SNDT WOMEN'S UNIVERSITY

BMK Knowledge Resource Centre

Vithaldas Vidyavihar, Juhu Tara Road,
Santacruz (West) Mumbai - 400049

In Pursuit of an Expert l Intelligence System: Reproducing Human Physicians Diagnostic Reasoning and Triage Decision Making (Record no. 132688)

MARC details
000 -LEADER
fixed length control field 02622nam a2200145 4500
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 250901b |||||||| |||| 00| 0 eng d
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Azad Kabir
245 ## - TITLE STATEMENT
Title In Pursuit of an Expert l Intelligence System: Reproducing Human Physicians Diagnostic Reasoning and Triage Decision Making
300 ## - PHYSICAL DESCRIPTION
Extent pp28-39
520 ## - SUMMARY, ETC.
Summary, etc. biblio.abstract Aprimary objective in the development of an l intelligence (AI) system should be to replicate an expert<br/>physician’s thought process. s study compares a hypothetico-deductive powered system (Doctor Ai)<br/>and a decision tree powered sys tem (Babylon Health Ai) with human physicians to evaluate ,<br/>measured by the time needed to (1) diagnose and (2)make triage decisions. In this study, both AI<br/>systems and the physicians evaluated a total of n typical textbook presentations of clinical scenarios. e<br/>study found that both AI systems agreed on patient disposition decisions for 93% of cases (14out of 15<br/>cases; p<0.08) with no statistically t e from physicians, indicating that both AI systems are equally e in<br/>patient triage decisions relative to the physicians. e Doctor Ai system agreed with the physicians on<br/>thenal diagnosis for 73.3% (11 out of 15) of the cases, while Babylon Health Ai provided a l diagnosis<br/>in only 53% (8 out of15) of cases. For the remaining cases, the diagnosis was either undisclosed or<br/>could not be determined. In this study, DoctorAi used an average of 7.8 (±2.08) computer screens to<br/>reach diagnostic n compared to Babylon Health’s 21.5(±9.63) screens (p<0.001). e number of screens<br/>utilized to reach a l disposition decision (triage) was 10.0 (±2.33) forDoctor Ai, whereas Babylon<br/>Health utilized 21.5 (±9.63) screens (p<0.001). Additionally, Doctor Ai used on average 13.9(±6.54)<br/>Yes/No events to determine the l diagnosis compared to Babylon Health’s 62.3 (±31.55) Yes/No events<br/>(p<0.001). In conclusion, the hypothetico-deductive system can diagnose more quickly and provide<br/>more accurate triage decisions compared to a decision tree powered system. However, both systems<br/>combined perform as well as physicians. It is important to evaluate whether such AI can be utilized to<br/>tackle pandemics in the U.S. healthcare system and in any develop ing country healthcare systems<br/>facing dire circumstances due to a scarcity of trained physicians<br/>
654 ## - SUBJECT ADDED ENTRY--FACETED TOPICAL TERMS
Subject <a href="Aritifical intelligence">Aritifical intelligence</a>
-- <a href=" hypothetico- decuctive Reasoning Decision Tree Alogrithm Diagnostics Reasoning Triage"> hypothetico- decuctive Reasoning Decision Tree Alogrithm Diagnostics Reasoning Triage</a>
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Raeed Kabir
773 0# - HOST ITEM ENTRY
Host Biblionumber 131673
Host Itemnumber 113505
Place, publisher, and date of publication New Delhi Enriched Publications
Title Journal of Artificial Intelligence and Soft Computing research
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type Journal Article
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Location (home branch) Sublocation or collection (holding branch) Date acquired Koha issues (times borrowed) Piece designation (barcode) Koha date last seen Price effective from Koha item type
    Dewey Decimal Classification     SNDT Juhu SNDT Juhu 01/09/2025   JP881.4 01/09/2025 01/09/2025 Journal Article