of the angiography monitor and manually registered with fluoroscopy. Conclusion: Augmented reality with holographic rendering is feasible and helpful during endovascular aortic repair. Its routine use could possibly lead to shorter operating time, reduced contrast volume, and lower radiation dose; however, larger studies are required to obtain statistically significant results on the outcomes.

Meta-analysis of short- and long-term outcomes after pure laparoscopic versus open liver surgery in hepatocellular carcinoma patients.

BACKGROUND: The advantages of laparoscopy are widely known. Nevertheless, its legitimacy in liver surgery is often questioned because of the uncertain value associated with minimally invasive methods. Our main goal was to compare the outcomes of pure laparoscopic (LLR) and open liver resection (OLR) in patients with hepatocellular carcinoma. METHODS: We searched EMBASE, MEDLINE, Web of Science, and The Cochrane Library databases to find eligible studies. The most recent search was performed on December 1, 2017. Studies were regarded as suitable if they reported morbidity in patients undergoing LLR versus OLR. Extracted data were pooled and subsequently used in a meta-analysis with a random-effects model. Clinical applicability of results was evaluated using predictive intervals. Review was reported following the PRISMA guidelines. RESULTS: From 2085 articles, forty-three studies (N = 5100 patients) were included in the meta-analysis. Our findings showed that LLR had lower overall morbidity than OLR (15.59% vs. 29.88%, p < 0.001). Moreover, major morbidity was reduced in the LLR group (3.78% vs. 8.69%, p < 0.001). There were no differences between groups in terms of mortality (1.58% vs. 2.96%, p = 0.05) and both 3- and 5-year overall survival (68.97% vs. 68.12%, p = 0.41) and disease-free survival (46.57% vs. 44.84%, p = 0.46). CONCLUSIONS: The meta-analysis showed that LLR is beneficial in terms of overall morbidity and non-procedure-specific complications. That being said, these results are based on non-randomized trials. For these reasons, we are calling for randomization in upcoming studies. Systematic review registration: PROSPERO registration number CRD42018084576.

Functional outcomes after resections for low rectal tumors: comparison of Transanal with laparoscopic Total Mesorectal excision.

BACKGROUND: Aim of this study was to evaluate functional outcomes of transanal total mesorectal excision (TaTME) in comparison to conventional laparoscopic approach (LaTME) in terms of low anterior resection syndrome (LARS). METHODS: Forty-six patients who underwent total mesorectal excision for low rectal cancer between 2013 and 2017 were enrolled. Primary outcome was the severity of faecal incontinence, assessed both before the treatment and 6 months after ileostomy reversal. LARS score and Jorge-Wexner scale were utilized to analyze its severity. RESULTS: Twenty (87%) from TaTME and 21 (91%) from LaTME group developed LARS postoperatively. There were no significant differences between groups in terms of LARS occurrence (p = 0.63) and severity. The median Wexner score was comparable in both groups (8 [IQR: 4-12] vs 7 [3-11], p = 0.83). Univariate analysis revealed that postoperative complications were a risk factor for LARS development (p = 0.02). Perioperative outcomes, including operative time, blood loss and intraoperative adverse events did not differ significantly between groups either. Five TaTME patients developed postoperative complications, while there were morbidity 6 cases in LaTME group. Quality of mesorectal excision was comparable with 20 and 19 complete cases in TaTME and LaTME groups, respectively. CONCLUSIONS: TaTME provided comparable outcomes in terms of functional outcomes in comparison to LaTME for total mesorectal excision in low rectal cancers. Having said that, LARS prevalence is still high and requires further evaluation of the technique.

The Use of a Three-Dimensional Printed Model for Surgical Excision of a Vascular Lesion in the Head and Neck.

Facial vascular lesions are considered a great therapeutic challenge due to the considerable variability of clinical presentations. Surgical removal requires precise planning and advanced visualization to understand the three-dimensional anatomical relationships better.The aim of the study was to evaluate the feasibility of three-dimensional printed models, based on computed tomography angiography (CTA), in planning and guiding surgical excision of vascular lesions.A patient with a suspected vascular malformation in the face was recruited for participation in this feasibility study. Two personalized three-dimensional models were printed based off 2 separate CTA examinations. These constructs were used in preoperative planning and navigating surgical excision. The three-dimensional constructs identified the vicinity of the lesion and highlighted significant anatomical structures including the infraorbital nerve and vessels supplying the area of vascular anomaly. On postoperative follow-up the patient reported no recurrence of swelling and no sensory deficits.A personalized three-dimensional printed model of a facial vascular lesion was developed based on CTA images and used in preoperative planning and navigating surgical excision. It was most useful in establishing dangerous areas during the dissection process, including critical anatomical structures such as the infraorbital nerve. Combining conventional imaging techniques with three-dimensional printing may lead to improved diagnosis of vascular malformations and should be considered a useful adjunct to surgical management.

What Makes Bariatric Operations Difficult-Results of a National Survey.

Background and objective: The most commonly performed bariatric procedures include laparoscopic sleeve gastrectomy (LSG), laparoscopic Roux-en-Y gastric bypass (LRYGB), and one anastomosis gastric bypass-mini gastric bypass (OAGB-MGB). A study comparing the degree of difficulty among those procedures could serve as a guide for decision making in bariatric surgery and further improve training programs for general surgery trainees. The aim of this study was to compare the subjective level of technical difficulty of LSG, LRYGB, and OAGB-MGB as perceived by surgeons and surgical residents. Materials and Methods: An anonymous internet-based survey was designed to evaluate the subjective opinions of surgeons and surgical residents in training in Poland. It covered baseline characteristics of the participants, difficulty of LSG, OAGB-MGB, LRYGB and particular stages of each operation assessed on a 1-5 scale. Results: Overall, 70 surgeons and residents participated in our survey. The mean difficulty degree of LSG was 2.34 ± 0.89. The reinforcing staple line with sutures was considered most difficult stage of this operation (3.17 ± 1.19). The LRYGB operation had an average difficulty level of 3.87 ± 1.04. Creation of the gastrojejunostomy was considered the most difficult stage of LRYGB with a mean difficulty level (3.68 ± 1.16). Responders to our survey assessed the mean degree of difficulty of OAGB-MGB as 2.34 ± 0.97. According to participating surgeons, creating the gastrojejunostomy is the most difficult phase of this operation (3.68 ± 1.16). Conclusion: The LSG is perceived by surgeons as a relatively easy operation. The LRYGB was considered to be the most technically challenging procedure in our survey. Operative stages, which require intra-abdominal suturing with laparoscopic instruments, seem to be the most difficult phases of each operation.

Changes in plasma albumin levels in early detection of infectious complications after laparoscopic colorectal cancer surgery with ERAS protocol.

BACKGROUND: Combination of laparoscopic approach with ERAS protocol in colorectal surgery allows for an early discharge. However there is a risk that some of the discharged patients are developing, asymptomatic at the time, infectious complications. This may lead to a delay in diagnostics and proper treatment introduction. We aimed to assess the usefulness of preoperative plasma albumin concentration and their changes as indicators of infectious complications in patients undergoing colorectal cancer surgery. METHODS: Prospective analysis included 105 consecutive patients who underwent laparoscopic colorectal cancer resection between August 2014 and September 2016. In all cases standardised 16-item perioperative care ERAS protocol was used (mean compliance > 85%). Patients with IBD, distant metastases, undergoing emergency or multivisceral resection were excluded. Blood samples were collected preoperatively and on POD 1, 2, 3. Plasma albumin concentration was measured. Patients were divided into two groups depending on the presence of infectious complications. We analysed the differences in the levels of albumin and the dynamics of changes. RESULTS: Group 1-82 not complicated patients, Group 2-23 patients with at least one infectious complication. Preoperatively, there were no significant differences in the levels of serum albumin between those groups (Group 1-38.7 ± 4.9 g/l; Group 2-37.7 ± 5.0 g/l). In postoperative period, decrease was observed in both (POD 1: Group 1-36.5 ± 4.2 g/l, Group 2-34.7 ± 4.2 g/l, p = 0.07; POD 2: Group 1-36.2 ± 4.1 g/l, Group 2-32.6 ± 5.6 g/l, p = 0.01; POD 3: Group 1-36.0 ± 4.4 g/l, Group 2-30.9 ± 3.5 g/l, p = 0.01). The decrease was significantly greater in Group 2 on POD 2 and 3. CONCLUSIONS: We showed that a regular measurement of albumin in the early postoperative days may be beneficial in the detection of postoperative infectious complications. Although changes in albumins are observed early after surgery, this parameter is relatively unspecific.

3D Printing in Liver Surgery: A Systematic Review.

BACKGROUND: Rapid growth of three-dimensional (3D) printing in recent years has led to new applications of this technology across all medical fields. This review article presents a broad range of examples on how 3D printing is facilitating liver surgery, including models for preoperative planning, education, and simulation. MATERIALS AND METHODS: We have performed an extensive search of the medical databases Ovid/MEDLINE and PubMed/EMBASE and screened articles fitting the scope of review, following previously established exclusion criteria. Articles deemed suitable were analyzed and data on the 3D-printed models-including both technical properties and desirable application-and their impact on clinical proceedings were extracted. RESULTS: Fourteen articles, presenting unique utilizations of 3D models, were found suitable for data analysis. A great majority of articles (93%) discussed models used for preoperative planning and intraoperative guidance. PolyJet was the most common (43%) and, at the same time, most expensive 3D printing technology used in the development process. Many authors of reviewed articles reported that models were accurate (71%) and allowed them to understand patient's complex anatomy and its spatial relationships. CONCLUSIONS: Although the technology is still in its early stages, presented models are considered useful in preoperative planning and patient and student education. There are multiple factors limiting the use of 3D printing in everyday healthcare, the most important being high costs and the time-consuming process of development. Promising early results need to be verified in larger randomized trials, which will provide more statistically significant results.

An Efficient Deep Neural Network to Classify Large 3D Images With Small Objects.

3D imaging enables accurate diagnosis by providing spatial information about organ anatomy. However, using 3D images to train AI models is computationally challenging because they consist of 10x or 100x more pixels than their 2D counterparts. To be trained with high-resolution 3D images, convolutional neural networks resort to downsampling them or projecting them to 2D. We propose an effective alternative, a neural network that enables efficient classification of full-resolution 3D medical images. Compared to off-the-shelf convolutional neural networks, our network, 3D Globally-Aware Multiple Instance Classifier (3D-GMIC), uses 77.98%-90.05% less GPU memory and 91.23%-96.02% less computation. While it is trained only with image-level labels, without segmentation labels, it explains its predictions by providing pixel-level saliency maps. On a dataset collected at NYU Langone Health, including 85,526 patients with full-field 2D mammography (FFDM), synthetic 2D mammography, and 3D mammography, 3D-GMIC achieves an AUC of 0.831 (95% CI: 0.769-0.887) in classifying breasts with malignant findings using 3D mammography. This is comparable to the performance of GMIC on FFDM (0.816, 95% CI: 0.737-0.878) and synthetic 2D (0.826, 95% CI: 0.754-0.884), which demonstrates that 3D-GMIC successfully classified large 3D images despite focusing computation on a smaller percentage of its input compared to GMIC. Therefore, 3D-GMIC identifies and utilizes extremely small regions of interest from 3D images consisting of hundreds of millions of pixels, dramatically reducing associated computational challenges. 3D-GMIC generalizes well to BCS-DBT, an external dataset from Duke University Hospital, achieving an AUC of 0.848 (95% CI: 0.798-0.896).

Application of HoloLens-based augmented reality and three-dimensional printed anatomical tooth reference models in dental education.

Tooth anatomy is fundamental knowledge used in everyday dental practice to reconstruct the occlusal surface during cavity fillings. The main objective of this project was to evaluate the suitability of two types of anatomical tooth reference models used to support reconstruction of the occlusal anatomy of the teeth: (1) a three-dimensional (3D)-printed model and (2) a model displayed in augmented reality (AR) using Microsoft HoloLens. The secondary objective was to evaluate three aspects impacting the outcome: clinical experience, comfort of work, and other variables. The tertiary objective was to evaluate the usefulness of AR in dental education. Anatomical models of crowns of three different molars were made using cone beam computed tomography image segmentation, printed with a stereolithographic 3D-printer, and then displayed in the HoloLens. Each participant reconstructed the occlusal anatomy of three teeth. One without any reference materials and two with an anatomical reference model, either 3D-printed or holographic. The reconstruction work was followed by the completion of an evaluation questionnaire. The maximum Hausdorff distances (Hmax) between the superimposed images of the specimens after the procedures and the anatomical models were then calculated. The results showed that the most accurate but slowest reconstruction was achieved with the use of 3D-printed reference models and that the results were not affected by other aspects considered. For this method, the Hmax was observed to be 630 µm (p = 0.004). It was concluded that while AR models can be helpful in dental anatomy education, they are not suitable replacements for physical models.

Enhancing the reliability and accuracy of AI-enabled diagnosis via complementarity-driven deferral to clinicians.

Predictive artificial intelligence (AI) systems based on deep learning have been shown to achieve expert-level identification of diseases in multiple medical imaging settings, but can make errors in cases accurately diagnosed by clinicians and vice versa. We developed Complementarity-Driven Deferral to Clinical Workflow (CoDoC), a system that can learn to decide between the opinion of a predictive AI model and a clinical workflow. CoDoC enhances accuracy relative to clinician-only or AI-only baselines in clinical workflows that screen for breast cancer or tuberculosis (TB). For breast cancer screening, compared to double reading with arbitration in a screening program in the UK, CoDoC reduced false positives by 25% at the same false-negative rate, while achieving a 66% reduction in clinician workload. For TB triaging, compared to standalone AI and clinical workflows, CoDoC achieved a 5-15% reduction in false positives at the same false-negative rate for three of five commercially available predictive AI systems. To facilitate the deployment of CoDoC in novel futuristic clinical settings, we present results showing that CoDoC's performance gains are sustained across several axes of variation (imaging modality, clinical setting and predictive AI system) and discuss the limitations of our evaluation and where further validation would be needed. We provide an open-source implementation to encourage further research and application.

Improving Information Extraction from Pathology Reports using Named Entity Recognition.

Pathology reports are considered the gold standard in medical research due to their comprehensive and accurate diagnostic information. Natural language processing (NLP) techniques have been developed to automate information extraction from pathology reports. However, existing studies suffer from two significant limitations. First, they typically frame their tasks as report classification, which restricts the granularity of extracted information. Second, they often fail to generalize to unseen reports due to variations in language, negation, and human error. To overcome these challenges, we propose a BERT (bidirectional encoder representations from transformers) named entity recognition (NER) system to extract key diagnostic elements from pathology reports. We also introduce four data augmentation methods to improve the robustness of our model. Trained and evaluated on 1438 annotated breast pathology reports, acquired from a large medical center in the United States, our BERT model trained with data augmentation achieves an entity F1-score of 0.916 on an internal test set, surpassing the BERT baseline (0.843). We further assessed the model's generalizability using an external validation dataset from the United Arab Emirates, where our model maintained satisfactory performance (F1-score 0.860). Our findings demonstrate that our NER systems can effectively extract fine-grained information from widely diverse medical reports, offering the potential for large-scale information extraction in a wide range of medical and AI research. We publish our code at https://github.com/nyukat/pathology_extraction.

A Competition, Benchmark, Code, and Data for Using Artificial Intelligence to Detect Lesions in Digital Breast Tomosynthesis.

Importance: An accurate and robust artificial intelligence (AI) algorithm for detecting cancer in digital breast tomosynthesis (DBT) could significantly improve detection accuracy and reduce health care costs worldwide. Objectives: To make training and evaluation data for the development of AI algorithms for DBT analysis available, to develop well-defined benchmarks, and to create publicly available code for existing methods. Design, Setting, and Participants: This diagnostic study is based on a multi-institutional international grand challenge in which research teams developed algorithms to detect lesions in DBT. A data set of 22 032 reconstructed DBT volumes was made available to research teams. Phase 1, in which teams were provided 700 scans from the training set, 120 from the validation set, and 180 from the test set, took place from December 2020 to January 2021, and phase 2, in which teams were given the full data set, took place from May to July 2021. Main Outcomes and Measures: The overall performance was evaluated by mean sensitivity for biopsied lesions using only DBT volumes with biopsied lesions; ties were broken by including all DBT volumes. Results: A total of 8 teams participated in the challenge. The team with the highest mean sensitivity for biopsied lesions was the NYU B-Team, with 0.957 (95% CI, 0.924-0.984), and the second-place team, ZeDuS, had a mean sensitivity of 0.926 (95% CI, 0.881-0.964). When the results were aggregated, the mean sensitivity for all submitted algorithms was 0.879; for only those who participated in phase 2, it was 0.926. Conclusions and Relevance: In this diagnostic study, an international competition produced algorithms with high sensitivity for using AI to detect lesions on DBT images. A standardized performance benchmark for the detection task using publicly available clinical imaging data was released, with detailed descriptions and analyses of submitted algorithms accompanied by a public release of their predictions and code for selected methods. These resources will serve as a foundation for future research on computer-assisted diagnosis methods for DBT, significantly lowering the barrier of entry for new researchers.

Radiological Features for Frailty Assessment in Patients Requiring Emergency Laparotomy.

INTRODUCTION: As the number of elderly patients requiring surgical intervention rises, it is believed that frailty syndrome has a greater impact on perioperative course than on chronological age. The aim of this study was to evaluate the efficacy of various imaging features for frailty assessment in patients undergoing emergency laparotomy. METHODS: The study included all patients that qualified for emergency surgery with preoperative CT scans between 2016 and 2020 in the Second Department of General Surgery. Multiple trauma patients were excluded from the analysis. The modified frailty index and brief geriatric assessment were used in the analysis. CT images were reviewed for the assessment of osteopenia, sarcopenia, sarcopenic obesity, renal volume and abdominal aorta calcification rate. RESULTS: A total of 261 patients were included in the analysis. Multivariate logistic regression identified every next ASA class (OR: 4.161, 95%CI: 1.672-10.355, p = 0.002), intraoperative adverse events (OR: 12.397, 95%CI: 2.166-70.969, p = 0.005) and osteopenia (OR: 4.213, 95%CI: 1.235-14.367, p = 0.022) as a risk factor for 30-day mortality. Our study showed that every next ASA class (OR: 1.952, 95%Cl: 1.171-3.256, p = 0.010) and every point of the BGA score (OR: 1.496, 95%Cl: 1.110-2.016, p = 0.008) are risk factors for major complications. CONCLUSIONS: Osteopenia was the best parameter for perioperative mortality risk stratification in patients undergoing emergency surgical intervention. Sarcopenia (measured as psoas muscle area), sarcopenic obesity, aortic calcifications and mean kidney volume do not predict poor outcomes in those patients. None of the radiological markers appeared to be useful for the prediction of perioperative morbidity.

Development and Validation of a Virtual Reality Simulator for Robot-Assisted Minimally Invasive Liver Surgery Training.

The value of kinematic data for skill assessment is being investigated. This is the first virtual reality simulator developed for liver surgery. This simulator was coded in C++ using PhysX and FleX with a novel cutting algorithm and used a patient data-derived model and two instruments functioning as ultrasonic shears. The simulator was evaluated by nine expert surgeons and nine surgical novices. Each participant performed a simulated metastasectomy after training. Kinematic data were collected for the instrument position. Each participant completed a survey. The expert participants had a mean age of 47 years and 9/9 were certified in surgery. Novices had a mean age of 30 years and 0/9 were certified surgeons. The mean path length (novice 0.76 ± 0.20 m vs. expert 0.46 ± 0.16 m, p = 0.008), movements (138 ± 45 vs. 84 ± 32, p = 0.043) and time (174 ± 44 s vs. 102 ± 42 s, p = 0.004) were significantly different for the two participant groups. There were no significant differences in activating the instrument (107 ± 25 vs. 109 ± 53). Participants considered the simulator realistic (6.5/7) (face validity), appropriate for education (5/7) (content validity) with an effective interface (6/7), consistent motion (5/7) and realistic soft tissue behavior (5/7). This study showed that the simulator differentiates between experts and novices. Simulation may be an effective way to obtain kinematic data.

Improving breast cancer diagnostics with deep learning for MRI.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has a high sensitivity in detecting breast cancer but often leads to unnecessary biopsies and patient workup. We used a deep learning (DL) system to improve the overall accuracy of breast cancer diagnosis and personalize management of patients undergoing DCE-MRI. On the internal test set (n = 3936 exams), our system achieved an area under the receiver operating characteristic curve (AUROC) of 0.92 (95% CI: 0.92 to 0.93). In a retrospective reader study, there was no statistically significant difference (P = 0.19) between five board-certified breast radiologists and the DL system (mean ΔAUROC, +0.04 in favor of the DL system). Radiologists' performance improved when their predictions were averaged with DL's predictions [mean ΔAUPRC (area under the precision-recall curve), +0.07]. We demonstrated the generalizability of the DL system using multiple datasets from Poland and the United States. An additional reader study on a Polish dataset showed that the DL system was as robust to distribution shift as radiologists. In subgroup analysis, we observed consistent results across different cancer subtypes and patient demographics. Using decision curve analysis, we showed that the DL system can reduce unnecessary biopsies in the range of clinically relevant risk thresholds. This would lead to avoiding biopsies yielding benign results in up to 20% of all patients with BI-RADS category 4 lesions. Last, we performed an error analysis, investigating situations where DL predictions were mostly incorrect. This exploratory work creates a foundation for deployment and prospective analysis of DL-based models for breast MRI.

MarkIt: A Collaborative Artificial Intelligence Annotation Platform Leveraging Blockchain For Medical Imaging Research.

Current research on medical image processing relies heavily on the amount and quality of input data. Specifically, supervised machine learning methods require well-annotated datasets. A lack of annotation tools limits the potential to achieve high-volume processing and scaled systems with a proper reward mechanism. We developed MarkIt, a web-based tool, for collaborative annotation of medical imaging data with artificial intelligence and blockchain technologies. Our platform handles both Digital Imaging and Communications in Medicine (DICOM) and non-DICOM images, and allows users to annotate them for classification and object detection tasks in an efficient manner. MarkIt can accelerate the annotation process and keep track of user activities to calculate a fair reward. A proof-of-concept experiment was conducted with three fellowship-trained radiologists, each of whom annotated 1,000 chest X-ray studies for multi-label classification. We calculated the inter-rater agreement and estimated the value of the dataset to distribute the reward for annotators using a crypto currency. We hypothesize that MarkIt allows the typically arduous annotation task to become more efficient. In addition, MarkIt can serve as a platform to evaluate the value of data and trade the annotation results in a more scalable manner in the future. The platform is publicly available for testing on https://markit.mgh.harvard.edu.

An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department.

During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745-0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

Quality of Life After Bariatric Surgery-a Systematic Review with Bayesian Network Meta-analysis.

OBJECTIVE: Comprehensive analysis and comparison of HRQoL following different bariatric interventions through systematic review with network meta-analysis. BACKGROUND: Different types of bariatric surgeries have been developed throughout the years. Apart from weight loss and comorbidities remission, improvement of health-related quality of life (HRQoL) is an important outcome of metabolic surgery. METHODS: MEDLINE, EMBASE, and Scopus databases have been searched up to April 2020. Inclusion criteria to the analysis were (1) study with at least 2 arms comparing bariatric surgeries; (2) reporting of HRQoL with a validated tool; (3) follow-up period of 1, 2, 3, or 5 years. Network meta-analysis was conducted using Bayesian statistics. The primary outcome was HRQoL. RESULTS: Forty-seven studies were included in the analysis involving 26,629 patients and 11 different surgeries such as sleeve gastrectomy (LSG), gastric bypass (LRYGB), one anastomosis gastric bypass (OAGB), and other. At 1 year, there was significant difference in HRQoL in favor of LSG, LRYGB, and OAG compared with lifestyle intervention (SMD: 0.44; 95% CrI 0.2 to 0.68 for LSG, SMD: 0.56; 95% CrI 0.31 to 0.8 for LRYGB; and SMD: 0.43; 95% CrI 0.06 to 0.8 for OAGB). At 5 years, LSG, LRYGB, and OAGB showed better HRQoL compared to control (SMD: 0.92; 95% CrI 0.58 to 1.26, SMD: 1.27; 95% CrI 0.94 to 1.61, and SMD: 1.01; 95% CrI 0.63 to 1.4, respectively). CONCLUSIONS: LSG and LRYGB may lead to better HRQoL across most follow-up time points. Long-term analysis shows that bariatric intervention results in better HRQoL than non-surgical interventions.