Deep learning in voice analysis for diagnosing vocal cord pathologies: a systematic review.

OBJECTIVES: With smartphones and wearable devices becoming ubiquitous, they offer an opportunity for large-scale voice sampling. This systematic review explores the application of deep learning models for the automated analysis of voice samples to detect vocal cord pathologies. METHODS: We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines. We searched MEDLINE and Embase databases for original publications on deep learning applications for diagnosing vocal cord pathologies between 2002 and 2022. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS: Out of the 14 studies that met the inclusion criteria, data from a total of 3037 patients were analyzed. All studies were retrospective. Deep learning applications targeted Reinke's edema, nodules, polyps, cysts, unilateral cord paralysis, and vocal fold cancer detection. Most pathologies had detection accuracy above 90%. Thirteen studies (93%) exhibited a high risk of bias and concerns about applicability. CONCLUSIONS: Technology holds promise for enhancing the screening and diagnosis of vocal cord pathologies. While current research is limited, the presented studies offer proof of concept for developing larger-scale solutions.

The Effect of Oral Iron Chelator Deferiprone on Iron Overload and Oxidative Stress in Patients with Myelodysplastic Syndromes: A Study by the Israeli MDS Working Group.

BACKGROUND: Most patients with lower risk myelodysplastic neoplasms or syndromes (MDSs) become RBC transfusion-dependent, resulting in iron overload, which is associated with an increased oxidative stress state. Iron-chelation therapy is applied to attenuate the toxic effects of this state. Deferiprone (DFP) is an oral iron chelator, which is not commonly used in this patient population, due to safety concerns, mainly agranulocytosis. The purpose of this study was to assess the effect of DFP, on oxidative stress parameters in iron-overloaded RBC transfusion-dependent patients with lower risk MDSs. METHODS: Adult lower risk MDS patients with a cumulative transfusion burden of >20 red blood cell units and evidence of iron overload (serum ferritin >1,000 ng/mL) were included in this study. DFP was administered (100 mg/kg/day) for 4 months. Blood samples for oxidative stress parameters and iron overload parameters were done at baseline and monthly: reactive oxygen species (ROS), phosphatidylserine, reduced glutathione, membrane lipid peroxidation, serum ferritin, and cellular labile iron pool. The primary efficacy variable was ROS. Tolerability and side effects were recorded as well. A paired t test was applied for statistical analyses. RESULTS: Eighteen patients were treated with DFP. ROS significantly decreased in all cell lineages: median decrease of 58.6% in RBC, 33.3% in PMN, and 39.8% in platelets (p < 0.01 for all). Other oxidative stress markers improved: phosphatidylserine decreased by 57.95%, lipid peroxidase decreased by 141.3%, and reduced gluthathione increased by 72.8% (p < 0.01 for all). The iron-overload marker and cellular labile iron pool decreased by 35% in RBCs, 44.3% in PMN, and 46.3% in platelets (p < 0.01 for all). No significant changes were observed in SF levels. There were no events of agranulocytosis. All AEs were grades 1-2. CONCLUSIONS: Herein, we showed preliminary evidence that DFP decreases iron-induced oxidative stress in MDS patients with a good tolerability profile (albeit a short follow-up period). No cases of severe neutropenia or agranulocytosis were reported. The future challenge is to prove that reduction in iron toxicity will eventually be translated into a clinically meaningful improvement.

Adversarial attacks in radiology - A systematic review.

PURPOSE: The growing application of deep learning in radiology has raised concerns about cybersecurity, particularly in relation to adversarial attacks. This study aims to systematically review the literature on adversarial attacks in radiology. METHODS: We searched for studies on adversarial attacks in radiology published up to April 2023, using MEDLINE and Google Scholar databases. RESULTS: A total of 22 studies published between March 2018 and April 2023 were included, primarily focused on image classification algorithms. Fourteen studies evaluated white-box attacks, three assessed black-box attacks and five investigated both. Eleven of the 22 studies targeted chest X-ray classification algorithms, while others involved chest CT (6/22), brain MRI (4/22), mammography (2/22), abdominal CT (1/22), hepatic US (1/22), and thyroid US (1/22). Some attacks proved highly effective, reducing the AUC of algorithm performance to 0 and achieving success rates up to 100 %. CONCLUSIONS: Adversarial attacks are a growing concern. Although currently the threats are more theoretical than practical, they still represent a potential risk. It is important to be alert to such attacks, reinforce cybersecurity measures, and influence the formulation of ethical and legal guidelines. This will ensure the safe use of deep learning technology in medicine.

Current Applications of Artificial Intelligence in Sarcoidosis.

PURPOSE: Sarcoidosis is a complex disease which can affect nearly every organ system with manifestations ranging from asymptomatic imaging findings to sudden cardiac death. As such, diagnosis and prognostication are topics of continued investigation. Recent technological advancements have introduced multiple modalities of artificial intelligence (AI) to the study of sarcoidosis. Machine learning, deep learning, and radiomics have predominantly been used to study sarcoidosis. METHODS: Articles were collected by searching online databases using keywords such as sarcoid, machine learning, artificial intelligence, radiomics, and deep learning. Article titles and abstracts were reviewed for relevance by a single reviewer. Articles written in languages other than English were excluded. CONCLUSIONS: Machine learning may be used to help diagnose pulmonary sarcoidosis and prognosticate in cardiac sarcoidosis. Deep learning is most comprehensively studied for diagnosis of pulmonary sarcoidosis and has less frequently been applied to prognostication in cardiac sarcoidosis. Radiomics has primarily been used to differentiate sarcoidosis from malignancy. To date, the use of AI in sarcoidosis is limited by the rarity of this disease, leading to small, suboptimal training sets. Nevertheless, there are applications of AI that have been used to study other systemic diseases, which may be adapted for use in sarcoidosis. These applications include discovery of new disease phenotypes, discovery of biomarkers of disease onset and activity, and treatment optimization.

MRI features of intraductal papillary mucinous neoplasm of the bile ducts, "The myth about the cyst": A systematic review.

Rationale and objectives: Intraductal papillary mucinous neoplasm of the bile ducts (IPMN-B) is a true pre-cancerous lesion, which shares common features with pancreatic IPMN (IPMN-P). While IPMN-P is a well described entity for which guidelines were formulated and revised, IPMN-B is a poorly described entity.We carried out a systematic review to evaluate the existing literature, emphasizing the role of MRI in IPMN-B depiction. Materials and methods: PubMed database was used to identify original studies and case series that reported MR Imaging features of IPMN-B. The search keywords were "IPMN OR intraductal papillary mucinous neoplasm OR IPNB OR intraductal papillary neoplasm of the bile duct AND Biliary OR biliary cancer OR hepatic cystic lesions". Risk of bias and applicability were evaluated using the QUADAS-2 tool. Results: 884 Records were Identified through database searching. 12 studies satisfied the inclusion criteria, resulting in MR features of 288 patients. All the studies were retrospective. Classic features of IPMN-B are under-described. Few studies note worrisome features, concerning for an underlying malignancy. 50 % of the studies had a high risk of bias and concerns regarding applicability. Conclusions: The MRI features of IPMN-B are not well elaborated and need to be further studied. Worrisome features and guidelines regarding reporting the imaging findings should be established and published. Radiologists should be aware of IPMN-B, since malignancy diagnosis in an early stage will yield improved prognosis.

Jejunal Inflammation in Crohn's Disease: Comparison between Diffusion Weighted Magnetic Resonance Imaging and Video Capsule Endoscopy.

BACKGROUND: Jejunal disease is associated with worse prognosis in Crohn's disease. The added value of diffusion weighted imaging for evaluating jejunal inflammation related to Crohn's Disease is scarce. OBJECTIVES: To compare diffusion weighted imaging, video capsule endoscopy, and inflammatory biomarkers in the assessment of Crohn's disease involving the jejunum. METHODS: Crohn's disease patients in clinical remission were prospectively recruited and underwent magnetic resonance (MR)-enterography and video capsule endoscopy. C-reactive protein and fecal-calprotectin levels were obtained. MR-enterography images were evaluated for restricted diffusion, and apparent diffusion coefficient values were measured. The video capsule endoscopy-based Lewis score was calculated. Associations between diffusion weighted imaging, apparent diffusion coefficient, Lewis score, and inflammatory biomarkers were evaluated. RESULTS: The study included 51 patients, and 27/51 (52.9%) with video capsule endoscopies showed jejunal mucosal inflammation. Sensitivity and specificity of restricted diffusion for video capsule endoscopy mucosal inflammation were 59.3% and 37.5% for the first reader, and 66.7% and 37.5% for the second reader, respectively. Diffusion weighted imaging was not statistically associated with jejunal video capsule endoscopy inflammation (P = 0.813). CONCLUSIONS: Diffusion weighted imaging was not an effective test for evaluation of jejunal inflammation as seen by video capsule endoscopy in patients with quiescent Crohn's disease.

Self-reported treatment effectiveness for Crohn's disease using a novel crowdsourcing web-based platform.

BACKGROUND AND AIMS: Internet and social media platforms have become an unprecedented source for sharing self-experience, potentially allowing the collection and integration of health data with patient experience. StuffThatWorks (STW) is an online open platform that applies machine learning and the power of crowdsourcing, where patients with chronic medical conditions can self-report and compare their individual outcomes using a structured online questionnaire. We aimed to conduct a cross-sectional, international, crowdsourcing, artificial-intelligence (AI) web-based study of patients with Crohn's disease (CD) self-reporting their outcomes. METHODS: A proprietary STW Bayesian inference model was built to measure improvement in CD severity (on scale of 1-5) for each treatment and ranked treatments using effectiveness. The effectiveness of first-line biological treatments was analyzed by multiple comparisons and by calculating odds ratios and 95% confidence intervals for each treatment pair. RESULTS: We included 7593 self-reported CD patients for the analysis. Most of the participants were female (75.8%) and from English-speaking countries (95.7%). Overall, anti-TNF drugs were the most reported tried treatment (52.8%). Infliximab (IFX) was ranked as the most effective treatment by the STW effectiveness model followed by bowel surgery (second), adalimumab (ADA, third), ustekinumab (UST, 4rd), and vedolizumab (VDZ, fifth). In paired comparison analyses, IFX was most effective, ADA had similar effectiveness compared to UST and all three were more effective than VDZ. CONCLUSION: We present the first online crowdsourcing AI platform-based study of self-reported treatment effectiveness in CD. Net-based crowdsourcing patient-reported outcome platforms can potentially help both clinicians and patients select the best treatment for their condition.

Capsule Endoscopy in Inflammatory Bowel Disease: Panenteric Capsule Endoscopy and Application of Artificial Intelligence.

Video capsule endoscopy (VCE) of the small-bowel has been proven to accurately diagnose small-bowel inflammation and to predict future clinical flares among patients with Crohn's disease (CD). In 2017, the panenteric capsule (PillCam Crohn's system) was introduced for the first time, enabling a reliable evaluation of the whole small and large intestines. The great advantage of visualization of both parts of the gastrointestinal tract in a feasible and single procedure, holds a significant promise for patients with CD, enabling determination of the disease extent and severity, and potentially optimize disease management. In recent years, applications of machine learning, for VCE have been well studied, demonstrating impressive performance and high accuracy for the detection of various gastrointestinal pathologies, among them inflammatory bowel disease lesions. The use of artificial neural network models has been proven to accurately detect/classify and grade CD lesions, and shorten the VCE reading time, resulting in a less tedious process with a potential to minimize missed diagnosis and better predict clinical outcomes. Nevertheless, prospective, and real-world studies are essential to precisely examine artificial intelligence applications in real-life inflammatory bowel disease practice.

Diffusion-weighted MRI for predicting and assessing treatment response of liver metastases from CRC - A systematic review and meta-analysis.

The evaluation of response to chemotherapy and targeted therapies in colorectal liver metastases has traditionally been based on size changes, as per the RECIST criteria. However, therapy may alter tissue composition and not only tumor size, therefore, functional imaging techniques such as diffusion-weighted magnetic resonance imaging (DWI) may offer a more comprehensive assessment of treatment response. The aim of this systematic review and meta-analysis was to evaluate the use of DWI in the prediction and assessment of response to treatment in colorectal liver metastases and to determine if there is a baseline apparent diffusion coefficient (ADC) cut-off value that can predict a favorable response. A literature search was conducted using the MEDLINE/PubMed database, and risk of bias was evaluated using the QUADAS-2 tool. The mean differences between responders and non-responders were pooled. A total of 16 studies met the inclusion criteria, and various diffusion-derived techniques and coefficients were found to have potential for predicting and assessing treatment response. However, discrepancies were noted between studies. The most consistent predictor of response was a lower baseline ADC value calculated using traditional mono-exponential methods. Non-mono-exponential techniques for calculating DWI-derived parameters were also reported. A meta-analysis of a subset of studies failed to establish a cut-off value of ADC due to heterogeneity, but revealed a pooled mean difference of -0.12 × 10-3 mm2/s between responders and non-responders. The results of this systematic review suggest that diffusion-derived techniques and coefficients may contribute to the evaluation and prediction of treatment response in colorectal liver metastases. Further controlled prospective studies are needed to confirm these findings and to guide clinical and radiological decision-making in the management of patients with CRC liver metastases.

A systematic review of adeno-associated virus gene therapy clinical trials for HIV - A potential solution for patients with haemophilia and HIV?

INTRODUCTION: In the past HIV infection was a common complication of haemophilia therapy. Gene therapy trials in Haemophilia patients using rAAV have shown promising results; Unfortunately, the majority of gene therapy trials studies have excluded HIV positive patients. We decided to systematically review the published clinical trials using rAAV for HIV prevention. METHODS: A comprehensive literature search was performed to identify studies evaluating clinical trials using rAAV for HIV. The search was conducted using the MEDLINE/PubMed databases. Search keywords included 'gene therapy', 'adeno-associated virus', 'HIV' and 'clinical trial'. RESULTS: Three studies met our inclusion criteria. Two were phase 1 studies and one was a phase 2 study. One study examined an AAV coding for human monoclonal IgG1 antibody whereas the other two studies delivered a vector coding for viral protease and part of reverse transcriptase. All studies administered the vaccine intramuscularly and showed a response as well a good safety profile. DISCUSSION: The concept of using a viral vector to prevent a viral infection is revolutionary. Due to the paucity of information regarding application of any gene therapy in HIV patients and the potential use of gene therapy in haemophilia patients with HIV in the future warrants attention.

MCP-1/CCR2 axis inhibition sensitizes the brain microenvironment against melanoma brain metastasis progression.

Development of resistance to chemo- and immunotherapies often occurs following treatment of melanoma brain metastasis (MBM). The brain microenvironment (BME), particularly astrocytes, cooperate toward MBM progression by upregulating secreted factors, among which we found that monocyte chemoattractant protein-1 (MCP-1) and its receptors, CCR2 and CCR4, were overexpressed in MBM compared with primary lesions. Among other sources of MCP-1 in the brain, we show that melanoma cells altered astrocyte secretome and evoked MCP-1 expression and secretion, which in turn induced CCR2 expression in melanoma cells, enhancing in vitro tumorigenic properties, such as proliferation, migration, and invasion of melanoma cells. In vivo pharmacological blockade of MCP-1 or molecular knockout of CCR2/CCR4 increased the infiltration of cytotoxic CD8+ T cells and attenuated the immunosuppressive phenotype of the BME as shown by decreased infiltration of Tregs and tumor-associated macrophages/microglia in several models of intracranially injected MBM. These in vivo strategies led to decreased MBM outgrowth and prolonged the overall survival of the mice. Our findings highlight the therapeutic potential of inhibiting interactions between BME and melanoma cells for the treatment of this disease.

Changes in Helicobacter pylori Treatment from Discovery to Nowadays: A High-Level Analysis of PubMed Publications.

Background: Since the discovery of Helicobacter pylori (H. pylori) 40 years ago, treatment options have changed dramatically adjacent to new drugs development and the emergence of multi-drug resistance. In this study, we aimed to assess published literature on treatment regimens for H. pylori in the past four decades, with regards to specific drug resistance and geographic distribution. Methods: We have queried PubMed for all available H. pylori-related entries published during 1987-2020. For each entry, we retrieved the title, abstract, and keywords. Two gastrointestinal specialists decided in consensus on a list of terms to classify entries. The terms specify types of treatment and different types of regimens. Annual trends of publications were plotted for different treatment types and sub-analyses. Results: Overall, 47,170 H. pylori-related entries were published between 1987 and 2020. Medication treatment showed the highest number of total publications 6183/47,170 (13.1%), followed by antibiotics 5493/47,170 (11.6%), and probiotic which was substantially lower (0.7%). For treatment regimens type, triple therapy had the highest number of publications 2400/47,170 (5.1%) followed by sequential therapy 342/47,170 (0.7%), and bismuth quadruple therapy 115/47,170 (0.2%). Analysis by antibiotic resistance showed that clarithromycin treatment had the highest number of publications 3537/47,170 (7.5%). Since 2013, there is a steep upward slope (5.1±0.7 publications/year, p < 0.001) for publications originating from China. Conclusion: Our findings reflect the changes of the commonly prescribed regimens along the years, following the occurrence and the rise of H. pylori antibiotic resistance. In recent years, there is a steep rise in publications in countries with policies of screening and eradication for gastric cancer prevention, which is currently not applied in Western countries. A text-mining analysis of H. pylori publications contributes to the understanding of treatment options and development trends worldwide.

Alerting on mortality among patients discharged from the emergency department: a machine learning model.

OBJECTIVES: Physicians continuously make tough decisions when discharging patients. Alerting on poor outcomes may help in this decision. This study evaluates a machine learning model for predicting 30-day mortality in emergency department (ED) discharged patients. METHODS: We retrospectively analysed visits of adult patients discharged from a single ED (1/2014-12/2018). Data included demographics, evaluation and treatment in the ED, and discharge diagnosis. The data comprised of both structured and free-text fields. A gradient boosting model was trained to predict mortality within 30 days of release from the ED. The model was trained on data from the years 2014-2017 and validated on data from the year 2018. In order to reduce potential end-of-life bias, a subgroup analysis was performed for non-oncological patients. RESULTS: Overall, 363 635 ED visits of discharged patients were analysed. The 30-day mortality rate was 0.8%. A majority of the mortality cases (65.3%) had a known oncological disease. The model yielded an area under the curve (AUC) of 0.97 (95% CI 0.96 to 0.97) for predicting 30-day mortality. For a sensitivity of 84% (95% CI 0.81 to 0.86), this model had a false positive rate of 1:20. For patients without a known malignancy, the model yielded an AUC of 0.94 (95% CI 0.92 to 0.95). CONCLUSIONS: Although not frequent, patients may die following ED discharge. Machine learning-based tools may help ED physicians identify patients at risk. An optimised decision for hospitalisation or palliative management may improve patient care and system resource allocation.

Synergistic effect of hypoalbuminaemia and hypotension in predicting in-hospital mortality and intensive care admission: a retrospective cohort study.

OBJECTIVE: Hypoalbuminaemia is an important prognostic factor. It may be associated with poor nutritional states, chronic heart and kidney disease, long-standing infection and cancer. Hypotension is a hallmark of circulatory failure. We evaluated hypoalbuminaemia and hypotension synergism as predictor of in-hospital mortality and intensive care unit (ICU) admission. DESIGN: We retrospectively analysed emergency department (ED) visits from January 2011 to December 2019. SETTING: Data were retrieved from five Mount Sinai health system hospitals, New York. PARTICIPANTS: We included consecutive ED patients ≥18 years with albumin measurements. PRIMARY AND SECONDARY OUTCOME MEASURES: Clinical outcomes were in-hospital mortality and ICU admission. The rates of these outcomes were stratified by systolic blood pressure (SBP) (<90 vs ≥90 mm Hg) and albumin levels. Variables included demographics, presenting vital signs, comorbidities (measured as ICD codes) and other common blood tests. Multivariable logistic regression models analysed the adjusted OR of different levels of albumin and SBP for predicting ICU admission and in-hospital mortality. The models were adjusted for demographics, vital signs, comorbidities and common laboratory results. Patients with albumin 3.5-4.5 g/dL and SBP ≥90 mm Hg were used as reference. RESULTS: The cohort included 402 123 ED arrivals (27.9% of total adult ED visits). The rates of in-hospital mortality, ICU admission and overall admission were 1.7%, 8.4% and 47.1%, respectively. For SBP <90 mm Hg and albumin <2.5 g/dL, mortality and ICU admission rates were 34.0% and 40.6%, respectively; for SBP <90 mm Hg and albumin ≥2.5 g/dL 8.2% and 24.1%, respectively; for SBP ≥90 mm Hg and albumin <2.5 g/dL 11.4% and 18.6%, respectively; for SBP ≥90 mm Hg and albumin 3.5-4.5 g/dL 0.5% and 6.4%, respectively. Multivariable analysis showed that in patients with hypotension and albumin <2.5 g/dL the adjusted OR for in-hospital mortality was 37.1 (95% CI 32.3 to 42.6), and for ICU admission was 5.4 (95% CI 4.8 to 6.1). CONCLUSION: Co-occurrence of hypotension and hypoalbuminaemia is associated with poor hospital outcomes.

The Prognostic Role of Neutrophil-to-Lymphocyte Ratio in Patients Hospitalized with Acute Pulmonary Embolism.

Early risk stratification is essential for determining the appropriate therapeutic management approach of pulmonary embolism (PE). This study aimed to evaluate the prognostic value of the neutrophil-to-lymphocyte ratio (NLR) in patients hospitalized with acute pulmonary embolism by investigating its association with mortality in a large-scale population diagnosed and hospitalized with acute PE. We retrieved all consecutive patients hospitalized in an internal medicine department or an intensive care unit in a tertiary medical center from December 2007 to April 2021 with a discharge diagnosis of pulmonary embolism. A total of 2072 patients were included. Patients with above-median NLR (i.e., 5.12) had a higher 30-day mortality risk (adjusted odds ratio (aOR), 2.82; 95% confidence interval (CI) 2.14-3.70) and higher one-year mortality risk (aOR, 2.51; 95% CI 2.04-3.08). Similar trends were demonstrated in a sub-analysis of patients without cancer and hemodynamically stable (i.e., systolic blood pressure over 90 mmHg). Furthermore, the median hospital length of stay in patients with an elevated NLR was higher, and so was the in-hospital mortality rate. Elevated NLR in acute PE is associated with a worse short-term and long-term prognosis and with a longer duration of hospitalization.

Trends in inflammatory bowel disease treatment in the past two decades-a high-level text mining analysis of PubMed publications.

AIM: Many therapeutic options for inflammatory bowel disease (IBD) emerged during the last 2 decades, along with the rise in disease prevalence and incidence. We aimed at assessing the published literature on different treatment options in that period. Special attention was attributed to specific medication mechanisms and geographic diversity. MATERIALS AND METHODS: We have queried PubMed for all available IBD-related entries published during 2000-2020. The following data were extracted for each entry: PubMed unique article ID (PMID), title, publishing journal, abstract text, keywords (if any), and authors' affiliations. Two gastrointestinal specialists decided in consensus on a list of terms to classify entries. The terms belonged to five treatment groups: medical, surgical, dietary, microbiome manipulation, and complementary medicine. The medical and complementary medicine groups were further sub-classified. Annual trends of publications for the years 2000-2020 were plotted for different treatment types. The slopes of publication trends were calculated by fitting regression lines to the annual number of publications. RESULTS: Overall, 77,505 IBD entries were published between 2000 and 2020. Medical treatment showed the highest number of total publications 21,540/77,505 (27.8%), followed by surgical 7605/77,505 (9.8%), microbiome research 5260/77,505 (6.8%), dietary 4819/77,505 (6.2%), and complementary medicine treatment 762/77,505 (1.0%). Interestingly, since 2012 there is a steep rise in microbiome publications that outnumbered surgery in the last 2 years. Trend analysis of medical treatment showed that biologics had the steepest slope (57.5, p < 0.001), followed by immunomodulators (4.9, p < 0.001), small molecules (3.9, p < 0.001), and 5-ASA (3.8, p < 0.001). CONCLUSION: According to our high-level publications trend analysis, the past 2 decades certainly deserve the reference as the "biologic era", as publications regarding biological therapy outnumbered all other treatment options. Interestingly, though very popular among patients, complementary medicine was not studied with correlation to its' acceptance among patients.

Deep learning for noninvasive liver fibrosis classification: A systematic review.

BACKGROUND AND AIMS: While biopsy is the gold standard for liver fibrosis staging, it poses significant risks. Noninvasive assessment of liver fibrosis is a growing field. Recently, deep learning (DL) technology has revolutionized medical image analysis. This technology has the potential to enhance noninvasive fibrosis assessment. We systematically examined the application of DL in noninvasive liver fibrosis imaging. METHODS: Embase, MEDLINE, Web of Science, and IEEE Xplore databases were used to identify studies that reported on the accuracy of DL for classification of liver fibrosis on noninvasive imaging. The search keywords were "liver or hepatic," "fibrosis or cirrhosis," and "neural or DL networks." Risk of bias and applicability were evaluated using the QUADAS-2 tool. RESULTS: Sixteen studies were retrieved. Imaging modalities included ultrasound (n = 10), computed tomography (n = 3), and magnetic resonance imaging (n = 3). The studies analyzed a total of 40 405 radiological images from 15 853 patients. All but two of the studies were retrospective. In most studies the "ground truth" reference was the METAVIR score for pathological staging (n = 9.56%). The majority of the studies reported an accuracy >85% when compared to histopathology. Fourteen studies (87.5%) had a high risk of bias and concerns regarding applicability. CONCLUSIONS: Deep learning has the potential to play an emerging role in liver fibrosis classification. Yet, it is still limited by a relatively small number of retrospective studies. Clinicians should facilitate the use of this technology by sharing databases and standardized reports. This may optimize the noninvasive evaluation of liver fibrosis on a large scale.