Patient history recall was near ceiling in both conditions, with significant decline over two weeks but no difference between genAI and ePBLM conditions¶

Claim · All claims
Evidence · 1 study · causal r1 · q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Across conditions, recall decreased significantly from immediate to delayed assessment, and the rate of forgetting did not differ by condition; the condition coefficient was not significant (p = .052). → Allison Mool · Jacob Schmid · Thomas Johnston · Kodi J. Smith McCoy · Zachary Patterson · Hannah Feldt · William Thomas · Emma Fenner · Kevin Lu · Raya Gandhi · Adam Western · Brendan Seabold · Daniel Vollmer · Roshan Nallaveettil · Anthony Fanelli · Logan Schmillen · Shelley Tischkau · Anna T. Cianciolo · Pinckney Benedict · Richard Selinfreund 2026

Evidence¶

Allison Mool · Jacob Schmid · Thomas Johnston · Kodi J. Smith McCoy · Zachary Patterson · Hannah Feldt · William Thomas · Emma Fenner · Kevin Lu · Raya Gandhi · Adam Western · Brendan Seabold · Daniel Vollmer · Roshan Nallaveettil · Anthony Fanelli · Logan Schmillen · Shelley Tischkau · Anna T. Cianciolo · Pinckney Benedict · Richard Selinfreund 2026¶

Allison Mool · Jacob Schmid · Thomas Johnston · Kodi J. Smith McCoy · Zachary Patterson · Hannah Feldt · William Thomas · Emma Fenner · Kevin Lu · Raya Gandhi · Adam Western · Brendan Seabold · Daniel Vollmer · Roshan Nallaveettil · Anthony Fanelli · Logan Schmillen · Shelley Tischkau · Anna T. Cianciolo · Pinckney Benedict · Richard Selinfreund. (2026). Using Generative AI to Simulate Patient History-Taking in a Problem-Based Learning Tutorial: A Mixed-Methods Study. Technology, Knowledge and Learning. https://doi.org/10.1007/s10758-025-09929-4

q2 · i? · causal · r1

Linear regression of the 11-item Patient History Information Quiz (immediate and 2-week delayed, 52 observations) with time and condition as predictors. Immediate means were 9.40 (ePBLM) and 10.10 (genAI) of 11; delayed 7.94 and 8.63. The condition coefficient was 0.69, p = .052 — not significant.

"A significant effect was found for time only (Table 4). Across conditions, students’ recall decreased significantly from immediate to delayed assessment, and the rate of forgetting did not differ by condition."

Discussion¶

Learner Variables¶

• Long-Term Memory — outcome: instruction changes it

Related Claims¶

• GenAI-condition students rated their PBL tutorial significantly higher after the tutorial than they rated their previous ePBLM-based experiences, especially clinical accuracy — related
• GenAI tutorials took longer than ePBLM tutorials, with approximately 10 additional minutes spent on history-taking — related
• The genAI-enabled patient presented pertinent positive findings consistently with the ePBLM but deviated on non-essential content — related
• Students treated the genAI avatar as a sophisticated question base rather than a virtual patient, using predominantly closed-ended, efficiency-focused questioning — related
• GenAI students collaboratively phrased and troubleshooted questions, with collaborative problem-solving varying substantially between the two genAI groups — related
• Controlled GenAI virtual-patient and communication studies reported short-term skill gains, but positive findings were not universal — related