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 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.

scholarly journals Deep Learning: A New Horizon for Personalized Treatment of Depression?

2018 ◽  
Vol 16 (1) ◽  
Author(s):  
David Benrimoh ◽  
Robert Fratila ◽  
Sonia Israel ◽  
Kelly Perlman
Keyword(s):  
Deep Learning ◽  
Decision Aid ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Personalized Care ◽  
Treatment Of Depression ◽  
Number Of Patients ◽  
Treatment Plans ◽  
Patient Responses ◽  
Deep Learning Model

Globally, depression affects 300 million people and is projected be the leading cause of disability by 2030. While different patients are known to benefit from different therapies, there is no principled way for clinicians to predict individual patient responses or side effect profiles. A form of machine learning based on artificial neural networks, deep learning, might be useful for generating a predictive model that could aid in clinical decision making. Such a model’s primary outcomes would be to help clinicians select the most effective treatment plans and mitigate adverse side effects, allowing doctors to provide greater personalized care to a larger number of patients. In this commentary, we discuss the need for personalization of depression treatment and how a deep learning model might be used to construct a clinical decision aid.

scholarly journals Learning the Preferences of Physicians for the Organization of Result Lists of Medical Evidence Articles

2014 ◽  
Vol 53 (05) ◽  
pp. 344-356 ◽  
Author(s):  
S. Wilk ◽  
W. Michalowski ◽  
R. Slowinski ◽  
R. Thomas ◽  
M. Kadzinski ◽  
...  
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Medical Knowledge ◽  
Clinical Decision ◽  
Cochrane Library ◽  
Value Functions ◽  
List Position ◽  
Relevant Article ◽  
Information Retrieval Systems ◽  
The Cochrane Library

SummaryBackground: Online medical knowledge repositories such as MEDLINE and The Cochrane Library are increasingly used by physicians to retrieve articles to aid with clinical decision making. The prevailing approach for organizing retrieved articles is in the form of a rank-ordered list, with the assumption that the higher an article is presented on a list, the more relevant it is.Objectives: Despite this common list-based organization, it is seldom studied how physicians perceive the association between the relevance of articles and the order in which articles are presented. In this paper we describe a case study that captured physician preferences for 3-element lists of medical articles in order to learn how to organize medical knowledge for decision-making.Methods: Comprehensive relevance evaluations were developed to represent 3-element lists of hypothetical articles that may be retrieved from an online medical knowledge source such as MEDLINE or The Cochrane Library. Comprehensive relevance evalua tions asses not only an article’s relevance for a query, but also whether it has been placed on the correct list position. In other words an article may be relevant and correctly placed on a result list (e.g. the most relevant article appears first in the result list), an article may be relevant for a query but placed on an incorrect list position (e.g. the most relevant article appears second in a result list), or an article may be irrelevant for a query yet still appear in the result list. The relevance evaluations were presented to six senior physi cians who were asked to express their preferences for an article’s relevance and its position on a list by pairwise comparisons representing different combinations of 3-element lists. The elicited preferences were assessed using a novel GRIP (Generalized Regression with Intensities of Preference) method and represented as an additive value function. Value functions were derived for individual physicians as well as the group of physicians.Results: The results show that physicians assign significant value to the 1st position on a list and they expect that the most relevant article is presented first. Whilst physicians still prefer obtaining a correctly placed article on position 2, they are also quite satisfied with misplaced relevant article. Low consideration of the 3rd position was uniformly confirmed.Conclusions: Our findings confirm the importance of placing the most relevant article on the 1st position on a list and the importance paid to position on a list significantly diminishes after the 2nd position. The derived value functions may be used by developers of clinical decision support applications to decide how best to organize medical knowledge for decision making and to create personalized evaluation measures that can augment typical measures used to evaluate information retrieval systems.

Mining Medical Data to Develop Clinical Decision Making Tools in Hemodialysis

2012 ◽  
Author(s):  
J. Ion Titapiccolo ◽  
M. Ferrario ◽  
S. Cerutti ◽  
M.G. Signorini ◽  
C. Barbieri ◽  
...  
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Medical Data

scholarly journals Health Information Resources Accessibility as Predictors for Clinical Decision Making among Medical Doctors in Obafemi Awolowo University Ile-Ife, Nigeria

2021 ◽  
Vol 11 (4) ◽  
pp. 81-91
Author(s):  
Moyosore O. Adegboye ◽  
Samuel Adeyoyin
Keyword(s):  
Decision Making ◽  
Focus Group ◽  
Health Information ◽  
Clinical Decision Making ◽  
Group Discussion ◽  
Clinical Decision ◽  
Information Resources ◽  
Medical Doctors ◽  
Core Skills ◽  
Health Information Resources

The study evaluates health information resources as predictors for clinical decision- making among medical doctors in Obafemi Awolowo University Teaching Hospital Ile-Ife. A survey research design was adopted by the study and random sampling technique was used to select 265 medical doctors from a population of 822. Primary data were obtained on socioeconomic characteristics of the respondents, level of accessibility, frequency and various core skills of health information resources using a structured questionnaire and focus group discussion (FGD). Data were analyzed using frequency counts, percentage and mean. Results revealed that 59.8% of the respondents were male while 51.1% were female. Findings, however, showed that pattern recognition from experience ( &#x0304 = 3.32), critical thinking without emotion (&#x0304 = 3.16), hypothesis updating (&#x0304 = 3.607) and perception based confidence (&#x0304 = 2.97) were the core skills used by the medical doctors in clinical decision making. The focus group discussion emphasized that medical doctors should possess critical thinking without emotions and good time pressure balance in order to make accurate clinical decisions. The study concludes that medical doctors have quality access to health information resources to make clinical decisions. The study, therefore recommended regular trainings of medical personnel on health information resources to ensure accurate and sound decision making in order to enhance optimal performance. Keywords Information sharing, Job satisfaction, Librarians, Private Universities

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 Cost effective use of free to use apps (FAN) in neurosurgery in developing countries: from clinical decision making to educational courses, strengthening the health care delivery

2016 ◽  
Vol 18 (3) ◽  
pp. 36 ◽  
Author(s):  
Amit Thapa ◽  
Bidur KC ◽  
Bikram Shakya
Keyword(s):  
Decision Making ◽  
Developing Countries ◽  
Data Storage ◽  
Clinical Decision Making ◽  
Care Delivery ◽  
Medical Knowledge ◽  
Cost Effective ◽  
Clinical Decision ◽  
Good Communication ◽  
Related Data

Introduction and Objective: Financial limitations and scarcity of technological knowledge is a major hurdle to good communication platform, data storage and dissemination of medical knowledge in developing countries. Out of necessity we used free to use apps in our practice. We studied the applicability and cost effective aspect of a systematic use of these apps in neurosurgery.Materials and Methods: We designed Free to use apps in neurosurgery (FAN) module in 4 phases at KMCTH over the last 3 years. We used free apps like viber, dropbox, skype and vlc media player on 3G and wifi. Users were trained in ethics and measures to ensure confidentiality and privacy of patient related data. Endpoints studied were feasibility, reliability, cost effectiveness and overall satisfaction of the users.Results: In the FAN module, viber app was used to send pictures of digital imagings (DI) using smartphones within 30 minutes enabling quick decision by the consultants. Dropbox not only helped store images but also helped quick verification of discharge summaries as early as 15 minutes increasing overall efficiency. With Skype, consultants could be contacted even when they were abroad and using FAN they remain updated of their patients. Using skype and vlc, 2 operative live workshops from abroad was transmitted live with good visual and audio reception allowing question answer sessions with the faculties. Users’ satisfaction was more than 90%.Conclusion: FAN module helped in quick reliable decision making, allowing for instantaneous communication and storing data and exchange of knowledge across countries.

Sign in / Sign up

Export Citation Format

Share Document