scholarly journals Text Classification in Clinical Practice Guidelines Using Machine-Learning Assisted Pattern-Based Approach

2021 ◽  
Vol 11 (8) ◽  
pp. 3296
Author(s):  
Musarrat Hussain ◽  
Jamil Hussain ◽  
Taqdir Ali ◽  
Syed Imran Ali ◽  
Hafiz Syed Muhammad Bilal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Clinical Practice ◽  
Clinical Practice Guidelines ◽  
Practice Guidelines ◽  
Machine Learning Algorithms ◽  
Nominal Group ◽  
Specific Information ◽  
Matching Techniques ◽  
Disease Specific

Clinical Practice Guidelines (CPGs) aim to optimize patient care by assisting physicians during the decision-making process. However, guideline adherence is highly affected by its unstructured format and aggregation of background information with disease-specific information. The objective of our study is to extract disease-specific information from CPG for enhancing its adherence ratio. In this research, we propose a semi-automatic mechanism for extracting disease-specific information from CPGs using pattern-matching techniques. We apply supervised and unsupervised machine-learning algorithms on CPG to extract a list of salient terms contributing to distinguishing recommendation sentences (RS) from non-recommendation sentences (NRS). Simultaneously, a group of experts also analyzes the same CPG and extract the initial patterns “Heuristic Patterns” using a group decision-making method, nominal group technique (NGT). We provide the list of salient terms to the experts and ask them to refine their extracted patterns. The experts refine patterns considering the provided salient terms. The extracted heuristic patterns depend on specific terms and suffer from the specialization problem due to synonymy and polysemy. Therefore, we generalize the heuristic patterns to part-of-speech (POS) patterns and unified medical language system (UMLS) patterns, which make the proposed method generalize for all types of CPGs. We evaluated the initial extracted patterns on asthma, rhinosinusitis, and hypertension guidelines with the accuracy of 76.92%, 84.63%, and 89.16%, respectively. The accuracy increased to 78.89%, 85.32%, and 92.07% with refined machine-learning assistive patterns, respectively. Our system assists physicians by locating disease-specific information in the CPGs, which enhances the physicians’ performance and reduces CPG processing time. Additionally, it is beneficial in CPGs content annotation.

Frailty Status and Cognitive Function Should Guide Prescribing in Long-term Care Facilities

2021 ◽  
Vol 36 (10) ◽  
pp. 469-473
Author(s):  
Shin J. Liau ◽  
J. Simon Bell
Keyword(s):  
Clinical Practice ◽  
Clinical Practice Guidelines ◽  
Practice Guidelines ◽  
Long Term Care ◽  
Adverse Drug Events ◽  
Cognitive Status ◽  
Term Care ◽  
Care Facilities ◽  
Disease Specific

Frailty, dementia and complex multimorbidity are highly prevalent among residents of long-term care facilities (LTCFs). Prescribing for residents of LTCFs is often informed by disease-specific clinical practice guidelines based on research conducted among younger and more robust adults. However, frailty and cognitive impairment may modify medication benefits and risks. Residents with frailty and advanced dementia may be at increased susceptibility to adverse drug events (ADEs) and often have a lower likelihood of achieving long-term therapeutic benefit from chronic preventative medications. For this reason, there is a strong rationale for deprescribing, particularlyamong residents with high medication burdens, swallowing difficulties or limited dexterity. Conversely, frailty and dementia have also been associated with under-prescribing of clinically indicated medications. Unnecessarily withholding treatment based on assumed risk may deprive vulnerable population groups from receiving evidence-based care. There is a need for specific evidence regarding medication benefits and risks in LTCF residents with frailty and dementia. Observational studies conducted using routinely collected health data may complement evidence from randomized controlled trials that often exclude people living with dementia, frailty and in LTCFs. Balancing over- and under-prescribing requires consideration of each resident’s frailty and cognitive status, therapeutic goals, time-to-benefit, potential ADEs, and individual values or preferences. Incorporating frailty screening into medication review may also provide better alignment of medication regimens to changing goals of care. Timely identification of frail residents as part of treatment decision-making may assist with targeting interventions to minimize and monitor for ADEs. Shifting away from rigid application of conventional disease-specific clinical practice guidelines may provide an individualized and more holistic assessment of medication benefits and risks in the LTCF setting.

scholarly journals Early Mobilization After Stroke: Do Clinical Practice Guidelines Support Clinicians' Decision-Making?

2021 ◽  
Vol 12 ◽  
Author(s):  
Venesha Rethnam ◽  
Kathryn S. Hayward ◽  
Julie Bernhardt ◽  
Leonid Churilov
Keyword(s):  
Decision Making ◽  
Clinical Practice ◽  
Clinical Practice Guidelines ◽  
Practice Guidelines ◽  
Early Mobilization ◽  
Cross Sectional Study ◽  
Structured Interviews ◽  
Cross Sectional ◽  
Delivery Of Care ◽  
Individual Patient Level

Importance: Early mobilization, out-of-bed activity, is a component of acute stroke unit care; however, stroke patient heterogeneity requires complex decision-making. Clinically credible and applicable CPGs are needed to support and optimize the delivery of care. In this study, we are specifically exploring the role of clinical practice guidelines to support individual patient-level decision-making by stroke clinicians about early mobilization post-stroke.Methods: Our study uses a novel, two-pronged approach. (1) A review of CPGs containing recommendations for early mobilization practices published after 2015 was appraised using purposely selected items from the Appraisal of Guidelines Research and Evaluation–Recommendations Excellence (AGREE-REX) tool relevant to decision-making for clinicians. (2) A cross-sectional study involving semi-structured interviews with Australian expert stroke clinicians representing content experts and CPG target users. Every CPG was independently assessed against the AGREE-REX standard by two reviewers. Expert stroke clinicians, invited via email, were recruited between June 2019 to March 2020.The main outcomes from the review was the proportion of criteria addressed for each AGREE-REX item by individual and all CPG(s). The main cross-sectional outcomes were the distributions of stroke clinicians' responses about the utility of CPGs, specific areas of uncertainty in early mobilization decision-making, and suggested parameters for inclusion in future early mobilization CPGs.Results: In 18 identified CPGs, many did not adequately address the “Evidence” and “Applicability to Patients” AGREE-REX items. Out of 30 expert stroke clinicians (11 physicians [37%], 11 physiotherapists [37%], 8 nurses [26%]; median [IQR] years of experience, 14 [10–25]), 47% found current CPGs “too broad or vague,” while 40% rely on individual clinical judgement and interpretation of the evidence to select an evidence-based choice of action. The areas of uncertainty in decision-making revealed four key suggestions: (1) more granular descriptions of patient and stroke characteristics for appropriate tailoring of decisions, (2) clear statements about when clinical flexibility is appropriate, (3) detailed description of the intervention dose, and (4) physical assessment criteria including safety parameters.Conclusions: The lack of specificity, clinical applicability, and adaptability of current CPGs to effectively respond to the heterogeneous clinical stroke context has provided a clear direction for improvement.

scholarly journals Shared Decision Making Does Not Influence Physicians against Clinical Practice Guidelines

PLoS ONE ◽  
2013 ◽  
Vol 8 (4) ◽  
pp. e62537 ◽  
Author(s):  
Mireille Guerrier ◽  
France Légaré ◽  
Stéphane Turcotte ◽  
Michel Labrecque ◽  
Louis-Paul Rivest
Keyword(s):  
Decision Making ◽  
Clinical Practice ◽  
Shared Decision Making ◽  
Clinical Practice Guidelines ◽  
Practice Guidelines ◽  
Shared Decision

CAM Recommended by Standard Guidelines for Chronic Illnesses

2019 ◽  
pp. 38-60
Author(s):  
Annalisa Casarin
Keyword(s):  
Decision Making ◽  
Clinical Practice ◽  
Alternative Medicine ◽  
Chronic Diseases ◽  
Clinical Practice Guidelines ◽  
Practice Guidelines ◽  
Chronic Illnesses ◽  
Current Clinical Practice ◽  
Definition Of ◽  
Decision Making Tool

This chapter will focus on guidelines for clinical practice that mention a range of Complementary and Alternative Medicine (CAM) techniques. After exploring the definition and grading of clinical practice guidelines as a decision-making tool, the CAM methods included in the review will be described. A definition of chronic diseases will be provided and an overview of the current clinical practice guidelines on a number of prevalent conditions will be presented. Guidelines released by several international regulatory organisations will be compared in order to detect which CAM techniques have been or not been recommended for chronic illnesses in different countries. The challenges in implementing and appraising guidelines will be finally discussed.

Sign in / Sign up

Export Citation Format

Share Document