Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Computerized analysis of digital pathology images offers the potential of improving clinical care (e.g. automated diagnosis) and catalyzing research (e.g. discovering disease subtypes). There are two key challenges thwarting computerized analysis of digital pathology images: first, whole slide pathology images are massive, making computerized analysis inefficient, and second, diverse tissue regions in whole slide images that are not directly relevant to the disease may mislead computerized diagnosis algorithms. We propose a method to overcome both of these challenges that utilizes a coarse-to-fine analysis of the localized characteristics in pathology images. An initial surveying stage analyzes the diversity of coarse regions in the whole slide image. This includes extraction of spatially localized features of shape, color and texture from tiled regions covering the slide. Dimensionality reduction of the features assesses the image diversity in the tiled regions and clustering creates representative groups. A second stage provides a detailed analysis of a single representative tile from each group. An Elastic Net classifier produces a diagnostic decision value for each representative tile. A weighted voting scheme aggregates the decision values from these tiles to obtain a diagnosis at the whole slide level. We evaluated our method by automatically classifying 302 brain cancer cases into two possible diagnoses (glioblastoma multiforme (N = 182) versus lower grade glioma (N = 120)) with an accuracy of 93.1 % (p << 0.001). We also evaluated our method in the dataset provided for the 2014 MICCAI Pathology Classification Challenge, in which our method, trained and tested using 5-fold cross validation, produced a classification accuracy of 100% (p << 0.001). Our method showed high stability and robustness to parameter variation, with accuracy varying between 95.5% and 100% when evaluated for a wide range of parameters. Our approach may be useful to automatically differentiate between the two cancer subtypes.     

Digital pathology and image analysis augment biospecimen annotation and biobank quality assurance harmonization

Standardization of biorepository best practices will enhance the quality of translational biomedical research utilizing patient-derived biobank specimens. Harmonization of pathology quality assurance procedures for biobank accessions has lagged behind other avenues of biospecimen research and biobank development. Comprehension of the cellular content of biorepository specimens is important for discovery of tissue-specific clinically relevant biomarkers for diagnosis and treatment. While rapidly emerging technologies in molecular analyses and data mining create focus on appropriate measures for minimizing pre-analytic artifact-inducing variables, less attention gets paid to annotating the constituent makeup of biospecimens for more effective specimen selection by biobank clients. Both pre-analytic tissue processing and specimen composition influence acquisition of relevant macromolecules for downstream assays. Pathologist review of biorepository submissions, particularly tissues as part of quality assurance procedures, helps to ensure that the intended target cells are present and in sufficient quantity in accessioned specimens. This manual procedure can be tedious and subjective. Incorporating digital pathology into biobank quality assurance procedures, using automated pattern recognition morphometric image analysis to quantify tissue feature areas in digital whole slide images of tissue sections, can minimize variability and subjectivity associated with routine pathologic evaluations in biorepositories. Whole-slide images and pathologist-reviewed morphometric analyses can be provided to researchers to guide specimen selection. Harmonization of pathology quality assurance methods that minimize subjectivity and improve reproducibility among collections would facilitate research-relevant specimen selection by investigators and could facilitate information sharing in an integrated network approach to biobanking.     

Computational framework for generating large panoramic super-resolution images from localization microscopy

Combining super-resolution localization microscopy with pathology creates new opportunities for biomedical researches. This combination requires a suitable image mosaic method for generating a panoramic image from many overlapping super-resolution images. However, current image mosaic methods are not suitable for this purpose. Here we proposed a computational framework and developed an image mosaic method called NanoStitcher. We generated ground truth datasets and defined criteria to evaluate this computational framework. We used both simulated and experimental datasets to prove that NanoStitcher exhibits better performance than two representative image mosaic methods. This study is helpful for the mature of super-resolution digital pathology.     

Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides

Feature vectors provided by pre-trained deep artificial neural networks have become a dominant source for image representation in recent literature. Their contribution to the performance of image analysis can be improved through fine-tuning. As an ultimate solution, one might even train a deep network from scratch with the domain-relevant images, a highly desirable option which is generally impeded in pathology by lack of labeled images and the computational expense. In this study, we propose a new network, namely KimiaNet, that employs the topology of the DenseNet with four dense blocks, fine-tuned and trained with histopathology images in different configurations. We used more than 240,000 image patches with $1000\times 1000$ pixels acquired at 20$\times$ magnification through our proposed “high-cellularity mosaic” approach to enable the usage of weak labels of 7126 whole slide images of formalin-fixed paraffin-embedded human pathology samples publicly available through The Cancer Genome Atlas (TCGA) repository. We tested KimiaNet using three public datasets, namely TCGA, endometrial cancer images, and colorectal cancer images by evaluating the performance of search and classification when corresponding features of different networks are used for image representation. As well, we designed and trained multiple convolutional batch-normalized ReLU (CBR) networks. The results show that KimiaNet provides superior results compared to the original DenseNet and smaller CBR networks when used as feature extractor to represent histopathology images.     

Automated image analysis in histopathology: a valuable tool in medical diagnostics

Virtual pathology, the process of assessing digital images of histological slides, is gaining momentum in today's laboratory environment. Indeed, digital image acquisition systems are becoming commonplace, and associated image analysis solutions are viewed by most as the next critical step in automated histological analysis. Here, we document the advances in the technology, with reference to past and current techniques in histological assessment. In addition, the demand for these technologies is analyzed with major players profiled. As there are several image analysis software programs focusing on the quantification of immunohistochemical staining, particular attention is paid to this application in this review. Oncology has been a primary target area for these approaches, with example studies in this therapeutic area being covered here. Toxicology-based image analysis solutions are also profiled as these are steadily increasing in popularity, especially within the pharmaceutical industry. Reinforced by the phenomenal growth of the virtual pathology field, it is envisioned that the market for automated image analysis tools will greatly expand over the next 10 years.     

Conditional GANs based system for fibrosis detection and quantification in Hematoxylin and Eosin whole slide images

Assessing the degree of liver fibrosis is fundamental for the management of patients with chronic liver disease, in liver transplants procedures, and in general liver disease research. The fibrosis stage is best assessed by histopathologic evaluation, and Masson’s Trichrome stain (MT) is the stain of choice for this task in many laboratories around the world. However, the most used stain in histopathology is Hematoxylin Eosin (HE) which is cheaper, has a faster turn-around time and is the primary stain routinely used for evaluation of liver specimens. In this paper, we propose a novel digital pathology system that accurately detects and quantifies the footprint of fibrous tissue in HE whole slide images (WSI). The proposed system produces virtual MT images from HE using a deep learning model that learns deep texture patterns associated with collagen fibers. The training pipeline is based on conditional generative adversarial networks (cGAN), which can achieve accurate pixel-level transformation. Our comprehensive training pipeline features an automatic WSI registration algorithm, which qualifies the HE/MT training slides for the cGAN model. Using liver specimens collected during liver transplantation procedures, we conducted a range of experiments to evaluate the detected footprint of selected anatomical features. Our evaluation includes both image similarity and semantic segmentation metrics. The proposed system achieved enhanced results in the experiments with significant improvement over the state-of-the-art CycleGAN learning style, and over direct prediction of fibrosis in HE without having the virtual MT step.     

Yottixel – An Image Search Engine for Large Archives of Histopathology Whole Slide Images

With the emergence of digital pathology, searching for similar images in large archives has gained considerable attention. Image retrieval can provide pathologists with unprecedented access to the evidence embodied in already diagnosed and treated cases from the past. This paper proposes a search engine specialized for digital pathology, called Yottixel, a portmanteau for “one yotta pixel,” alluding to the big-data nature of histopathology images. The most impressive characteristic of Yottixel is its ability to represent whole slide images (WSIs) in a compact manner. Yottixel can perform millions of searches in real-time with a high search accuracy and low storage profile. Yottixel uses an intelligent indexing algorithm capable of representing WSIs with a mosaic of patches which are then converted into barcodes, called “Bunch of Barcodes” (BoB), the most prominent performance enabler of Yottixel. The performance of the prototype platform is qualitatively tested using 300 WSIs from the University of Pittsburgh Medical Center (UPMC) and 2,020 WSIs from The Cancer Genome Atlas Program (TCGA) provided by the National Cancer Institute. Both datasets amount to more than 4,000,000 patches of 1000 × 1000 pixels. We report three sets of experiments that show that Yottixel can accurately retrieve organs and malignancies, and its semantic ordering shows good agreement with the subjective evaluation of human observers.     

A review in radiomics: Making personalized medicine a reality via routine imaging

Radiomics is the quantitative analysis of standard-of?care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid “scientific pollution” and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.     

虚拟切片技术在肾内科临床、科研及教学中的应用前景

虚拟切片技术能够将传统的病理切片转换为数字图像, 使其具备长期保存、容易获取等特点, 正逐渐替代玻璃切片和光学显微镜用于病理远程会诊、科研和教学, 但其在肾内科领域的应用尚未广泛开展。本文通过文献复习和实践经验, 对虚拟切片技术在肾内科临床、科研和教学中的应用前景进行阐述, 一方面强调其潜在价值, 另一方面对目前实际应用中存在的问题及挑战提出解决建议。     

Federated learning for computational pathology on gigapixel whole slide images

Deep Learning-based computational pathology algorithms have demonstrated profound ability to excel in a wide array of tasks that range from characterization of well known morphological phenotypes to predicting non human-identifiable features from histology such as molecular alterations. However, the development of robust, adaptable and accurate deep learning-based models often rely on the collection and time-costly curation large high-quality annotated training data that should ideally come from diverse sources and patient populations to cater for the heterogeneity that exists in such datasets. Multi-centric and collaborative integration of medical data across multiple institutions can naturally help overcome this challenge and boost the model performance but is limited by privacy concerns among other difficulties that may arise in the complex data sharing process as models scale towards using hundreds of thousands of gigapixel whole slide images. In this paper, we introduce privacy-preserving federated learning for gigapixel whole slide images in computational pathology using weakly-supervised attention multiple instance learning and differential privacy. We evaluated our approach on two different diagnostic problems using thousands of histology whole slide images with only slide-level labels. Additionally, we present a weakly-supervised learning framework for survival prediction and patient stratification from whole slide images and demonstrate its effectiveness in a federated setting. Our results show that using federated learning, we can effectively develop accurate weakly-supervised deep learning models from distributed data silos without direct data sharing and its associated complexities, while also preserving differential privacy using randomized noise generation. We also make available an easy-to-use federated learning for computational pathology software package: http://github.com/mahmoodlab/HistoFL.     

Single image super-resolution for whole slide image using convolutional neural networks and self-supervised color normalization

High-quality whole slide scanners used for animal and human pathology scanning are expensive and can produce massive datasets, which limits the access to and adoption of this technique. As a potential solution to these challenges, we present a deep learning-based approach making use of single image super-resolution (SISR) to reconstruct high-resolution histology images from low-resolution inputs. Such low-resolution images can easily be shared, require less storage, and can be acquired quickly using widely available low-cost slide scanners. The network consists of multi-scale fully convolutional networks capable of capturing hierarchical features. Conditional generative adversarial loss is incorporated to penalize blurriness in the output images. The network is trained using a progressive strategy where the scaling factor is sampled from a normal distribution with an increasing mean. The results are evaluated with quantitative metrics and are used in a clinical histopathology diagnosis procedure which shows that the SISR framework can be used to reconstruct high-resolution images with clinical level quality. We further propose a self-supervised color normalization method that can remove staining variation artifacts. Quantitative evaluations show that the SISR framework can generalize well on unseen data collected from other patient tissue cohorts by incorporating the color normalization method.     

Tissue microarrays: applications in genomic research

The widespread application of tissue microarrays in cancer research and the clinical pathology laboratory demonstrates a versatile and portable technology. The rapid integration of tissue microarrays into biomarker discovery and validation processes reflects the forward thinking of researchers who have pioneered the high-density tissue microarray. The precise arrangement of hundreds of archival clinical tissue samples into a composite tissue microarray block is now a proven method for the efficient and standardized analysis of molecular markers. With applications in cancer research, tissue microarrays are a valuable tool in validating candidate markers discovered in highly sensitive genome-wide microarray experiments. With applications in clinical pathology, tissue microarrays are used widely in immunohistochemistry quality control and quality assurance. The timeline of a biomarker implicated in prostate neoplasia, which was identified by complementary DNA expression profiling, validated by tissue microarrays and is now used as a prognostic immunohistochemistry marker, is reviewed. The tissue microarray format provides opportunities for digital imaging acquisition, image processing and database integration. Advances in digital imaging help to alleviate previous bottlenecks in the research pipeline, permit computer image scoring and convey telepathology opportunities for remote image analysis. The tissue microarray industry now includes public and private sectors with varying degrees of research utility and offers a range of potential tissue microarray applications in basic research, prognostic oncology and drug discovery.     

Prototypical multiple instance learning for predicting lymph node metastasis of breast cancer from whole-slide pathological images

Computerized identification of lymph node metastasis of breast cancer (BCLNM) from whole-slide pathological images (WSIs) can largely benefit therapy decision and prognosis analysis. Besides the general challenges of computational pathology, like extra-high resolution, very expensive fine-grained annotation, etc., two particular difficulties with this task lie in (1) modeling the significant inter-tumoral heterogeneity in BCLNM pathological images, and (2) identifying micro-metastases, i.e., metastasized tumors with tiny foci. Towards this end, this paper presents a novel weakly supervised method, termed as Prototypical Multiple Instance Learning (PMIL), to learn to predict BCLNM from WSIs with slide-level class labels only. PMIL introduces the well-established vocabulary-based multiple instance learning (MIL) paradigm into computational pathology, which is characterized by utilizing the so-called prototypes to model pathological data and construct WSI features. PMIL mainly consists of two innovatively designed modules, i.e., the prototype discovery module which acquires prototypes from training data by unsupervised clustering, and the prototype-based slide embedding module which builds WSI features by matching constitutive patches against the prototypes. Relative to existing MIL methods for WSI classification, PMIL has two substantial merits: (1) being more explicit and interpretable in modeling the inter-tumoral heterogeneity in BCLNM pathological images, and (2) being more effective in identifying micro-metastases. Evaluation is conducted on two datasets, i.e., the public Camelyon16 dataset and the Zbraln dataset created by ourselves. PMIL achieves an AUC of 88.2% on Camelyon16 and 98.4% on Zbraln (at 40x magnification factor), which consistently outperforms other compared methods. Comprehensive analysis will also be carried out to further reveal the effectiveness and merits of the proposed method.     

Neighbourhood approximation using randomized forests

Leveraging available annotated data is an essential component of many modern methods for medical image analysis. In particular, approaches making use of the “neighbourhood” structure between images for this purpose have shown significant potential. Such techniques achieve high accuracy in analysing an image by propagating information from its immediate “neighbours” within an annotated database. Despite their success in certain applications, wide use of these methods is limited due to the challenging task of determining the neighbours for an out-of-sample image. This task is either computationally expensive due to large database sizes and costly distance evaluations, or infeasible due to distance definitions over semantic information, such as ground truth annotations, which is not available for out-of-sample images.This article introduces Neighbourhood Approximation Forests (NAFs), a supervised learning algorithm providing a general and efficient approach for the task of approximate nearest neighbour retrieval for arbitrary distances. Starting from an image training database and a user-defined distance between images, the algorithm learns to use appearance-based features to cluster images approximating the neighbourhood structured induced by the distance. NAF is able to efficiently infer nearest neighbours of an out-of-sample image, even when the original distance is based on semantic information. We perform experimental evaluation in two different scenarios: (i) age prediction from brain MRI and (ii) patch-based segmentation of unregistered, arbitrary field of view CT images. The results demonstrate the performance, computational benefits, and potential of NAF for different image analysis applications.     

Comparison between image texture and polarization features in histopathology

Digital pathology has shown great importance for diagnostic purposes in the digital age by integrating basic image features into multi-modality information. We quantify the degree of correlation between the multiple texture features from H&E images and polarization parameter sets derived from Mueller matrix images of the same sample to provide more microstructural information for assisting diagnosis. The experimental result shows the correlations between texture feature and polarization parameter via Pearson coefficients. Polarization parameters t₁, D_L and the depolarization parameter Δ correlated with image texture features Tamura_Fcon and Tamura_Frgh, and can be used as powerful tools to quantitatively characterize cell nuclei related with tumor progression in breast pathological tissues. Polarization parameters δ and r_L associated with the image texture feature Tamura_Flin have great potential for the quantitative characterization of proliferative fibers produced by inflammation. Furthermore, polarization parameters have the advantages of stable recognition in low resolution images. This work validates the associations between image texture features and polarization parameters and the merit of polarization imaging methods in low-resolution situations.     

Low-cost whole slide imaging system with single-shot autofocusing based on color-multiplexed illumination and deep learning

Recent research on whole slide imaging (WSI) has greatly promoted the development of digital pathology. However, accurate autofocusing is still the main challenge for WSI acquisition and automated digital microscope. To address this problem, this paper describes a low cost WSI system and proposes a fast, robust autofocusing method based on deep learning. We use a programmable LED array for sample illumination. Before the brightfield image acquisition, we turn on a red and a green LED, and capture a color-multiplexed image, which is fed into a neural network for defocus distance estimation. After the focus tracking process, we employ a low-cost DIY adaptor to digitally adjust the photographic lens instead of the mechanical stage to perform axial position adjustment, and acquire the in-focus image under brightfield illumination. To ensure the calculation speed and image quality, we build a network model based on a ‘light weight’ backbone network architecture-MobileNetV3. Since the color-multiplexed coherent illuminated images contain abundant information about the defocus orientation, the proposed method enables high performance of autofocusing. Experimental results show that the proposed method can accurately predict the defocus distance of various types of samples and has good generalization ability for new types of samples. In the case of using GPU, the processing time for autofocusing is less than 0.1 second for each field of view, indicating that our method can further speed up the acquisition of whole slide images.     

A disentangled generative model for disease decomposition in chest X-rays via normal image synthesis

The interpretation of medical images is a complex cognition procedure requiring cautious observation, precise understanding/parsing of the normal body anatomies, and combining knowledge of physiology and pathology. Interpreting chest X-ray (CXR) images is challenging since the 2D CXR images show the superimposition on internal organs/tissues with low resolution and poor boundaries. Unlike previous CXR computer-aided diagnosis works that focused on disease diagnosis/classification, we firstly propose a deep disentangled generative model (DGM) simultaneously generating abnormal disease residue maps and “radiorealistic” normal CXR images from an input abnormal CXR image. The intuition of our method is based on the assumption that disease regions usually superimpose upon or replace the pixels of normal tissues in an abnormal CXR. Thus, disease regions can be disentangled or decomposed from the abnormal CXR by comparing it with a generated patient-specific normal CXR. DGM consists of three encoder-decoder architecture branches: one for radiorealistic normal CXR image synthesis using adversarial learning, one for disease separation by generating a residue map to delineate the underlying abnormal region, and the other one for facilitating the training process and enhancing the model’s robustness on noisy data. A self-reconstruction loss is adopted in the first two branches to enforce the generated normal CXR image to preserve similar visual structures as the original CXR. We evaluated our model on a large-scale chest X-ray dataset. The results show that our model can generate disease residue/saliency maps (coherent with radiologist annotations) along with radiorealistic and patient specific normal CXR images. The disease residue/saliency map can be used by radiologists to improve the CXR reading efficiency in clinical practice. The synthesized normal CXR can be used for data augmentation and normal control of personalized longitudinal disease study. Furthermore, DGM quantitatively boosts the diagnosis performance on several important clinical applications, including normal/abnormal CXR classification, and lung opacity classification/detection.     

Digital photography: a primer for pathologists

The computer and the digital camera provide a unique means for improving hematology education, research, and patient service. High quality photographic images of gross specimens can be rapidly and conveniently acquired with a high-resolution digital camera, and specialized digital cameras have been developed for photomicroscopy. Digital cameras utilize charge-coupled devices (CCD) or Complementary Metal Oxide Semiconductor (CMOS) image sensors to measure light energy and additional circuitry to convert the measured information into a digital signal. Since digital cameras do not utilize photographic film, images are immediately available for incorporation into web sites or digital publications, printing, transfer to other individuals by email, or other applications. Several excellent digital still cameras are now available for less than 2,500 dollars that capture high quality images comprised of more than 6 megapixels. These images are essentially indistinguishable from conventional film images when viewed on a quality color monitor or printed on a quality color or black and white printer at sizes up to 11x14 inches. Several recent dedicated digital photomicroscopy cameras provide an ultrahigh quality image output of more than 12 megapixels and have low noise circuit designs permitting the direct capture of darkfield and fluorescence images.There are many applications of digital images of pathologic specimens. Since pathology is a visual science, the inclusion of quality digital images into lectures, teaching handouts, and electronic documents is essential. A few institutions have gone beyond the basic application of digital images to developing large electronic hematology atlases, animated, audio-enhanced learning experiences, multidisciplinary Internet conferences, and other innovative applications. Digital images of single microscopic fields (single frame images) are the most widely utilized in hematology education at this time, but single images of many adjacent microscopic fields can be stitched together to prepare "zoomable" panoramas that encompass a large part of a microscope slide and closely simulate observation through a real microscope. With further advances in computer speed and Internet streaming technology, the virtual microscope could easily replace the real microscope in pathology education. Later in this decade, interactive immersive computer experiences may completely revolutionize hematology education and make the conventional lecture and laboratory format obsolete. Patient care is enhanced by the transmission of digital images to other individuals for consultation and education, and by the inclusion of these images in patient care documents. In research laboratories, digital cameras are widely used to document experimental results and to obtain experimental data.     

Cultural adaptation and validating a Japanese version of the readiness for interprofessional learning scale (RIPLS)

Readiness for interprofessional education (IPE) can be an important factor to evaluate because of the influences of attitudes toward the outcomes of interprofessional learning activities. However, a dearth of Japanese evaluation tools hinders its evaluation. The readiness for interprofessional learning scale (RIPLS) was selected, because it has been validated in different countries and its items reflected our local situation best. This research aimed to develop and validate a Japanese version of the original 19-item RIPLS. We developed a Japanese RIPLS employing forward/backward translation. Reliability of the Japanese version was studied using classical test theory and structural equation modeling to construct a model to inform curriculum development. We obtained a 0.74 Cronbach's α, which indicates adequacy. Subscales of “interprofessional education opportunities” (α = 0.90) and “uniqueness of profession” (α = 0.60) have relatively little weight compared to “teamwork and collaboration” (α = 0.92). A one-way structure suggests that readiness for interprofessional learning starts with “teamwork & collaboration” followed by changes in “learning opportunities” and subsequently “uniqueness of profession” (root mean square error of approximation = 0.06, comparative fit index = 0.93). This Japanese RIPLS can be used in undergraduate health sciences students with appropriate caution. Further development of the subscales and a client-centered subscale would be beneficial to fully achieve its potential. The need for further research into its reliability and validity is identified. Recommendations are provided for cross-cultural adaptation and for establishing validity across different contexts.     

Risk Assessment of Self-Injurious Behavior and Suicide Presentation in the Emergency Department: An Integrative Review

IntroductionGlobally, there is a lack of clarity regarding the best practice to distinguish patients at the highest risk of suicide. This review explores the use of risk assessment tools in emergency departments to identify patients at high risk of repeat self-harm, suicide attempts, or death by suicide.MethodsThe review question (“Does the use of risk assessment tools in emergency departments identify patients at high risk of repeat self-harm, suicide attempts, or death by suicide?”) focused on exposure and outcome. Studies of any design were included. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines were used. Study characteristics and concepts were extracted, compared, and verified. An integrative approach was used for reporting through narrative synthesis.ResultsNine studies were identified for inclusion. Two risk assessment tools were found to have good predictive ability for suicide ideation and self-harm. Three had modest prediction of patient disposition, but in one study, the clinical impression of nurses had higher predictive ability. One tool showed modest predictive ability for patients requiring admission.DiscussionThis review found no strong evidence to indicate that any particular risk tool has a superior predictive ability to identify repeat self-harm, suicide attempts, or death by suicide. Best practice lacks clarity to determine patients at highest risk of suicide, but the use of risk assessment tools has been recommended. Nevertheless, such tools should not be used in isolation from clinical judgment and experience to evaluate patients at risk. Education and training to augment risk assessment within the emergency department are recommended.