307 Machine learning identification of diabetic foot ulcer severity to reduce amputation risk
OBJECTIVES/GOALS: Target: Computationally identify the markers of ulcer severity and risk of amputation from datasets that include demographics data, clinical, laboratory data, and medical history over 6000 patients. METHODS/STUDY POPULATION: In this study we will use tables of demographics such as...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2023-04-01
|
| Series: | Journal of Clinical and Translational Science |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2059866123003606/type/journal_article |
| _version_ | 1797840426058645504 |
|---|---|
| author | Mario Flores Karla Paniagua Rivera Yufang Jin |
| author_facet | Mario Flores Karla Paniagua Rivera Yufang Jin |
| author_sort | Mario Flores |
| collection | DOAJ |
| description | OBJECTIVES/GOALS: Target: Computationally identify the markers of ulcer severity and risk of amputation from datasets that include demographics data, clinical, laboratory data, and medical history over 6000 patients. METHODS/STUDY POPULATION: In this study we will use tables of demographics such as age, gender, and ethnicity/race. Inspired by previous research we’ll include wound age (duration in days), wound size, number of concurrent wounds of any etiology, evidence of bioburden/infection, Wagner grade, being non ambulatory, renal dialysis, renal transplant, peripheral vascular disease, and patient hospitalization. Another table will include laboratory vital signs to include physiological variables such as height, weight, body mass index, pulse rate, blood pressure, respiratory rate, and temperature. We’ll include also social data like smoking status, socio-economic status, housing condition. RESULTS/ANTICIPATED RESULTS: Our project aligns with previous efforts to identify high risk Diabetic Foot Ulcer individuals but also takes a different perspective by collecting and marking clinical data from a subset of patients (e.g., severity, Hispanic versus non-Hispanic) and computationally process these data to provide a tool that can identify DFU severity and high-risk patients. We will obtain samples from Hispanics and non-Hispanics because these two groups are likely to have significant differences in the progression of ulcer severity. The rationale is that by comparing these two groups, we will assess and study the factors that are differentially present. It is our expectation that the proposed project will provide an easy-to-use tool for DFU progression and risk of amputation and contribute to identify high-risk individuals. DISCUSSION/SIGNIFICANCE: Diabetes prevalence estimates in Bexar County, TX exceeds national estimates (15.5% vs. 11.3%) and diagnosed cases are higher among Hispanic adults (13.4%) compared to their non-Hispanic white counterparts (9.5%). Late identification of severe foot ulcers minimizes the likelihood of reducing amputation risk. |
| first_indexed | 2024-04-09T16:14:55Z |
| format | Article |
| id | doaj.art-a389984a20bb43399ec69f9f76bd7e98 |
| institution | Directory Open Access Journal |
| issn | 2059-8661 |
| language | English |
| last_indexed | 2024-04-09T16:14:55Z |
| publishDate | 2023-04-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Journal of Clinical and Translational Science |
| spelling | doaj.art-a389984a20bb43399ec69f9f76bd7e982023-04-24T05:55:57ZengCambridge University PressJournal of Clinical and Translational Science2059-86612023-04-017929210.1017/cts.2023.360307 Machine learning identification of diabetic foot ulcer severity to reduce amputation riskMario Flores0Karla Paniagua1Rivera Yufang Jin2University of Texas at San AntonioUniversity of Texas at San AntonioUniversity of Texas at San AntonioOBJECTIVES/GOALS: Target: Computationally identify the markers of ulcer severity and risk of amputation from datasets that include demographics data, clinical, laboratory data, and medical history over 6000 patients. METHODS/STUDY POPULATION: In this study we will use tables of demographics such as age, gender, and ethnicity/race. Inspired by previous research we’ll include wound age (duration in days), wound size, number of concurrent wounds of any etiology, evidence of bioburden/infection, Wagner grade, being non ambulatory, renal dialysis, renal transplant, peripheral vascular disease, and patient hospitalization. Another table will include laboratory vital signs to include physiological variables such as height, weight, body mass index, pulse rate, blood pressure, respiratory rate, and temperature. We’ll include also social data like smoking status, socio-economic status, housing condition. RESULTS/ANTICIPATED RESULTS: Our project aligns with previous efforts to identify high risk Diabetic Foot Ulcer individuals but also takes a different perspective by collecting and marking clinical data from a subset of patients (e.g., severity, Hispanic versus non-Hispanic) and computationally process these data to provide a tool that can identify DFU severity and high-risk patients. We will obtain samples from Hispanics and non-Hispanics because these two groups are likely to have significant differences in the progression of ulcer severity. The rationale is that by comparing these two groups, we will assess and study the factors that are differentially present. It is our expectation that the proposed project will provide an easy-to-use tool for DFU progression and risk of amputation and contribute to identify high-risk individuals. DISCUSSION/SIGNIFICANCE: Diabetes prevalence estimates in Bexar County, TX exceeds national estimates (15.5% vs. 11.3%) and diagnosed cases are higher among Hispanic adults (13.4%) compared to their non-Hispanic white counterparts (9.5%). Late identification of severe foot ulcers minimizes the likelihood of reducing amputation risk.https://www.cambridge.org/core/product/identifier/S2059866123003606/type/journal_article |
| spellingShingle | Mario Flores Karla Paniagua Rivera Yufang Jin 307 Machine learning identification of diabetic foot ulcer severity to reduce amputation risk Journal of Clinical and Translational Science |
| title | 307 Machine learning identification of diabetic foot ulcer severity to reduce amputation risk |
| title_full | 307 Machine learning identification of diabetic foot ulcer severity to reduce amputation risk |
| title_fullStr | 307 Machine learning identification of diabetic foot ulcer severity to reduce amputation risk |
| title_full_unstemmed | 307 Machine learning identification of diabetic foot ulcer severity to reduce amputation risk |
| title_short | 307 Machine learning identification of diabetic foot ulcer severity to reduce amputation risk |
| title_sort | 307 machine learning identification of diabetic foot ulcer severity to reduce amputation risk |
| url | https://www.cambridge.org/core/product/identifier/S2059866123003606/type/journal_article |
| work_keys_str_mv | AT marioflores 307machinelearningidentificationofdiabeticfootulcerseveritytoreduceamputationrisk AT karlapaniagua 307machinelearningidentificationofdiabeticfootulcerseveritytoreduceamputationrisk AT riverayufangjin 307machinelearningidentificationofdiabeticfootulcerseveritytoreduceamputationrisk |