scholarly journals Deep learning in cancer pathology: a new generation of clinical biomarkers

2020 ◽  
Author(s):  
Amelie Echle ◽  
Niklas Timon Rindtorff ◽  
Titus Josef Brinker ◽  
Tom Luedde ◽  
Alexander Thomas Pearson ◽  
...  
Keyword(s):  
Decision Making ◽  
Image Analysis ◽  
Deep Learning ◽  
Clinical Decision Making ◽  
External Validation ◽  
Therapy Response ◽  
Clinical Decision ◽  
Tumour Tissue ◽  
Molecular Features ◽  
Clinical Biomarkers

AbstractClinical workflows in oncology rely on predictive and prognostic molecular biomarkers. However, the growing number of these complex biomarkers tends to increase the cost and time for decision-making in routine daily oncology practice; furthermore, biomarkers often require tumour tissue on top of routine diagnostic material. Nevertheless, routinely available tumour tissue contains an abundance of clinically relevant information that is currently not fully exploited. Advances in deep learning (DL), an artificial intelligence (AI) technology, have enabled the extraction of previously hidden information directly from routine histology images of cancer, providing potentially clinically useful information. Here, we outline emerging concepts of how DL can extract biomarkers directly from histology images and summarise studies of basic and advanced image analysis for cancer histology. Basic image analysis tasks include detection, grading and subtyping of tumour tissue in histology images; they are aimed at automating pathology workflows and consequently do not immediately translate into clinical decisions. Exceeding such basic approaches, DL has also been used for advanced image analysis tasks, which have the potential of directly affecting clinical decision-making processes. These advanced approaches include inference of molecular features, prediction of survival and end-to-end prediction of therapy response. Predictions made by such DL systems could simplify and enrich clinical decision-making, but require rigorous external validation in clinical settings.

scholarly journals Automated Classification of Significant Prostate Cancer on MRI: A Systematic Review on the Performance of Machine Learning Applications

Cancers ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1606
Author(s):  
Jose M. Castillo T. ◽  
Muhammad Arif ◽  
Wiro J. Niessen ◽  
Ivo G. Schoots ◽  
Jifke F. Veenland
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Deep Learning ◽  
Clinical Decision Making ◽  
External Validation ◽  
Clinical Decision ◽  
Interquartile Range ◽  
Added Value ◽  
Receiver Operating Curve ◽  
Learning Approaches

Significant prostate carcinoma (sPCa) classification based on MRI using radiomics or deep learning approaches has gained much interest, due to the potential application in assisting in clinical decision-making. Objective: To systematically review the literature (i) to determine which algorithms are most frequently used for sPCa classification, (ii) to investigate whether there exists a relation between the performance and the method or the MRI sequences used, (iii) to assess what study design factors affect the performance on sPCa classification, and (iv) to research whether performance had been evaluated in a clinical setting Methods: The databases Embase and Ovid MEDLINE were searched for studies describing machine learning or deep learning classification methods discriminating between significant and nonsignificant PCa on multiparametric MRI that performed a valid validation procedure. Quality was assessed by the modified radiomics quality score. We computed the median area under the receiver operating curve (AUC) from overall methods and the interquartile range. Results: From 2846 potentially relevant publications, 27 were included. The most frequent algorithms used in the literature for PCa classification are logistic regression (22%) and convolutional neural networks (CNNs) (22%). The median AUC was 0.79 (interquartile range: 0.77–0.87). No significant effect of number of included patients, image sequences, or reference standard on the reported performance was found. Three studies described an external validation and none of the papers described a validation in a prospective clinical trial. Conclusions: To unlock the promising potential of machine and deep learning approaches, validation studies and clinical prospective studies should be performed with an established protocol to assess the added value in decision-making.

scholarly journals Explaining deep neural networks for knowledge discovery in electrocardiogram analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Steven A. Hicks ◽  
Jonas L. Isaksen ◽  
Vajira Thambawita ◽  
Jonas Ghouse ◽  
Gustav Ahlberg ◽  
...  
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Clinical Decision Making ◽  
Medical Knowledge ◽  
Clinical Decision ◽  
Medical Data ◽  
Medical Doctors ◽  
Medical Tests ◽  
Deep Learning Model

AbstractDeep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.

scholarly journals Clinical decision-making in older adults following emergency admission to hospital. Derivation and validation of a risk stratification score: OPERA

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248477
Author(s):  
Khushal Arjan ◽  
Lui G. Forni ◽  
Richard M. Venn ◽  
David Hunt ◽  
Luke Eliot Hodgson
Keyword(s):  
Older Adults ◽  
Decision Making ◽  
Risk Stratification ◽  
Hospital Mortality ◽  
Hospital Stay ◽  
Risk Score ◽  
Clinical Decision Making ◽  
External Validation ◽  
Clinical Decision ◽  
Early Warning Score

Objectives of the study Demographic changes alongside medical advances have resulted in older adults accounting for an increasing proportion of emergency hospital admissions. Current measures of illness severity, limited to physiological parameters, have shortcomings in this cohort, partly due to patient complexity. This study aimed to derive and validate a risk score for acutely unwell older adults which may enhance risk stratification and support clinical decision-making. Methods Data was collected from emergency admissions in patients ≥65 years from two UK general hospitals (April 2017- April 2018). Variables underwent regression analysis for in-hospital mortality and independent predictors were used to create a risk score. Performance was assessed on external validation. Secondary outcomes included seven-day mortality and extended hospital stay. Results Derivation (n = 8,974) and validation (n = 8,391) cohorts were analysed. The model included the National Early Warning Score 2 (NEWS2), clinical frailty scale (CFS), acute kidney injury, age, sex, and Malnutrition Universal Screening Tool. For mortality, area under the curve for the model was 0.79 (95% CI 0.78–0.80), superior to NEWS2 0.65 (0.62–0.67) and CFS 0.76 (0.74–0.77) (P<0.0001). Risk groups predicted prolonged hospital stay: the highest risk group had an odds ratio of 9.7 (5.8–16.1) to stay >30 days. Conclusions Our simple validated model (Older Persons’ Emergency Risk Assessment [OPERA] score) predicts in-hospital mortality and prolonged length of stay and could be easily integrated into electronic hospital systems, enabling automatic digital generation of risk stratification within hours of admission. Future studies may validate the OPERA score in external populations and consider an impact analysis.

Deep learning in patient management and clinical decision making

2021 ◽  
pp. 115-140
Author(s):  
D. A. Janeera ◽  
G. Jims John Wesley ◽  
P. Rajalakshmy ◽  
S. Shalini Packiam Kamala ◽  
P. Subha Hency Jose ◽  
...  
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Patient Management ◽  
Clinical Decision Making ◽  
Clinical Decision

scholarly journals Automatic Identification of High Impact Relevant Articles to Support Clinical Decision Making Using Attention-Based Deep Learning

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1364
Author(s):  
Beomjoo Park ◽  
Muhammad Afzal ◽  
Jamil Hussain ◽  
Asim Abbas ◽  
Sungyoung Lee
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Precision Medicine ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
High Impact ◽  
Biomedical Literature ◽  
Classification Model ◽  
Evidence Based ◽  
Proposed Model

To support evidence-based precision medicine and clinical decision-making, we need to identify accurate, appropriate, and clinically relevant studies from voluminous biomedical literature. To address the issue of accurate identification of high impact relevant articles, we propose a novel approach of attention-based deep learning for finding and ranking relevant studies against a topic of interest. For learning the proposed model, we collect data consisting of 240,324 clinical articles from the 2018 Precision Medicine track in Text REtrieval Conference (TREC) to identify and rank relevant documents matched with the user query. We built a BERT (Bidirectional Encoder Representations from Transformers) based classification model to classify high and low impact articles. We contextualized word embedding to create vectors of the documents, and user queries combined with genetic information to find contextual similarity for determining the relevancy score to rank the articles. We compare our proposed model results with existing approaches and obtain a higher accuracy of 95.44% as compared to 94.57% (the next best performer) and get a higher precision by about 14% at P@5 (precision at 5) and about 12% at P@10 (precision at 10). The contextually viable and competitive outcomes of the proposed model confirm the suitability of our proposed model for use in domains like evidence-based precision medicine.

scholarly journals Calibration: the Achilles heel of predictive analytics

BMC Medicine ◽  
2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Ben Van Calster ◽  
◽  
David J. McLernon ◽  
Maarten van Smeden ◽  
Laure Wynants ◽  
...  
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Prediction Models ◽  
Predictive Analytics ◽  
External Validation ◽  
Clinical Decision ◽  
Machine Learning Algorithms ◽  
Model Complexity ◽  
Patient Counseling ◽  
Flexible Machine

Abstract Background The assessment of calibration performance of risk prediction models based on regression or more flexible machine learning algorithms receives little attention. Main text Herein, we argue that this needs to change immediately because poorly calibrated algorithms can be misleading and potentially harmful for clinical decision-making. We summarize how to avoid poor calibration at algorithm development and how to assess calibration at algorithm validation, emphasizing balance between model complexity and the available sample size. At external validation, calibration curves require sufficiently large samples. Algorithm updating should be considered for appropriate support of clinical practice. Conclusion Efforts are required to avoid poor calibration when developing prediction models, to evaluate calibration when validating models, and to update models when indicated. The ultimate aim is to optimize the utility of predictive analytics for shared decision-making and patient counseling.

scholarly journals Explaining Deep Neural Networks for Knowledge Discovery in Electrocardiogram Analysis

2021 ◽  
Author(s):  
Steven Hicks ◽  
Jonas Isaksen ◽  
Vajira Thambawita ◽  
Jonas Ghouse ◽  
Gustav Ahlberg ◽  
...  
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Clinical Decision Making ◽  
Medical Knowledge ◽  
Clinical Decision ◽  
Medical Doctors ◽  
Medical Tests ◽  
Deep Learning Network ◽  
Deep Learning Model

Deep learning-based tools may annotate and interpret medical tests more quickly, consistently, and accurately than medical doctors. However, as medical doctors remain ultimately responsible for clinical decision-making, any deep learning-based prediction must necessarily be accompanied by an explanation that can be interpreted by a human. In this study, we present an approach, called ECGradCAM, which uses attention maps to explain the reasoning behind AI decision-making and how interpreting these explanations can be used to discover new medical knowledge. Attention maps are visualizations of how a deep learning network makes, which may be used in the clinic to aid diagnosis, and in research to identify novel features and characteristics of diagnostic medical tests. Here, we showcase the use of ECGradCAM attention maps using a novel deep learning model capable of measuring both amplitudes and intervals in 12-lead electrocardiograms.

Sign in / Sign up

Export Citation Format

Share Document