QUAIDE - Quality assessment of AI preclinical studies in diagnostic endoscopy.

Artificial intelligence (AI) holds significant potential for enhancing quality of gastrointestinal (GI) endoscopy, but the adoption of AI in clinical practice is hampered by the lack of rigorous standardisation and development methodology ensuring generalisability. The aim of the Quality Assessment of pre-clinical AI studies in Diagnostic Endoscopy (QUAIDE) Explanation and Checklist was to develop recommendations for standardised design and reporting of preclinical AI studies in GI endoscopy.The recommendations were developed based on a formal consensus approach with an international multidisciplinary panel of 32 experts among endoscopists and computer scientists. The Delphi methodology was employed to achieve consensus on statements, with a predetermined threshold of 80% agreement. A maximum three rounds of voting were permitted.Consensus was reached on 18 key recommendations, covering 6 key domains: data acquisition and annotation (6 statements), outcome reporting (3 statements), experimental setup and algorithm architecture (4 statements) and result presentation and interpretation (5 statements). QUAIDE provides recommendations on how to properly design (1. Methods, statements 1-14), present results (2. Results, statements 15-16) and integrate and interpret the obtained results (3. Discussion, statements 17-18).The QUAIDE framework offers practical guidance for authors, readers, editors and reviewers involved in AI preclinical studies in GI endoscopy, aiming at improving design and reporting, thereby promoting research standardisation and accelerating the translation of AI innovations into clinical practice.

Excess Mortality in Kidney and Kidney-Pancreas Transplant Recipients in the COVID-19 Pandemic in Portugal-A Cohort Study.

The COVID-19 pandemic increased morbidity and mortality worldwide, particularly in the Kidney and Kidney-Pancreas Transplant Recipient (KTR/KPTR) population. Aiming at assessing the absolute and relative excess mortality (EM) in a Portuguese KTR/KPTR cohort, we conducted a retrospective observational study of two KTR/KPTRs cohorts: cohort 1 (P1; n = 2,179) between September/2012 and March/2020; cohort 2 (P2; n = 2067) between March/2020, and August/2022. A correlation between relative and absolute EM and age, sex, time from transplantation and cause of death was explored. A total of 145 and 84 deaths by all causes were observed in P1 and P2, respectively. The absolute EM in P2 versus P1 was 19.2 deaths (observed/expected mortality ratio 1.30, p = 0.006), and the relative EM was 1.47/1,000 person-months (95% CI 1.11-1.93, p = 0.006). Compared to the same period in the general population, the standardized mortality rate by age in P2 was 3.86 (95% CI 2.40-5.31), with a peak at 9.00 (95% CI 4.84-13.16) in P2C. The higher EM identified in this population was associated, mainly, with COVID-19 infection, with much higher values during the second seasonal COVID-19 peak when compared to the general population, despite generalized vaccination. These highlight the need for further preventive measures and improved therapies in these patients.

Standalone performance of artificial intelligence for upper GI neoplasia: a meta-analysis.

OBJECTIVE: Artificial intelligence (AI) may reduce underdiagnosed or overlooked upper GI (UGI) neoplastic and preneoplastic conditions, due to subtle appearance and low disease prevalence. Only disease-specific AI performances have been reported, generating uncertainty on its clinical value. DESIGN: We searched PubMed, Embase and Scopus until July 2020, for studies on the diagnostic performance of AI in detection and characterisation of UGI lesions. Primary outcomes were pooled diagnostic accuracy, sensitivity and specificity of AI. Secondary outcomes were pooled positive (PPV) and negative (NPV) predictive values. We calculated pooled proportion rates (%), designed summary receiving operating characteristic curves with respective area under the curves (AUCs) and performed metaregression and sensitivity analysis. RESULTS: Overall, 19 studies on detection of oesophageal squamous cell neoplasia (ESCN) or Barrett's esophagus-related neoplasia (BERN) or gastric adenocarcinoma (GCA) were included with 218, 445, 453 patients and 7976, 2340, 13 562 images, respectively. AI-sensitivity/specificity/PPV/NPV/positive likelihood ratio/negative likelihood ratio for UGI neoplasia detection were 90% (CI 85% to 94%)/89% (CI 85% to 92%)/87% (CI 83% to 91%)/91% (CI 87% to 94%)/8.2 (CI 5.7 to 11.7)/0.111 (CI 0.071 to 0.175), respectively, with an overall AUC of 0.95 (CI 0.93 to 0.97). No difference in AI performance across ESCN, BERN and GCA was found, AUC being 0.94 (CI 0.52 to 0.99), 0.96 (CI 0.95 to 0.98), 0.93 (CI 0.83 to 0.99), respectively. Overall, study quality was low, with high risk of selection bias. No significant publication bias was found. CONCLUSION: We found a high overall AI accuracy for the diagnosis of any neoplastic lesion of the UGI tract that was independent of the underlying condition. This may be expected to substantially reduce the miss rate of precancerous lesions and early cancer when implemented in clinical practice.

A multicenter prospective study of the real-time use of narrow-band imaging in the diagnosis of premalignant gastric conditions and lesions.

BACKGROUND AND AIM: Some studies suggest that narrow-band imaging (NBI) can be more accurate at diagnosing gastric intestinal metaplasia and dysplasia than white-light endoscopy (WLE) alone. We aimed to assess the real-time diagnostic validity of high resolution endoscopy with and without NBI in the diagnosis of gastric premalignant conditions and to derive a classification for endoscopic grading of gastric intestinal metaplasia (EGGIM). METHODS: A multicenter prospective study (five centers: Portugal, Italy, Romania, UK, USA) was performed involving the systematic use of high resolution gastroscopes with image registry with and without NBI in a centralized informatics platform (available online). All users used the same NBI classification. Histologic result was considered the diagnostic gold standard. RESULTS: A total of 238 patients and 1123 endoscopic biopsies were included. NBI globally increased diagnostic accuracy by 11 percentage points (NBI 94 % vs. WLE 83 %; P < 0.001) with no difference in the identification of Helicobacter pylori gastritis (73 % vs. 74 %). NBI increased sensitivity for the diagnosis of intestinal metaplasia significantly (87 % vs. 53 %; P < 0.001) and for the diagnosis of dysplasia (92 % vs. 74 %). The added benefit of NBI in terms of diagnostic accuracy was greater in OLGIM III/IV than in OLGIM I/II (25 percentage points vs. 15 percentage points, respectively; P < 0.001). The area under the curve (AUC) of the receiver operating characteristic (ROC) curve for EGGIM in the identification of extensive metaplasia was 0.98. CONCLUSIONS: In a real-time scenario, NBI demonstrates a high concordance with gastric histology, superior to WLE. Diagnostic accuracy higher than 90 % suggests that routine use of NBI allows targeted instead of random biopsy samples. EGGIM also permits immediate grading of intestinal metaplasia without biopsies and merits further investigation.

Detection and separation of overlapping cells based on contour concavity for Leishmania images.

Life scientists often must count cells in microscopy images, which is a tedious and time-consuming task. Automatic approaches present a solution to this problem. Several procedures have been devised for this task, but the majority suffer from performance degradation in the case of cell overlap. In this article, we propose a method to determine the positions of macrophages and parasites in fluorescence images of Leishmania-infected macrophages. The proposed strategy is primarily based on blob detection, clustering, and separation using concave regions of the cells' contours. In comparison with the approaches of Nogueira (Master's thesis, Department of University of Porto Computer Science, 2011) and Leal et al. (Proceedings of the 9th international conference on Image Analysis and Recognition, Vol. II, ICIAR'12. Berlin, Heidelberg: Springer-Verlag; 2012. pp. 432-439), which also addressed this type of image, we conclude that the proposed methodology achieves better performance in the automatic annotation of Leishmania infections.

LNDb v4: pulmonary nodule annotation from medical reports.

Given the high prevalence of lung cancer, an accurate diagnosis is crucial. In the diagnosis process, radiologists play an important role by examining numerous radiology exams to identify different types of nodules. To aid the clinicians' analytical efforts, computer-aided diagnosis can streamline the process of identifying pulmonary nodules. For this purpose, medical reports can serve as valuable sources for automatically retrieving image annotations. Our study focused on converting medical reports into nodule annotations, matching textual information with manually annotated data from the Lung Nodule Database (LNDb)-a comprehensive repository of lung scans and nodule annotations. As a result of this study, we have released a tabular data file containing information from 292 medical reports in the LNDb, along with files detailing nodule characteristics and corresponding matches to the manually annotated data. The objective is to enable further research studies in lung cancer by bridging the gap between existing reports and additional manual annotations that may be collected, thereby fostering discussions about the advantages and disadvantages between these two data types.

Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation.

The integration of artificial intelligence (AI) in medical diagnostics represents a significant advancement in managing upper gastrointestinal (GI) cancer, which is a major cause of global cancer mortality. Specifically for gastric cancer (GC), chronic inflammation causes changes in the mucosa such as atrophy, intestinal metaplasia (IM), dysplasia, and ultimately cancer. Early detection through endoscopic regular surveillance is essential for better outcomes. Foundation models (FMs), which are machine or deep learning models trained on diverse data and applicable to broad use cases, offer a promising solution to enhance the accuracy of endoscopy and its subsequent pathology image analysis. This review explores the recent advancements, applications, and challenges associated with FMs in endoscopy and pathology imaging. We started by elucidating the core principles and architectures underlying these models, including their training methodologies and the pivotal role of large-scale data in developing their predictive capabilities. Moreover, this work discusses emerging trends and future research directions, emphasizing the integration of multimodal data, the development of more robust and equitable models, and the potential for real-time diagnostic support. This review aims to provide a roadmap for researchers and practitioners in navigating the complexities of incorporating FMs into clinical practice for the prevention/management of GC cases, thereby improving patient outcomes.

Endoscopic assessment and grading of Barrett's esophagus using magnification endoscopy and narrow band imaging: impact of structured learning and experience on the accuracy of the Amsterdam classification system.

OBJECTIVE: Several classification systems have been launched to characterize Barrett's esophagus (BE) mucosa using magnification endoscopy with narrow band imaging (ME-NBI). The good accuracy and interobserver agreement described in the early reports were not reproduced subsequently. Recently, we reported somewhat higher accuracy of the classification developed by the Amsterdam group. The critical question then formulated was whether a structured learning program and the level of experience would affect the clinical usefulness of this classification. MATERIAL & METHODS: Two hundred and nine videos were prospectively captured from patients with BE using ME-NBI. From these, 70 were randomly selected and evaluated by six endoscopists with different levels of expertise, using a dedicated software application. First, an educational set was studied. Thereafter, the 70 test videos were evaluated. After classification of each video, the respective histological feedback was automatically given. RESULTS: Within the learning process, there was a decrease in the time needed for evaluation and an increase in the certainty of prediction. The accuracy did not increase with the learning process. The sensitivity for detection of intestinal metaplasia ranged between 39% and 57%, and for neoplasia between 62% and 90%, irrespective of assessor's expertise. The kappa coefficient for the interobserver agreement ranged from 0.25 to 0.30 for intestinal metaplasia, and from 0.39 to 0.48 for neoplasia. CONCLUSION: Using a dedicated learning program, the ME-NBI Amsterdam classification system is suboptimal in terms of accuracy and inter- and intraobserver agreements. These results reiterate the questionable utility of corresponding classification system in clinical routine practice.

Assisted probe guidance in cardiac ultrasound: A review.

Echocardiography is the most frequently used imaging modality in cardiology. However, its acquisition is affected by inter-observer variability and largely dependent on the operator's experience. In this context, artificial intelligence techniques could reduce these variabilities and provide a user independent system. In recent years, machine learning (ML) algorithms have been used in echocardiography to automate echocardiographic acquisition. This review focuses on the state-of-the-art studies that use ML to automate tasks regarding the acquisition of echocardiograms, including quality assessment (QA), recognition of cardiac views and assisted probe guidance during the scanning process. The results indicate that performance of automated acquisition was overall good, but most studies lack variability in their datasets. From our comprehensive review, we believe automated acquisition has the potential not only to improve accuracy of diagnosis, but also help novice operators build expertise and facilitate point of care healthcare in medically underserved areas.

Markov-Based Neural Networks for Heart Sound Segmentation: Using Domain Knowledge in a Principled Way.

This work considers the problem of segmenting heart sounds into their fundamental components. We unify statistical and data-driven solutions by introducing Markov-based Neural Networks (MNNs), a hybrid end-to-end framework that exploits Markov models as statistical inductive biases for an Artificial Neural Network (ANN) discriminator. We show that an MNN leveraging a simple one-dimensional Convolutional ANN significantly outperforms two recent purely data-driven solutions for this task in two publicly available datasets: PhysioNet 2016 (Sensitivity: 0.947 ±0.02; Positive Predictive Value : 0.937 ±0.025) and the CirCor DigiScope 2022 (Sensitivity: 0.950 ±0.008; Positive Predictive Value: 0.943 ±0.012). We also propose a novel gradient-based unsupervised learning algorithm that effectively makes the MNN adaptive to unseen datum sampled from unknown distributions. We perform a cross dataset analysis and show that an MNN pre-trained in the CirCor DigiScope 2022 can benefit from an average improvement of 3.90% Positive Predictive Value on unseen observations from the PhysioNet 2016 dataset using this method.

Medical Challenges of a Common Variable Immunodeficiency With a TNFRSF13B Gene Mutation in a Simultaneous Kidney and Pancreas Transplant Recipient.

Common variable immune deficiency (CVID) is a primary immunodeficiency disorder, with hypogammaglobulinemia and increased susceptibility to recurrent infections, autoimmune disorders, granulomatous diseases and malignancy. Among the solid organ transplant (SOT) recipient population, those with primary immunodeficiency disorders under chronic immunosuppression therapy can theoretically be at higher risk of atypical infections, autoimmune complications and disease recurrence with suboptimal long term graft survival, but literature is scarce. Here, we report a 27-year-old female with type 1 diabetes mellitus, complicated with nephropathy that progressed to end-stage renal disease (ESRD), who had a history of a chronic inflammatory response dysregulation, with chronic monoarthritis, persistent elevation of inflammation markers, recurrent infections, low immunoglobulin G (IgG) and A (IgA) serum levels, a slightly decreased population of memory B cells at flow cytometric immunophenotyping, and a confirmed pathological heterozygous mutation in the tumor necrosis factor receptor superfamily 13B (TNFRSF13B), with a suspected diagnosis of CVID. Whilst on hemodialysis, she received a simultaneous kidney and pancreas transplant from a standard criteria donor (SCD), and our induction and maintenance immunosuppression protocol and prophylaxis regimen allowed for a successful transplant with immediate pancreatic function, with no evidence of renal graft rejection upon biopsy in the early post-transplant period, and no novel episodes of serious infectious complications were recorded during a follow-up period of six months.

Accidental Diagnosis of Isolated Persistent Left Superior Vena Cava After an Elective Central Venous Access Procedure for Chronic Hemodialysis: Clinical Implications and Precautions From a Case Report.

Persistent left superior vena cava (PLSVC) is the most frequent thoracic venous anatomical variant in the general population. Isolated PLSVC, without formation of the right superior vena cava, is described in 10% of cases of PLSVC only. While it can be associated with congenital heart disease, arrhythmias, and premature death, adult patients with PLSVC are mostly asymptomatic, and the diagnosis is usually accidental. We present the case of a 72-year-old male with end-stage renal disease who was started on urgent hemodialysis through a temporary non-tunneled femoral central venous catheter (CVC) in the SLED (slow low-efficiency dialysis) modality and later remained dependent on hemodialysis. At this stage, placement of a tunneled CVC in the right internal jugular vein was necessary and fluoroscopy guidance was not available. There were no complications during the procedure, but postoperative conventional chest radiography revealed an inadequate positioning of the CVC tip in the left hemithorax, crossing the midline. Subsequently, the diagnosis of PLSVC was obtained by performing a thoracic angio-CT scan, confirming CVC tip positioning inside the PLSVC, and also excluded the presence of cardiac defects or additional anatomical variations of the great vessels of the thorax. Early evaluation for the creation of autologous vascular access was started under our care, and there were no mechanical or other complications associated with hemodialysis sessions during early follow-up after discharge.

On the Impact of Synchronous Electrocardiogram Signals for Heart Sounds Segmentation.

In this paper we study the heart sound segmentation problem using Deep Neural Networks. The impact of available electrocardiogram (ECG) signals in addition to phonocardiogram (PCG) signals is evaluated. To incorporate ECG, two different models considered, which are built upon a 1D U-net - an early fusion one that fuses ECG in an early processing stage, and a late fusion one that averages the probabilities obtained by two networks applied independently on PCG and ECG data. Results show that, in contrast with traditional uses of ECG for PCG gating, early fusion of PCG and ECG information can provide more robust heart sound segmentation. As a proof of concept, we use the publicly available PhysioNet dataset. Validation results provide, on average, a sensitivity of 97.2%, 94.5%, and 95.6% and a Positive Predictive Value of 97.5%, 96.2%, and 96.1% for Early-fusion, Late-fusion, and unimodal (PCG only) models, respectively, showing the advantages of combining both signals at early stages to segment heart sounds.Clinical relevance- Cardiac auscultation is the first line of screening for cardiovascular diseases. Its low cost and simplicity are especially suitable for screening large populations in underprivileged countries. The proposed analysis and algorithm show the potential of effectively including electrocardiogram information to improve heart sound segmentation performance, thus enhancing the capacity of extracting useful information from heart sound recordings.

D313Y variant in two related end-stage renal disease patients - Pathogenic or not yet?

Fabry disease is a multisystem lysosomal storage disorder caused by mutations in the GLA gene that result in a deficient or absent activity of alpha-galactosidase A. There is a wide spectrum of GLA gene variants, some of which are described as non-pathogenic. The clinical importance of the D313Y variant is still under debate, although in recent years it has been considered as a variant of unknown significance or a benign variant. Despite this prevailing notion, there are multiple case reports of patients with D313Y variant that presented signs and symptoms consistent with FD without any other etiological explanation. In this article, we present two family members with an important renal phenotype and other typical manifestations of FD (white matter lesions and left ventricular hypertrophy) that only had the D313Y variant. These cases suggest that this variant of unknown significance may contribute to the development of common features of FD and should not be undervalued.

Diagnostic Performance of Deep Learning Models for Gastric Intestinal Metaplasia Detection in Narrow-band Images.

Gastric Intestinal Metaplasia (GIM) is one of the precancerous conditions in the gastric carcinogenesis cascade and its optical diagnosis during endoscopic screening is challenging even for seasoned endoscopists. Several solutions leveraging pre-trained deep neural networks (DNNs) have been recently proposed in order to assist human diagnosis. In this paper, we present a comparative study of these architectures in a new dataset containing GIM and non-GIM Narrow-band imaging still frames. We find that the surveyed DNNs perform remarkably well on average, but still measure sizeable inter-fold variability during cross-validation. An additional ad-hoc analysis suggests that these baseline architectures may not perform equally well at all scales when diagnosing GIM.Clinical relevance- Enhanching a clinician's ability to detect and localize intestinal metaplasia can be a crucial tool for gastric cancer management policies.

Automatic Contrast Generation from Contrastless Computed Tomography.

The use of contrast-enhanced computed tomography (CTCA) for detection of coronary artery disease (CAD) exposes patients to the risks of iodine contrast-agents and excessive radiation, increases scanning time and healthcare costs. Deep learning generative models have the potential to artificially create a pseudo-enhanced image from non-contrast computed tomography (CT) scans.In this work, two specific models of generative adversarial networks (GANs) - the Pix2Pix-GAN and the Cycle-GAN - were tested with paired non-contrasted CT and CTCA scans from a private and public dataset. Furthermore, an exploratory analysis of the trade-off of using 2D and 3D inputs and architectures was performed. Using only the Structural Similarity Index Measure (SSIM) and the Peak Signal-to-Noise Ratio (PSNR), it could be concluded that the Pix2Pix-GAN using 2D data reached better results with 0.492 SSIM and 16.375 dB PSNR. However, visual analysis of the output shows significant blur in the generated images, which is not the case for the Cycle-GAN models. This behavior can be captured by the evaluation of the Fréchet Inception Distance (FID), that represents a fundamental performance metric that is usually not considered by related works in the literature.Clinical relevance- Contrast-enhanced computed tomography is the first line imaging modality to detect CAD resulting in unnecessary exposition to the risk of iodine contrast and radiation in particularly in young patients with no disease. This algorithm has the potential of being translated into clinical practice as a screening method for CAD in asymptomatic subjects or quick rule-out method of CAD in the acute setting or centres with no CTCA service. This strategy can eventually represent a reduction in the need for CTCA reducing its burden and associated costs.

A New Perspective on Supporting Vulnerable Road Users' Safety, Security and Comfort through Personalized Route Planning.

Due to an increase in population, urban centers are currently seeing an increase in traffic, resulting in negative consequences such as pollution and congestion. Efforts have been made to promote a modal shift towards the use of more sustainable means of transport, such as walking and cycling, but several deterrents influence the citizens' perceptions of safety, security and comfort, discouraging their choice of active modes of transport. This study focuses on the importance of providing meaningful information to vulnerable road users (VRUs) to support their perceptions and objectives while moving within urban spaces through a novel concept of route planning. A broad survey of the needs and concerns of VRUs through interviews, focus groups and questionnaires, applied to the Portuguese population of the Metropolitan Area of Porto, led to the development of a new concept of route planners that show personalized routes according to the individual perceptions of each user. This concept is materialized in a route planner prototype that has been extensively tested by potential users. Subjective evaluation and feedback showed the usefulness of the concept and added value to a familiar product, leading to a satisfying experience for participants. This study shows that there is an opportunity to improve these tools to provide a higher degree of power and customization to users on route planning, which includes addressing mobility restrictions and personal perceptions of safety, security and comfort. The ultimate goal of this new approach is to persuade citizens to switch to more sustainable means of transport.

An Unexpected Catastrophe-Renal Artery Thrombosis in a Living Donor: A Case Report.

BACKGROUND: Renal artery thrombosis is a devastating complication if not detected early. Cardioembolic disease or surgical and technical complications are frequent causes of renal artery thrombosis. There are some reports of renal artery thrombosis in a renal allograft, but to our knowledge, this is the first case of renal artery thrombosis reported in a kidney donor.

Beyond Heart Murmur Detection: Automatic Murmur Grading From Phonocardiogram.

OBJECTIVE: Murmurs are abnormal heart sounds, identified by experts through cardiac auscultation. The murmur grade, a quantitative measure of the murmur intensity, is strongly correlated with the patient's clinical condition. This work aims to estimate each patient's murmur grade (i.e., absent, soft, loud) from multiple auscultation location phonocardiograms (PCGs) of a large population of pediatric patients from a low-resource rural area. METHODS: The Mel spectrogram representation of each PCG recording is given to an ensemble of 15 convolutional residual neural networks with channel-wise attention mechanisms to classify each PCG recording. The final murmur grade for each patient is derived based on the proposed decision rule and considering all estimated labels for available recordings. The proposed method is cross-validated on a dataset consisting of 3456 PCG recordings from 1007 patients using a stratified ten-fold cross-validation. Additionally, the method was tested on a hidden test set comprised of 1538 PCG recordings from 442 patients. RESULTS: The overall cross-validation performances for patient-level murmur gradings are 86.3% and 81.6% in terms of the unweighted average of sensitivities and F1-scores, respectively. The sensitivities (and F1-scores) for absent, soft, and loud murmurs are 90.7% (93.6%), 75.8% (66.8%), and 92.3% (84.2%), respectively. On the test set, the algorithm achieves an unweighted average of sensitivities of 80.4% and an F1-score of 75.8%. CONCLUSIONS: This study provides a potential approach for algorithmic pre-screening in low-resource settings with relatively high expert screening costs. SIGNIFICANCE: The proposed method represents a significant step beyond detection of murmurs, providing characterization of intensity, which may provide an enhanced classification of clinical outcomes.

Heart murmur detection from phonocardiogram recordings: The George B. Moody PhysioNet Challenge 2022.

Cardiac auscultation is an accessible diagnostic screening tool that can help to identify patients with heart murmurs, who may need follow-up diagnostic screening and treatment for abnormal cardiac function. However, experts are needed to interpret the heart sounds, limiting the accessibility of cardiac auscultation in resource-constrained environments. Therefore, the George B. Moody PhysioNet Challenge 2022 invited teams to develop algorithmic approaches for detecting heart murmurs and abnormal cardiac function from phonocardiogram (PCG) recordings of heart sounds. For the Challenge, we sourced 5272 PCG recordings from 1452 primarily pediatric patients in rural Brazil, and we invited teams to implement diagnostic screening algorithms for detecting heart murmurs and abnormal cardiac function from the recordings. We required the participants to submit the complete training and inference code for their algorithms, improving the transparency, reproducibility, and utility of their work. We also devised an evaluation metric that considered the costs of screening, diagnosis, misdiagnosis, and treatment, allowing us to investigate the benefits of algorithmic diagnostic screening and facilitate the development of more clinically relevant algorithms. We received 779 algorithms from 87 teams during the Challenge, resulting in 53 working codebases for detecting heart murmurs and abnormal cardiac function from PCG recordings. These algorithms represent a diversity of approaches from both academia and industry, including methods that use more traditional machine learning techniques with engineered clinical and statistical features as well as methods that rely primarily on deep learning models to discover informative features. The use of heart sound recordings for identifying heart murmurs and abnormal cardiac function allowed us to explore the potential of algorithmic approaches for providing more accessible diagnostic screening in resource-constrained environments. The submission of working, open-source algorithms and the use of novel evaluation metrics supported the reproducibility, generalizability, and clinical relevance of the research from the Challenge.