Tianyu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tianyu Zhang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Aliya Szpindel
McGill University
1 shared publication - Chenxi Sun
Harvard Medical School, Boston
1 shared publication - Elijah W. Keldsen
Stanford University School of Medicine Stanford California USA
1 shared publication - Fábio Augusto Nascimento
Washington University School of Medicine St. Louis Missouri USA
1 shared publication - Ioannis Karakis
Department of Neurology Emory University School of Medicine Atlanta Georgia USA
1 shared publication - Jin Jing
Beth Israel Deaconess Medical Center Boston Massachusetts USA
1 shared publication
Latest Publications
An adaptive, variable‐length test for certifying electroencephalographic spike‐detection skill: A retrospective feasibility study
Objective: Determining whether an individual reader has sufficient electroencephalographic (EEG) spike‐detection skill is challenging due to limited expert agreement. We evaluated whether modeling skill in interpretable signal‐detection terms—discrimination ability separate from response tendency—could power an adaptive, variable‐length test that can reliably and efficiently assess reader competence. Methods: We analyzed a multirater dataset containing 20 521 EEG segments and 2574 rater sessions. Case signal was estimated from multirater labels, and each reader was modeled using signal‐detection parameters: discrimination skill and response bias . Among 368 calibration‐eligible raters across five skill tiers, we used a stratified 50/50 train–validation split to select a certification threshold in training and to apply it in validation. We replayed an adaptive test on each rater's historical responses, using sequential stopping to issue pass, fail, or retest decisions. Results: The training‐derived threshold was (95% bootstrap confidence interval = –, Youden ). In validation, pass rates preserved the expected tier ordering: experts 100% (), experienced 100% (), novices 14% (), residents 0% (), and crowd raters 7% (). In the 81‐rater adaptive replay, clear failures stopped near 20 trials, and passing experts required a median of 95 trials. Split‐half replay showed intraclass correlation coefficient for at stopping; there were no hard pass–fail reversals among raters whose two halves both reached decisive verdicts. Significance: A signal‐detection framework quantified spike‐identification skill in EEG readers, and adaptive testing estimated this skill reliably with fewer than 100 short EEG segments. This approach could provide a practical, scalable method for assessing EEG reading competence.
An adaptive, variable‐length test for certifying electroencephalographic spike‐detection skill: A retrospective feasibility study
Objective: Determining whether an individual reader has sufficient electroencephalographic (EEG) spike‐detection skill is challenging due to limited expert agreement. We evaluated whether modeling skill in interpretable signal‐detection terms—discrimination ability separate from response tendency—could power an adaptive, variable‐length test that can reliably and efficiently assess reader competence. Methods: We analyzed a multirater dataset containing 20 521 EEG segments and 2574 rater sessions. Case signal was estimated from multirater labels, and each reader was modeled using signal‐detection parameters: discrimination skill and response bias . Among 368 calibration‐eligible raters across five skill tiers, we used a stratified 50/50 train–validation split to select a certification threshold in training and to apply it in validation. We replayed an adaptive test on each rater's historical responses, using sequential stopping to issue pass, fail, or retest decisions. Results: The training‐derived threshold was (95% bootstrap confidence interval = –, Youden ). In validation, pass rates preserved the expected tier ordering: experts 100% (), experienced 100% (), novices 14% (), residents 0% (), and crowd raters 7% (). In the 81‐rater adaptive replay, clear failures stopped near 20 trials, and passing experts required a median of 95 trials. Split‐half replay showed intraclass correlation coefficient for at stopping; there were no hard pass–fail reversals among raters whose two halves both reached decisive verdicts. Significance: A signal‐detection framework quantified spike‐identification skill in EEG readers, and adaptive testing estimated this skill reliably with fewer than 100 short EEG segments. This approach could provide a practical, scalable method for assessing EEG reading competence.
- Open Access
- 26 June 2026
- Published by Universidad Nacional de Córdoba in Revista de la Facultad de Ciencias Médicas de Córdoba
- Vol. 83 (2) , e48628
A double threat
A 73-year-old immunocompromised woman with a history of heart transplant presented with cognitive decline and left-sided neurological deficits. Imaging revealed atypical brain lesions. Initial biopsy was inconclusive. Despite extensive infectious workup, diagnosis remained unclear until a second brain biopsy confirmed central nervous system toxoplasmosis and cytomegalovirus (CMV) encephalitis. Treatment with antiparasitic and antiviral agents was initiated, but the patient’s condition deteriorated, leading to palliative care. This case highlights diagnostic challenges in immunocompromised patients, the importance of considering atypical presentations of CNS infections, and the potential necessity of repeat biopsies when initial evaluations are non-diagnostic.
- 26 June 2026
- Published by Universidad Nacional de Córdoba in Revista de la Facultad de Ciencias Médicas de Córdoba
- Vol. 83 (2) , e48628
Open AccessA double threat
A 73-year-old immunocompromised woman with a history of heart transplant presented with cognitive decline and left-sided neurological deficits. Imaging revealed atypical brain lesions. Initial biopsy was inconclusive. Despite extensive infectious workup, diagnosis remained unclear until a second brain biopsy confirmed central nervous system toxoplasmosis and cytomegalovirus (CMV) encephalitis. Treatment with antiparasitic and antiviral agents was initiated, but the patient’s condition deteriorated, leading to palliative care. This case highlights diagnostic challenges in immunocompromised patients, the importance of considering atypical presentations of CNS infections, and the potential necessity of repeat biopsies when initial evaluations are non-diagnostic.