HKHan Joon Kim

Han Joon Kim

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Han Joon Kim has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A machine learning framework for multimodal temporal prediction of neurological outcome after out-of-hospital cardiac arrest

    by Jee Yong Lim, Han Joon Kim

    Neurological prognostication after out-of-hospital cardiac arrest (OHCA) remains challenging. Existing clinical scores rely on static, single-timepoint assessments and fail to capture the dynamic interplay among coagulation derangement, systemic inflammation, brain injury, and evolving neurological status. Whether integrating serial multimodal data through machine learning can meaningfully improve prediction over established approaches has not been systematically evaluated. We conducted a retrospective cohort study of 414 consecutive OHCA patients treated with targeted temperature management (TTM) at a tertiary cardiac arrest center in South Korea (2009–2021), where withdrawal of life-sustaining treatment is not practiced. Ninety-one features spanning five modalities—coagulation, inflammation, brain injury biomarkers, neurological examination, and static clinical variables—were extracted at admission, 24 h, and 48 h. We compared four machine learning algorithms against single-modality models and a clinical score approximation using five-fold stratified cross-validation. Dynamic prediction models evaluated discriminative performance evolution. SHapley Additive exPlanations (SHAP) analysis quantified feature- and modality-level contributions. Robustness was assessed through temporal validation, self-fulfilling prophecy sensitivity analyses, and exclusion of clinician-decision-dependent variables. Of 414 patients (mean age 55.6 years, 71.8% male), 131 (31.6%) achieved favorable neurological outcome (Cerebral Performance Category [CPC] 1–2) at six months. The full multimodal random forest model achieved an area under the receiver operating characteristic curve (AUROC) of 0.983 (95% CI 0.972–0.991), significantly outperforming the clinical score approximation (AUROC 0.847; ΔAUROC + 0.136, p < 0.001) and every single-modality model (all p < 0.001). At 100% specificity, sensitivity was 0.519. Dynamic prediction improved from AUROC 0.950 at admission to 0.977 at 24 h ( p < 0.001) and 0.981 at 48 h. SHAP analysis revealed that neurological examination and brain injury biomarkers dominated overall prediction, while coagulation markers—particularly initial international normalized ratio (INR)—provided the strongest early discriminative signal. The model remained robust on temporal validation (AUROC 0.977), after neurological examination exclusion (0.965), and after excluding clinician-decision-dependent variables (0.979). A multimodal machine learning framework integrating serial thromboinflammation, brain injury, and neurological data substantially outperforms conventional approaches for neurological prognostication after OHCA. The dynamic prediction capability and modality-level explainability offer a pathway toward clinically actionable, time-evolving decision support in post-cardiac arrest care.


  • Open Access

    Distinct Coagulation Phenotypes and Long-Term Neurological Outcomes in Post-Cardiac Arrest Syndrome: A Latent Class Analysis of a 9-Year Single-Center Cohort

    by Sin Young Park, Sang Hoon Oh, Hyo Joon Kim, Han Joon Kim, Jee Yong Lim

    Background/Objectives: Post-cardiac arrest syndrome (PCAS) induces systemic ischemia–reperfusion injury accompanied by sepsis-like coagulopathy. This coagulopathy presents heterogeneously, yet distinct coagulation phenotypes and their impact on hypoxic–ischemic brain injury (HIBI) remain poorly defined. We aimed to identify coagulation phenotypes using latent class analysis (LCA) and assess their association with 6-month neurological outcomes. Methods: We retrospectively analyzed adult out-of-hospital cardiac arrest (OHCA) patients treated with targeted temperature management (TTM) between 2011 and 2019 from a prospective registry at a tertiary academic center. LCA was performed using coagulation biomarkers measured at admission and 24 h post-return of spontaneous circulation: D-dimer, fibrinogen, antithrombin III (ATIII), platelet count, and PT-INR. The primary outcome was poor neurological outcome (Cerebral Performance Category 3–5) at 6 months. Secondary outcomes included in-hospital mortality and cerebral edema severity assessed by gray-to-white matter ratio (GWR) on brain CT. Results: Among 325 patients, LCA identified three phenotypes: Class 1 (Preserved Coagulation, 36.9%), Class 2 (Hypercoagulable State, 41.5%) characterized by elevated D-dimer with preserved fibrinogen and ATIII, and Class 3 (Consumptive Coagulopathy, 21.5%) marked by profound D-dimer elevation with fibrinogen <150 mg/dL and ATIII <60%. Class 3 exhibited the lowest GWR and highest neuron-specific enolase levels. In multivariable analysis adjusting for age, low-flow time, initial rhythm, and lactate, Class 3 independently predicted poor neurological outcome (adjusted OR 4.52; 95% CI 2.15–9.48), whereas Class 2 did not. Conclusions: PCAS-related coagulopathy is heterogeneous. A consumptive coagulopathy phenotype identifies a high-risk subgroup associated with severe brain injury and poor long-term neurological outcomes. Early identification of this phenotype may enable targeted prognostication and guide future phenotype-specific interventional strategies.:

  • Brain MRI–based prognostication after cardiac arrest: qualitative assessment outperforms variable voxel-wise ADC thresholds

    by Ae Kyung Gong, Sang Hoon Oh, Jinhee Jang, Kyu Nam Park, Chun Song Youn, Ji Young Lee, Hyo Joon Kim, Hyo Jin Bang, Ji-Sook Lee

  • Open Access

    Prognostic Implication of Ventricular Volumetry in Early Brain Computed Tomography after Cardiac Arrest

    by Ae Kyung Gong, Sang Hoon Oh, Jinhee Jang, Kyu Nam Park, Han Joon Kim, Ji Young Lee, Chun Song Youn, Jee Yong Lim, Hyo Joon Kim, Hyo Jin Bang

    Brain swelling after cardiac arrest may affect brain ventricular volume. This study aimed to investigate the prognostic implications of ventricular volume on early thin-slice brain computed tomography (CT) after cardiac arrest. We measured the gray-to-white matter ratio (GWR) and the characteristics and volumes of the lateral, third, and fourth ventricles. The primary outcome was a poor 6-month neurological outcome. Of the 166 patients, 115 had a poor outcome. The fourth ventricle was significantly smaller in the poor outcome group (0.58 cm3 [95% CI, 0.43–0.80]) than in the good outcome group (0.74 cm3 [95% CI, 0.68–0.99], p < 0.001). Ventricular characteristics and other ventricular volumes did not differ between outcome groups. The area under the curve for the fourth ventricular volume was 0.68, comparable to 0.69 for GWR. Lower GWR (3) predicted poor outcomes with 100% specificity and sensitivities of 8.7% (95% CI, 4.2–15.4) and 20.9% (95% CI, 13.9–29.4), respectively. Combining these measures improved the sensitivity to 25.2% (95% CI, 17.6–34.2). After adjusting for covariates, the fourth ventricular volume was independently associated with neurologic outcome. A marked decrease in fourth ventricular volume, with concomitant hypoattenuation on CT scans, more accurately predicted outcomes.

  • Open Access

    Can Optic Nerve Sheath Images on a Thin-Slice Brain Computed Tomography Reconstruction Predict the Neurological Outcomes in Cardiac Arrest Survivors?

    by Sung Ho Kwon, Sang Hoon Oh, Jinhee Jang, Soo Hyun Kim, Kyu Nam Park, Chun Song Youn, Han Joon Kim, Jee Yong Lim, Hyo Joon Kim, Hyo Jin Bang

    We analyzed the prognostic performance of optic nerve sheath diameter (ONSD) on thin-slice (0.6 mm) brain computed tomography (CT) reconstruction images as compared to routine-slice (4 mm) images. We conducted a retrospective analysis of brain CT images taken within 2 h after cardiac arrest. The maximal ONSD (mONSD) and optic nerve sheath area (ONSA) were measured on thin-slice images, and the routine ONSD (rONSD) and gray-to-white matter ratio (GWR) were measured on routine-slice images. We analyzed their area under the receiver operator characteristic curve (AUC) and the cutoff values for predicting a poor 6-month neurological outcome (a cerebral performance category score of 3–5). Of the 159 patients analyzed, 113 patients had a poor outcome. There was no significant difference in rONSD between the outcome groups (p = 0.116). Compared to rONSD, mONSD (AUC 0.62, 95% CI: 0.54–0.70) and the ONSA (AUC 0.63, 95% CI: 0.55–0.70) showed better prognostic performance and had higher sensitivities to determine a poor outcome (mONSD, 20.4% [95% CI, 13.4–29.0]; ONSA, 16.8% [95% CI, 10.4–25.0]; rONSD, 7.1% [95% CI, 3.1–13.5]), with specificity of 95.7% (95% CI, 85.2–99.5). A combined cutoff value obtained by both the mONSD and GWR improved the sensitivity (31.0% [95% CI, 22.6–40.4]) of determining a poor outcome, while maintaining a high specificity. In conclusion, rONSD was clinically irrelevant, but the mONSD had an increased sensitivity in cutoff having acceptable specificity. Combination of the mONSD and GWR had an improved prognostic performance in these patients.


  • Open Access

    The Levels of Circulating MicroRNAs at 6-Hour Cardiac Arrest Can Predict 6-Month Poor Neurological Outcome

    by Sang Hoon Oh, Ho-Shik Kim, Kyu Nam Park, Sanghee Ji, Ji-Young Park, Seung Pill Choi, Jee Yong Lim, Han Joon Kim, on behalf of CROWN Investigators

    Early prognostication in cardiac arrest survivors is challenging for physicians. Unlike other prognostic modalities, biomarkers are easily accessible and provide an objective assessment method. We hypothesized that in cardiac arrest patients with targeted temperature management (TTM), early circulating microRNA (miRNA) levels are associated with the 6-month neurological outcome. In the discovery phase, we identified candidate miRNAs associated with cardiac arrest patients who underwent TTM by comparing circulating expression levels in patients and healthy controls. Next, using a larger cohort, we validated the prognostic values of the identified early miRNAs by measuring the serum levels of miRNAs, neuron-specific enolase (NSE), and S100 calcium-binding protein B (S100B) 6 h after cardiac arrest. The validation cohort consisted of 54 patients with TTM. The areas under the curve (AUCs) for poor outcome were 0.85 (95% CI (confidence interval), 0.72–0.93), 0.82 (95% CI, 0.70–0.91), 0.78 (95% CI, 0.64–0.88), and 0.77 (95% CI, 0.63–0.87) for miR-6511b-5p, -125b-1-3p, -122-5p, and -124-3p, respectively. When the cut-off was based on miRNA levels predicting poor outcome with 100% specificity, sensitivities were 67.7% (95% CI, 49.5–82.6), 50.0% (95% CI, 32.4–67.7), 35.3% (95% CI, 19.7–53.5), and 26.5% (95% CI, 12.9–44.4) for the above miRNAs, respectively. The models combining early miRNAs with protein biomarkers demonstrated superior prognostic performance to those of protein biomarkers.


  • Prognostic value of brainstem auditory and visual evoked potentials in cardiac arrest patients with targeted temperature management

    by Jee Yong Lim, Sang Hoon Oh, Kyu Nam Park, Seung Pill Choi, Joo Suk Oh, Chun Song Youn, Han Joon Kim, Hyo Joon Kim, Hwan Song


  • Open Access

    The impact of sex and age on neurological outcomes in out-of-hospital cardiac arrest patients with targeted temperature management

    by On behalf of the Korean Hypothermia Network Investigators, Sang Hoon Oh, Kyu Nam Park, Jeeyong Lim, Seung Pill Choi, Joo Suk Oh, In Soo Cho, Byung Kook Lee, Yong Hwan Kim, Young-Min Kim, et al.

    There are conflicting data regarding sex-based differences in the outcomes of out-of-hospital cardiac arrest (OHCA) patients, and whether the specific sex advantage is age-specific remains unclear. We assessed the impact of the interactions between sex and age on the neurological outcomes of OHCA patients receiving targeted temperature management (TTM). Data collected from 2007 to 2012 for a multicenter, registry-based study of the Korean Hypothermia Network were analyzed. We used a multivariate logistic regression model with an interaction term (age × sex) as the final model for the outcomes. To evaluate the association between sex and outcome in specific age groups, all patients were divided into specific age subgroups, and the adjusted ORs and 95% CIs of good neurological outcomes for males were calculated for each age group. Finally, the ORs of a good neurological outcome for the specific age groups compared with the 50- to 59-year-old group were calculated for both sexes. In the interaction analysis, age was a negative prognostic factor (OR, 0.95 [95% CI, 0.93-0.98]), whereas sex was not associated with neurological outcomes (OR, 3.74 [95% CI, 0.85–16.35]), and reproductive age in females (age, < 50 years) was also not associated with good neurological outcomes. After the patients were divided into five age groups, sex was not an independent predictor of neurological outcomes across all age groups. Patients of both sexes aged < 40 years had significantly better outcomes than patients in the 50- to 59-year-old group (males, OR, 4.03 [95% CI, 1.86–8.73]; females, OR, 10.34 [95% CI, 1.99–53.85]). Males aged ≥ 70 years had significantly poorer neurological outcomes than those in the 50- to 59-year-old group (OR, 0.15 [95% CI, 0.07–0.32]), but this outcome was not observed for females (OR, 0.78 [95% CI, 0.20–3.14]). Sex did not influence the neurological outcomes of TTM-treated OHCA patients. In contrast to the outcomes in males, the neurological outcomes of females worsened from 18 to 59 years of age and then remained constant.


  • Does rapid blood sampling affect the retention time of patients with low-acuity complaints in the emergency department?

    by Ju Young Lee, Sang Hoon Oh, Kyu Nam Park, Jee Yong Lim, Jung Min Lee, Hyun Suk Park, Han Joon Kim


  • Analysis of Deliberate Self-Wrist-Cutting Episodes Presenting to the Emergency Department

    by Jin Kim, Han Joon Kim, Soo Hyun Kim, Sang Hoon Oh, Kyu Nam Park

    Background: Previous suicide attempts increase the risk of a completed suicide. However, a large proportion of patients with deliberate self-wrist cutting (DSWC) are often discharged without undergoing a psychiatric interview. Aims: The aims of this study were to investigate the differences in the characteristics and outcomes of patients with DSWC and those with deliberate self-poisoning (DSP) episodes. The results of this study may be used to improve the efficacy of treatment for DSWC patients. Method: We retrospectively reviewed the medical records of 598 patients with DSWC and DSP who were treated at the emergency department of Seoul Saint Mary's Hospital between 2008 and 2013. We assessed sociodemographic information, clinical variables, the reasons for the suicide attempts, and the severity of the suicide attempts. Results: A total of 141 (23.6%) patients were included in the DSWC group, and 457 (76.4%) were included in the DSP group. A significantly greater number of patients in the DSWC group had previously attempted suicide (p = .014). A total of 63 patients (44.7%) in the DSWC group and 409 patients (89.5%) in the DSP group underwent psychiatric interviews. Conclusion: More DSWC patients had previously attempted suicide, but fewer of them underwent psychiatric interviews compared with the DSP patients.