Close

Presentation

Developing an Evidence-Based Clinical Decision-Support System to Enhance Prosthetic Prescription
Event Type
Oral Presentations
TimeThursday, April 151:10pm - 1:30pm EDT
LocationEducation and Simulation
DescriptionOver 40 million amputees reside in Low-Income Countries (LIC), and 95% of these amputees have limited or no access to appropriate prostheses and rehabilitation services. A significant contributor to this problem is the lack of prosthetic schools and training facilities across LIC. There are only 24 prosthetic and orthotic schools across all LIC, graduating approximately 400 personnel each year. The majority of these schools exist in a minority of LIC, and about 75% of the LICs have no prosthetic/orthotic training programs (World Health Organization, 2005). With the rapid increase in diabetes-related amputations in LIC, there is an urgent need for prosthetists to provide advanced amputee care to accommodate the increased comorbidities that often accompany a diabetic population. But, due to the scarcity of prosthetic schools and trained amputee care professionals in LICs, realizing this vision remains a challenge (Marino et al., 2015). Therefore, we must develop systems that can support healthcare workers and supplement training and education gaps. We propose that an evidence-based decision-making system designed to complement prosthetic care could improve amputees' overall quality-of-life via improved prosthetic prescriptions.

Evidence-based Medicine (EBM) is defined as “the ability to track down, critically appraise (for its validity and usefulness), and incorporate a rapidly growing body of evidence into one’s clinical practice” (Sackett & Rosenberg, 1995). Being an integration of relevant scientific evidence, clinical judgment, and patients’ values and preferences, EBM enhances the clinical outcomes of patients by assisting clinicians with their decisions (Masic et al., 2008). EBM is used to develop healthcare-based decision-support systems, as it considers past literature (relevant scientific evidence) and current techniques employed by the clinicians (clinical judgment) to improve patient outcomes (patients’ values and preferences) (Thompson et al., 2004). In addition to advancing patient care, EBM improves healthcare's economic viability, as it reduces error in treatment planning and promotes safe healthcare environmental design (Zadeh et al., 2015). Hence, in the current work, we follow an EBM paradigm to develop a prosthetic prescription decision support tool. The objective of this proposed work is to integrate our past research on studying decision-making strategies of amputee care providers and develop an evidence-based clinical decision-support system to assist the clinicians during prosthetic prescription processes in real-time.

Rosenberg (Rosenberg & Donald, 1995) argued that EBM for clinical problem solving and decision-making can be achieved via four steps: 1) By formulating a clear clinical question based on a patient’s problem, 2) searching literature for relevant clinical articles, 3) evaluating the evidence for its validity and usefulness, and 4) implementing the findings in clinical practice. Based on this framework, three research phases were designed towards implementing an EBM decision-support tool for the prosthetic prescription. In Phase 1, an extensive literature review combined with natural language processing (topic modelling) and expert survey was conducted, and a decision tree was developed to outline the major factors affecting the decision-making processes of prosthetists (Saravanan et al., 2019). In Phase 2, the decision-making strategies employed by expert and novice prosthetists were captured and analyzed for case studies of varying complexities using hidden Markov modelling and qualitative analysis. Specifically, this phase focused on identifying the cognitive schema of experts and novices during decision-making processes for amputees with varying case complications to understand what gaps may exist due to experience and training (Saravanan et al., 2020; Walker et al., 2020). In Phase 3, a fundamental understanding of the effect of gait analysis on the decision-making strategies of prosthetists was studied by employing quantitative methods and qualitative analysis methods. By studying the interaction between gait analysis and decision-making of prosthetists, this phase established a groundwork for a portable gait analysis system that leverages both in-clinic observational gait analysis and quantitative evaluation in a traditional gait lab. Each phase of this research is designed to incorporate two of the three components of EBM (relevant scientific evidence, clinical judgment, and patients’ values and preferences) in an effort to develop an evidence-based decision support tool for the prosthetic prescription. This proposed decision-support tool can potentially be used for training novices and other clinicians in LIC, thus improving the quality of amputee care via improved prescription.

Our presentation will focus on various machine learning algorithms and qualitative research that can be used towards understanding the in-depth decision-making processes of amputee care providers. By analyzing the existing literature, capturing the decision-making strategies of expert and novice prosthetists, and studying the influence of gait analysis in prosthetic prescription, this proposed work lays the foundation for an evidence-based decision support tool that can be used for a prosthetic prescription. Pairing this decision support tool with a robust off-the-shelf portable gait system marks a transformational benefit to amputees and healthcare providers. The anticipated portable gait system would not only analyze amputee gait but would simulate patient gait under various conditions (i.e. varying prosthetic components, loading conditions, environments, etc.). This is particularly critical given the increasing global population of amputees and the lack of prosthetic care facilities to meet the needs of this growing population.

References:
Day, H. J. B. (1998). Amputee rehabilitation—Finding the niche. 22(2), 92–101. https://doi.org/10.3109/03093649809164469
Hagberg, K., & Brånemark, R. (2001). Consequences of non‐vascular trans‐femoral amputation: A survey of quality of life, prosthetic use and problems. Prosthetics and Orthotics International, 25(3), 186–194. https://doi.org/10.1080/03093640108726601
Marino, M., Pattni, S., Greenberg, M., Miller, A., Hocker, E., Ritter, S., & Mehta, K. (2015). Access to prosthetic devices in developing countries: Pathways and challenges. 2015 IEEE Global Humanitarian Technology Conference (GHTC), 45–51. https://doi.org/10.1109/GHTC.2015.7343953
Masic, I., Miokovic, M., & Muhamedagic, B. (2008). Evidence Based Medicine – New Approaches and Challenges. Acta Informatica Medica, 16(4), 219–225. https://doi.org/10.5455/aim.2008.16.219-225
Robinson, V., Sansam, K., Hirst, L., & Neumann, V. (2010). Major lower limb amputation – what, why and how to achieve the best results. Orthopaedics and Trauma, 24(4), 276–285. https://doi.org/10.1016/j.mporth.2010.03.017
Rosenberg, W., & Donald, A. (1995). Evidence based medicine: An approach to clinical problem-solving. BMJ, 310(6987), 1122–1126. https://doi.org/10.1136/bmj.310.6987.1122
Sackett, D. L., & Rosenberg, W. M. C. (1995). On the need for evidence-based medicine. Journal of Public Health, 17(3), 330–334. https://doi.org/10.1093/oxfordjournals.pubmed.a043127
Saravanan, P., Hipple, C., Wang, J., McComb, C., & Menold, J. (2019). Decision-Making in the Prescription of Orthotics and Prosthetics for Partial-Foot Amputees. Volume 2B: 45th Design Automation Conference, V02BT03A001. https://doi.org/10.1115/DETC2019-97470
Saravanan, P., Walker, M., & Menold, J. (2020, November 3). Developing Training Tools for Clinicians in LICs: Using Hidden Markov Modeling to Study the Decision-Making Strategies of Expert and Novice Prosthetists. ASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. https://doi.org/10.1115/DETC2020-22144
Thompson, C., Cullum, N., McCaughan, D., Sheldon, T., & Raynor, P. (2004). Nurses, information use, and clinical decision making—The real world potential for evidence-based decisions in nursing. Evidence-Based Nursing, 7(3), 68–72. https://doi.org/10.1136/ebn.7.3.68
Walker, M., Saravanan, P., & Menold, J. (2020, November 3). Developing Training Tools for Clinicians in LICs: A Qualitative Investigation of the Patient Factors That Influence Prosthetic Prescription. ASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. https://doi.org/10.1115/DETC2020-22197
World Health Organization. (2005). Guidelines for training personnel in developing countries for prosthetic and orthotic services.
Zadeh, R., Sadatsafavi, H., & Xue, R. (2015). Evidence-Based and Value-Based Decision Making About Healthcare Design: An Economic Evaluation of the Safety and Quality Outcomes. HERD: Health Environments Research & Design Journal, 8(4), 58–76. https://doi.org/10.1177/1937586715586393