Christina Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Christina Gao has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Stephen Bacchi
Faculty of Health and Medical Sciences The University of Adelaide Adelaide South Australia Australia
10 shared publications - Brandon Stretton
Royal Adelaide Hospital Adelaide South Australia Australia
5 shared publications Weng Onn Chan
The University of Adelaide Adelaide South Australia Australia
5 shared publicationsAashray Gupta
Faculty of Health and Medical Sciences The University of Adelaide Adelaide South Australia Australia
4 shared publications- Joshua George Kovoor
Faculty of Health and Medical Sciences The University of Adelaide Adelaide South Australia Australia
4 shared publications Andrew Vanlint
Adelaide Medical School, The University of Adelaide, South Australia, Australia
2 shared publications
Latest Publications
- Open Access
- 1 June 2026
- Published by Wolters Kluwer Health in Neurology Education
- Vol. 5 (2) , e200320
Education Research: Quality of Narrative Feedback Generated by a Large Language Model Compared With Expert Faculty for Case-Based Learning in Neurology Education
Neurology learners often receive limited feedback in clinical settings because of workflow constraints, variability in supervision, and competing clinical demands. Artificial intelligence, including large language models (LLMs) may help address these gaps and provide clinical learners with effective formative feedback by generating real-time, case-specific feedback during neurology case-based learning (CBL). The aim of this study was to examine how the quality of LLM-generated feedback compares with human expert-generated feedback in neurology CBL. In this exploratory quantitative study, student participants undertook LLM-enabled interactive cases on the TEACHABLE platform, which included history gathering, physical examination elements, and ordering diagnostic testing. Participants were clinical-level students recruited from 2 medical institutions. Case transcripts were recorded and analyzed for feedback generation, which was provided by an LLM and human experts in 2 components: history taking/physical examination elements (H&P) and assessment and plan (A&P). Feedback characteristics including sentence count, word count, and reference to case key learning points were summarized and compared. Feedback quality was scored by blinded experts using the QuAL and EFeCT instruments. Results were compared for the H&P and A&P components of the case interactions. Four student participants completed 5 interactive cases each, generating 20 total transcripts for feedback. Word and sentence number were similar among LLM-generated and expert-generated feedback, except for a greater word length in expert-generated A&P feedback. Regarding H&P, the LLM commented on the key learning points in 20/20 (100%) of the cases as compared with 39/60 (65%) for the human experts. For A&P, the LLM feedback discussed key points in 20/20 (100%) cases as compared with 39/40 (97.5%) for the human experts. The LLM feedback had no medical inaccuracies. QuAL and EFeCT scores were significantly greater for the LLM as compared with human experts for the H&P component, but not significantly different for the A&P component. LLMs provided with key learning points can generate timely, quality feedback on case-based interactions in a manner comparable with human experts. A hybrid framework combining LLM-generated feedback with faculty input may offer high-quality and equitably accessible formative feedback at scale. These pilot findings are limited by a small sample size and experimental setting.
- 1 June 2026
- Published by Wolters Kluwer Health in Neurology Education
- Vol. 5 (2) , e200320
Open AccessEducation Research: Quality of Narrative Feedback Generated by a Large Language Model Compared With Expert Faculty for Case-Based Learning in Neurology Education
Neurology learners often receive limited feedback in clinical settings because of workflow constraints, variability in supervision, and competing clinical demands. Artificial intelligence, including large language models (LLMs) may help address these gaps and provide clinical learners with effective formative feedback by generating real-time, case-specific feedback during neurology case-based learning (CBL). The aim of this study was to examine how the quality of LLM-generated feedback compares with human expert-generated feedback in neurology CBL. In this exploratory quantitative study, student participants undertook LLM-enabled interactive cases on the TEACHABLE platform, which included history gathering, physical examination elements, and ordering diagnostic testing. Participants were clinical-level students recruited from 2 medical institutions. Case transcripts were recorded and analyzed for feedback generation, which was provided by an LLM and human experts in 2 components: history taking/physical examination elements (H&P) and assessment and plan (A&P). Feedback characteristics including sentence count, word count, and reference to case key learning points were summarized and compared. Feedback quality was scored by blinded experts using the QuAL and EFeCT instruments. Results were compared for the H&P and A&P components of the case interactions. Four student participants completed 5 interactive cases each, generating 20 total transcripts for feedback. Word and sentence number were similar among LLM-generated and expert-generated feedback, except for a greater word length in expert-generated A&P feedback. Regarding H&P, the LLM commented on the key learning points in 20/20 (100%) of the cases as compared with 39/60 (65%) for the human experts. For A&P, the LLM feedback discussed key points in 20/20 (100%) cases as compared with 39/40 (97.5%) for the human experts. The LLM feedback had no medical inaccuracies. QuAL and EFeCT scores were significantly greater for the LLM as compared with human experts for the H&P component, but not significantly different for the A&P component. LLMs provided with key learning points can generate timely, quality feedback on case-based interactions in a manner comparable with human experts. A hybrid framework combining LLM-generated feedback with faculty input may offer high-quality and equitably accessible formative feedback at scale. These pilot findings are limited by a small sample size and experimental setting.
- 12 September 2025
- Published by Wiley in Australian Journal of Rural Health
- Vol. 33 (5) , e70090
Predicting Hypotension Before It Hits the Highway in Rural Anaesthesia
- 12 September 2025
- Published by Wiley in Australian Journal of Rural Health
- Vol. 33 (5) , e70090
Predicting Hypotension Before It Hits the Highway in Rural Anaesthesia
- Open Access
- 22 August 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (10) , 1766-1770
How may grant applications change in future because of artificial intelligence? An international and historical perspective
Grant application processes fulfil a vital role by determining the allocation of resources to facilitate medical research. Existing grant application processes run by large governmental institutions have changed over time. Through examination of previous changes to grant application processes and the current challenges facing grant applicants and reviewers, including the increasing role of artificial intelligence, insights may be obtained into future modifications in grant application structures that require consideration.
- 22 August 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (10) , 1766-1770
Open AccessHow may grant applications change in future because of artificial intelligence? An international and historical perspective
Grant application processes fulfil a vital role by determining the allocation of resources to facilitate medical research. Existing grant application processes run by large governmental institutions have changed over time. Through examination of previous changes to grant application processes and the current challenges facing grant applicants and reviewers, including the increasing role of artificial intelligence, insights may be obtained into future modifications in grant application structures that require consideration.
- 20 August 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (9) , 1570-1574
Clindamycin intravenous to oral switch automatic notifications: a pilot study
Where possible, antimicrobials, such as clindamycin, should be given orally rather than intravenously when efficacy will be equivalent. A single‐centre pre‐/post‐intervention study was conducted. There were 11 134 patients admitted to included wards during the study period. Following the intervention, there was a reduction in the ratio of intravenous to oral clindamycin usage (P < 0.001) and in the median number of doses of intravenous clindamycin administered per day in the included wards (median 6 vs. 10, P < 0.001). The development and use of an automated notification system for rationalising the use of intravenous clindamycin was feasible and may have applicability to other medications.
- 20 August 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (9) , 1570-1574
Clindamycin intravenous to oral switch automatic notifications: a pilot study
Where possible, antimicrobials, such as clindamycin, should be given orally rather than intravenously when efficacy will be equivalent. A single‐centre pre‐/post‐intervention study was conducted. There were 11 134 patients admitted to included wards during the study period. Following the intervention, there was a reduction in the ratio of intravenous to oral clindamycin usage (P < 0.001) and in the median number of doses of intravenous clindamycin administered per day in the included wards (median 6 vs. 10, P < 0.001). The development and use of an automated notification system for rationalising the use of intravenous clindamycin was feasible and may have applicability to other medications.
- 5 August 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (8) , 1414
Publicly accessible reporting of tangible outcomes for government‐funded research should be mandated
- 5 August 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (8) , 1414
Publicly accessible reporting of tangible outcomes for government‐funded research should be mandated
- Open Access
Artificial Intelligence Deployment of Conversational Support (AI-DOCS): A patient acceptability study
This study evaluated an artificial intelligence (AI) system based on a large language model (LLM) in conducting complex patient assessments, comparing its acceptability to that of human basic physician trainees (BPTs) during a divisional clinical examination (DCE). Compared with BPTs, Artificial Intelligence Deployment of Conversational Support (AI-DOCS) scored similarly empathy, politeness, and comprehensiveness to human trainees. AI-DOCS also elicited important clinical information that was not divulged to human examiners. Further research is needed to explore the integration of AI-DOCS into clinical workflows.
Open AccessArtificial Intelligence Deployment of Conversational Support (AI-DOCS): A patient acceptability study
This study evaluated an artificial intelligence (AI) system based on a large language model (LLM) in conducting complex patient assessments, comparing its acceptability to that of human basic physician trainees (BPTs) during a divisional clinical examination (DCE). Compared with BPTs, Artificial Intelligence Deployment of Conversational Support (AI-DOCS) scored similarly empathy, politeness, and comprehensiveness to human trainees. AI-DOCS also elicited important clinical information that was not divulged to human examiners. Further research is needed to explore the integration of AI-DOCS into clinical workflows.
- Open Access
- 14 July 2025
- Published by Wiley in British Journal of Clinical Pharmacology
Potential for use of Al/machine learning for pharmacovigilance: Is there a role for regulators?
- 14 July 2025
- Published by Wiley in British Journal of Clinical Pharmacology
Open AccessPotential for use of Al/machine learning for pharmacovigilance: Is there a role for regulators?
- Open Access
- 5 May 2025
- Published by Wiley in Anz Journal of Surgery
- Vol. 95 (11) , 2250-2252
OpenAI 's ‘Deep Research’ for the Generation of Comprehensive Referenced Medical Text: Uses and Cautions
- 5 May 2025
- Published by Wiley in Anz Journal of Surgery
- Vol. 95 (11) , 2250-2252
Open AccessOpenAI 's ‘Deep Research’ for the Generation of Comprehensive Referenced Medical Text: Uses and Cautions
- 1 May 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (5) , 871-872
Educating medical trainees about artificial intelligence should not be optional
- 1 May 2025
- Published by Wiley in Internal Medicine Journal
- Vol. 55 (5) , 871-872
Educating medical trainees about artificial intelligence should not be optional