SRSuelynn Emily Ren

Suelynn Emily Ren

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Suelynn Emily Ren has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Retrospective Cohort Study of Hospitalised Patients With First‐Episode Substance‐Induced Psychosis and First‐Episode Psychosis: Comparing Long‐Acting Injectable Antipsychotic Use and Post‐Discharge Outcomes

    by John D. Eun, Matt Iles‐Shih, Suelynn Ren, Kevin A. Hallgren, Adam Kuczynski

    Introduction: Clinicians may not recommend long‐acting injectable antipsychotics (LAI‐APs) for patients diagnosed with first‐episode substance‐induced psychosis (FESIP), despite the risk of transition from FESIP to schizophrenia and the effectiveness of LAI‐AP in early psychosis. We compared LAI‐AP use and post‐discharge outcomes between patients with first‐episode psychosis (FEP) and those with FESIP during their index psychiatric hospitalisation. Methods: We conducted a retrospective cohort study using electronic health record data from patients aged 18–39 who were discharged from inpatient psychiatry units at a public academic hospital between 2021 and 2024. Outcomes included administration of any LAI‐AP during the index hospitalisation, documented recommendation of any LAI‐AP, psychiatric rehospitalisation and emergency department (ED) encounters after discharge. Results: The cohort included 90 patients with FEP and 84 patients with FESIP. Only one (1.2%) patient with FESIP received an LAI‐AP compared with 10 (11.1%) with FEP (OR = 0.10, 95% CI = 0.002–0.71); LAI‐AP was recommended to one (1.2%) patient with FESIP compared with 30 (33.3%) with FEP (OR = 0.02, 95% CI = 0.0006–0.16). Rehospitalisation occurred in 41 (45.6%) patients with FEP and 38 (45.2%) with FESIP; post‐discharge ED encounters occurred in 50 (55.6%) and 52 (61.9%) patients, respectively. Time to first rehospitalisation and ED encounter after discharge did not differ between the groups. Conclusions: Despite similar post‐discharge outcomes between patients with FEP and FESIP, administration or recommendation of an LAI‐AP was rarer among those with FESIP. Our findings highlight uncertainty in treatment decision‐making and support further research to guide early intervention strategies in patients with substance‐induced psychosis.

  • Investigating Whether Summarizing Raw Clinical Text Affects the Prediction of In-Hospital Violence: A Retrospective Case Study: Évaluation de l’effet du résumé des textes cliniques bruts sur la prédiction de la violence en milieu hospitalier : étude de cas rétrospective

    by Zixuan Yu, Jacqueline Chipkin, Julia Siar, Suelynn Emily Ren, Fei Xia, Meliha Yetisgen, Nicholas J. Dobbins, Taylor M. Black

    Background: We evaluated whether summaries and large language models (LLMs) preserve predictive performance for inpatient violence risk and assessed performance across demographics. Methods: We conducted a retrospective study of inpatient encounters at Harborview Medical Center between March 2021 and September 2023. Cases were inpatient behavioural violence events, and each was matched to 10 control encounters. For each encounter, we used clinical notes from the 72 hours before the event for cases and a matched window for controls. We compared Clinical-Longformer trained on original notes with pipelines that first generated summaries and then classified risk. Summaries were either general or guided by clinician-defined risk entities. We also tested Llama-3.1–8B and MedGemma-27B in zero-shot (ZS) and fine-tuned settings. Primary endpoints were positive-class precision, recall, and F1. We also reported overall and subgroup area under the receiver operating characteristic curve (AUROC) with bootstrap confidence intervals for sex, race, ethnicity, age, and mental health flag. Results: Clinical-Longformer on original notes achieved the strongest performance (F1 = 0.776, AUROC = 0.959). Replacing original notes with general or entity-guided summaries reduced performance (F1 = 0.465 and 0.510). Llama-3.1–8B improved with sequence-classification fine-tuning on original notes but remained below Clinical-Longformer (F1 = 0.701; AUROC = 0.933), while ZS prompting performed poorly. MedGemma-27B also remained inferior, with its best performance from sequence-classification fine-tuning on original notes (F1 = 0.612, AUROC = 0.947). Subgroup AUROCs were high across sex, race, ethnicity, and age, with lower performance among patients with a documented mental health flag. Conclusion: Direct classification of original notes remained the most reliable strategy. Summaries of clinical notes may compress or alter cues needed for discrimination, and off-the-shelf prompting was inadequate as a stand-alone predictor. A practical path is to anchor risk scoring in long-context discriminative models and use LLMs for auditable, clinician-facing summaries or rationales. Prospective and external validation are needed before clinical deployment.