A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse History
Online AI symptom checkers and diagnostic assistants (DAs) have tremendous potential to reduce misdiagnosis and cost, while increasing the quality, convenience, and availability of healthcare, but only if they can perform with high accuracy. We introduce a novel Bayesian DA designed to improve diagn...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2022.727486/full |
| _version_ | 1818189500584558592 |
|---|---|
| author | Alicia M. Jones Daniel R. Jones |
| author_facet | Alicia M. Jones Daniel R. Jones |
| author_sort | Alicia M. Jones |
| collection | DOAJ |
| description | Online AI symptom checkers and diagnostic assistants (DAs) have tremendous potential to reduce misdiagnosis and cost, while increasing the quality, convenience, and availability of healthcare, but only if they can perform with high accuracy. We introduce a novel Bayesian DA designed to improve diagnostic accuracy by addressing key weaknesses of Bayesian Network implementations for clinical diagnosis. We compare the performance of our prototype DA (MidasMed) to that of physicians and six other publicly accessible DAs (Ada, Babylon, Buoy, Isabel, Symptomate, and WebMD) using a set of 30 publicly available case vignettes, and using only sparse history (no exam findings or tests). Our results demonstrate superior performance of the MidasMed DA, with the correct diagnosis being the top ranked disorder in 93% of cases, and in the top 3 in 96% of cases. |
| first_indexed | 2024-12-11T23:43:49Z |
| format | Article |
| id | doaj.art-b0e87110c63a4f6abc03c7767a067eeb |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-12-11T23:43:49Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-b0e87110c63a4f6abc03c7767a067eeb2022-12-22T00:45:39ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122022-07-01510.3389/frai.2022.727486727486A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse HistoryAlicia M. JonesDaniel R. JonesOnline AI symptom checkers and diagnostic assistants (DAs) have tremendous potential to reduce misdiagnosis and cost, while increasing the quality, convenience, and availability of healthcare, but only if they can perform with high accuracy. We introduce a novel Bayesian DA designed to improve diagnostic accuracy by addressing key weaknesses of Bayesian Network implementations for clinical diagnosis. We compare the performance of our prototype DA (MidasMed) to that of physicians and six other publicly accessible DAs (Ada, Babylon, Buoy, Isabel, Symptomate, and WebMD) using a set of 30 publicly available case vignettes, and using only sparse history (no exam findings or tests). Our results demonstrate superior performance of the MidasMed DA, with the correct diagnosis being the top ranked disorder in 93% of cases, and in the top 3 in 96% of cases.https://www.frontiersin.org/articles/10.3389/frai.2022.727486/fullBayesian medical diagnosissymptom checkersgeneral medical diagnostic assistantdiagnostic performanceBayesian networkcomparison of physicians with AI decision support |
| spellingShingle | Alicia M. Jones Daniel R. Jones A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse History Frontiers in Artificial Intelligence Bayesian medical diagnosis symptom checkers general medical diagnostic assistant diagnostic performance Bayesian network comparison of physicians with AI decision support |
| title | A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse History |
| title_full | A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse History |
| title_fullStr | A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse History |
| title_full_unstemmed | A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse History |
| title_short | A Novel Bayesian General Medical Diagnostic Assistant Achieves Superior Accuracy With Sparse History |
| title_sort | novel bayesian general medical diagnostic assistant achieves superior accuracy with sparse history |
| topic | Bayesian medical diagnosis symptom checkers general medical diagnostic assistant diagnostic performance Bayesian network comparison of physicians with AI decision support |
| url | https://www.frontiersin.org/articles/10.3389/frai.2022.727486/full |
| work_keys_str_mv | AT aliciamjones anovelbayesiangeneralmedicaldiagnosticassistantachievessuperioraccuracywithsparsehistory AT danielrjones anovelbayesiangeneralmedicaldiagnosticassistantachievessuperioraccuracywithsparsehistory AT aliciamjones novelbayesiangeneralmedicaldiagnosticassistantachievessuperioraccuracywithsparsehistory AT danielrjones novelbayesiangeneralmedicaldiagnosticassistantachievessuperioraccuracywithsparsehistory |