Subarachnoid versus nonsubarachnoid traumatic brain injuries: The impact of decision-making on patient safety

Abstract Accumulating evidence demonstrates the impact of bias that reflects social inequality on the performance of machine learning (ML) models in health care. Given their intended placement within healthcare decision making more broadly, ML tools require attention to adequately quantify the impact of bias and reduce its potential to exacerbate inequalities. We suggest that taking a patient safety and quality improvement approach to bias can support the quantification of bias-related effects on ML. Drawing from the ethical principles underpinning these approaches, we argue that patient safety and quality improvement lenses support the quantification of relevant performance metrics, in order to minimize harm while promoting accountability, justice, and transparency. We identify specific methods for operationalizing these principles with the goal of attending to bias to support better decision making in light of controllable and uncontrollable factors.

Download Full-text

Poster 10: Exploring the Impact of a Knowledge Transfer and Exchange Tools With Clinicians Working With Teenagers Who Sustain Mild Traumatic Brain Injuries

Archives of Physical Medicine and Rehabilitation ◽

10.1016/j.apmr.2008.08.113 ◽

2008 ◽

Vol 89 (10) ◽

pp. e31

Author(s):

Isabelle Gagnon ◽

Bonnie Swaine

Keyword(s):

Knowledge Transfer ◽

Brain Injuries ◽

Traumatic Brain Injuries ◽

Knowledge Transfer And Exchange ◽

Mild Traumatic Brain Injuries ◽

The Impact

Download Full-text

Mild traumatic brain injuries: the impact of early intervention on late sequelae. A randomized controlled trial

Acta Neurochirurgica ◽

10.1007/s00701-006-1082-0 ◽

2007 ◽

Vol 149 (2) ◽

pp. 151-160 ◽

Cited By ~ 68

Author(s):

E. Elgmark Andersson ◽

I. Emanuelson ◽

R. Björklund ◽

D. A. Stålhammar

Keyword(s):

Randomized Controlled Trial ◽

Early Intervention ◽

Brain Injuries ◽

Controlled Trial ◽

Traumatic Brain Injuries ◽

Late Sequelae ◽

Randomized Controlled ◽

Mild Traumatic Brain Injuries ◽

The Impact

Download Full-text

Evaluating simplified web interfaces of risk models for clinical use (Preprint)

10.2196/preprints.22110 ◽

2020 ◽

Author(s):

Louis Beaubien ◽

Colin Conrad ◽

Janet Music ◽

Sandra Toze

Keyword(s):

Decision Making ◽

Patient Safety ◽

Clinical Setting ◽

Clinical Decision Making ◽

Information Overload ◽

Clinical Decision ◽

Intention To Use ◽

Regression Equations ◽

Risk Models ◽

The Impact

BACKGROUND Information overload negatively affects clinicians’ decision effectiveness and ultimately impacts patient safety. Clinicians who are tasked with assessing patient outcomes are often required to use complex outcome and risk models in a spreadsheet format. In response to this challenge, we developed a mobile web model which simplifies the information presented to clinicians and expedites the decision process. However, new electronic technologies often face barriers to adoption which inhibits their use in clinical settings. OBJECTIVE This pilot study investigated sociotechnical factors that affect intention to use a simplified WebModel to support clinical decision making. We investigated factors from the UTAUT2 model, which are known to affect technology adoption. METHODS A WebModel is developed based on the results from a previously published work, to allow users to work with regression equations and their predictions to evaluate the impact of various characteristics or treatments on key outcomes (e.g. survival time) for chronic obstructive pulmonary disease (COPD). To test the WebModel a questionnaire was designed to probe the efficacy of the WebModel and to assess the usability and usefulness of the system. The questionnaire was administered online, and data from 550 clinical users who had access to the WebModel was captured. SPSS and R were used for statistical analysis. RESULTS The regression model developed from UTAUT2 constructs was found to be a fit, with five variables found to significantly predicts behavioural intention to sue the WebModel: Performance Expectancy, Effort Expectancy, Facilitating Conditions, Hedonic Motivation and Habit. Social Influence was not a significant factor, while Value had a significant negative influence on intention to use the WebModel. Multiple influences were found to impact the positive response to the system, many of which related to the efficiency of the interface to provide clear information. Given that this was a pilot test, and that the system was not used in a clinical setting factors related to actual workflow, or patient safety could not be examined. CONCLUSIONS This study proves that the concept of a simplified WebModel could be effective and efficient in reducing information overload in complex clinical decision making. Further study to test this in a clinical setting, and gather qualitative data from users regarding the value of the tool in practice is recommended.

Download Full-text

Mild Traumatic Brain Injury: Lessons Learned from Clinical, Sports, and Combat Concussions

Rehabilitation Research and Practice ◽

10.1155/2012/371970 ◽

2012 ◽

Vol 2012 ◽

pp. 1-5 ◽

Cited By ~ 6

Author(s):

Judy C. Kelly ◽

Efland H. Amerson ◽

Jeffrey T. Barth

Keyword(s):

Brain Injuries ◽

Behavioral Therapy ◽

Traumatic Brain Injuries ◽

Lessons Learned ◽

Return To Play ◽

Concussion Management ◽

Tremendous Amount ◽

Return To Duty ◽

The Military ◽

The Impact

Over the past forty years, a tremendous amount of information has been gained on the mechanisms and consequences of mild traumatic brain injuries. Using sports as a laboratory to study this phenomenon, a natural recovery curve emerged, along with standards for managing concussions and returning athletes back to play. Although advances have been made in this area, investigation into recovery and return to play continues. With the increase in combat-related traumatic brain injuries in the military setting, lessons learned from sports concussion research are being applied by the Department of Defense to the assessment of blast concussions and return to duty decision making. Concussion management and treatment for military personnel can be complicated by additional combat related stressors not present in the civilian environment. Cognitive behavioral therapy is one of the interventions that has been successful in treating symptoms of postconcussion syndrome. While we are beginning to have an understanding of the impact of multiple concussions and subconcussive blows in the sports world, much is still unknown about the impact of multiple blast injuries.

Download Full-text