Kamiar Alaei

Prof. Dr. Kamiar Alaei


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 January 2026 in BioMedInformatics
Verified
Journal Article
Open access
PDF file
YLYupeng Li
Yupeng Li
JFJunyi Fan
Junyi Fan
KAKamiar Alaei
Kamiar Alaei
MPMaryam Pishgar
Maryam Pishgar
Background: Sepsis-associated liver injury (SALI) is a serious complication of sepsis that increases the risk of organ dysfunction and mortality; however, early identification of high-risk patients remains difficult due to nonspecific clinical features and complex pathophysiology. This study aimed to develop machine learning (ML) models to predict 28-day mortality in SALI patients within the first 24 h of intensive care unit (ICU) admission. Methods: A total of 1157 patients were included, comprising 826 from the MIMIC-IV (v2.2) database, 225 from MIMIC-III (v1.4), and 106 from eICU (v2.0). Data from MIMIC-IV were split into training and internal validation sets (7:3), while MIMIC-III and eICU served as external validation cohorts. Thirty clinically relevant features were selected. Eight ML models were evaluated using AUROC, accuracy, precision, recall, F1-score, and specificity. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) enhanced interpretability. Results: XGBoost model achieved the best performance, with an AUROC of 0.8556 (95% CI: 0.807–0.898), accuracy of 0.7702, recall of 0.8469, and specificity of 0.7200. SHAP identified lactate, blood urea nitrogen, heart rate, hemoglobin, and diastolic blood pressure as key predictors, while LIME provided patient-level interpretability. Conclusions: The XGBoost-based model may facilitate early mortality risk stratification and support clinical decision-making for SALI patients in ICU settings.

23 June 2024 in Viruses
Verified
Journal Article
Open access
PDF file
KAKamiar Alaei
Kamiar Alaei
BKBrian Kwan
Brian Kwan
HTHamid R. Torabzadeh
Hamid R. Torabzadeh
AAAdebimpe O. Akinwalere
Adebimpe O. Akinwalere
AAArash Alaei
Arash Alaei
AAArash Alaei
Arash Alaei
HIV early detection (CD4 counts ≥350 cells/μL) is correlated with higher life expectancy among people living with HIV (PLHIV). Several factors, including physical, cultural, structural, and financial barriers, may limit early detection of HIV. This is a first-of-its-kind study on population-level differences in early detection of HIV across time within Tajikistan and any country in the Central Asia region. Utilizing the Tajikistan Ministry of Health’s national HIV data (N = 10,700) spanning 2010 to 2023, we developed median regression models with the median CD4 cell count as the outcome and with the following predictors: time (years), region, age, gender, and area (urban/rural status). Individuals younger than 19 years old were detected early for HIV, whereas those older than 39 years were detected late. Females were detected earlier compared to their male counterparts regardless of region of residence. Rural populations were detected earlier in most years compared to their urban counterparts. The COVID-19 pandemic accelerated HIV early detection in 2021 but most regions have returned to near pre-pandemic levels of detection in 2022 and 2023. There were differences identified among different demographic and geographic groups which warrant further attention.

Verified
Journal Article
Open access
PDF file
BKBrian Kwan
Brian Kwan
HTHamid R. Torabzadeh
Hamid R. Torabzadeh
AAAdebimpe O. Akinwalere
Adebimpe O. Akinwalere
JNJulie Vy Lan Nguyen
Julie Vy Lan Nguyen
PCPatricia Cortez
Patricia Cortez
AAArash Alaei
Arash Alaei
Key populations are particularly vulnerable to human immunodeficiency virus (HIV) infection. Nearly half of Tajikistan’s gross domestic product (GDP) originates from labor migrant transfers. While not officially designated as a key population, over 300,000 migrants return to Tajikistan every year at increased risk for HIV due to absence or interruption of treatment, change in risky behaviors, and other factors. We analyzed cross-sectional data from the national registry system operated by the Tajikistan Ministry of Health and Social Protection of individuals (n = 10,700) who had been diagnosed with HIV from 1 January 2010 to 30 May 2023. Individual HIV cases resided in five regions: Districts of Republican Subordination (DRS), Dushanbe (Tajikistan’s capital city), Gorno-Badakhshan Autonomous Oblast (GBAO), Khatlon, and Sughd. We developed logistic regression models to investigate the relationships between key population status and demographic characteristics. GBAO has the largest proportion of labor migrants (49.59%), which is much larger than that of the other regions (<32%). In contrast to other key populations, there was a larger proportion of HIV cases in rural areas that were labor migrants (23.25%) in comparison to urban areas (16.05%). In multivariable analysis, the odds of being a labor migrant were 6.248 (95% CI: 4.811, 8.113), 2.691 (95% CI: 2.275, 3.184), and 1.388 (95% CI: 1.155, 1.668) times larger if a case was residing in GBAO, Sughd, or DRS, compared to Dushanbe, respectively. Our research contributes to the field by proposing to expand the definition of key population to include labor migrants in Central Asia who should be emphasized as a vulnerable population at high risk of HIV. We encourage policy action to provide designated HIV funding for labor migrants, increase international attention, and promote potential modifications of national regulations and/or laws regarding prevention and treatment of HIV among non-citizen populations.

30 March 2026 in BioMedInformatics
Verified
Journal Article
Open access
PDF file
YSYong Si
Yong Si
JFJunyi Fan
Junyi Fan
LSLi Sun
Li Sun
SCShuheng Chen
Shuheng Chen
EPElham Pishgar
Elham Pishgar
MPMaryam Pishgar
Maryam Pishgar
Traumatic Brain Injury (TBI) is a major contributor to mortality among older adults, with geriatric patients facing disproportionately high risk due to age-related physiological vulnerability and comorbidities. Early and accurate prediction of mortality is essential for guiding clinical decision-making and optimizing ICU resource allocation. In this study, we utilized the MIMIC-III database and identified a final analytic cohort of 667 geriatric TBI patients, on which we developed a machine learning framework for 30-day mortality prediction. A rigorous preprocessing pipeline—including Random Forest-based imputation, feature engineering, and hybrid selection—was implemented to refine predictors from 69 to 9 clinically meaningful variables. CatBoost emerged as the top-performing model, achieving an AUROC of 0.867 (95% CI: 0.809–0.922), with a sensitivity of 0.752 and a specificity of 0.888 on the independent test set. SHAP analysis confirmed the importance of the GCS score, oxygen saturation, and prothrombin time as dominant predictors. These findings highlight the potential value of interpretable machine learning tools for early mortality risk stratification in elderly TBI patients and support further validation for future clinical use.

19 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
LSLi Sun
Li Sun
SCShuheng Chen
Shuheng Chen
YSYong Si
Yong Si
JFJunyi Fan
Junyi Fan
MPMaryam Pishgar
Maryam Pishgar
GPGreg Placencia
Greg Placencia
Background: Patients with both diabetes mellitus (DM) and atrial fibrillation (AF) face elevated mortality in intensive care units (ICUs), yet models targeting this high-risk group remain limited. Objective: To develop an interpretable machine learning (ML) model predicting 28-day mortality in ICU patients with concurrent DM and AF using early-phase clinical data. Methods: A retrospective cohort of 1,535 adult ICU patients with DM and AF was extracted from the MIMIC-IV database. Data preprocessing involved median/mode imputation, z-score normalization, and early temporal feature engineering. A two-step feature selection pipeline-univariate filtering (ANOVA F-test) and Random Forest-based multivariate ranking-yielded 19 interpretable features. Seven ML models were trained with stratified 5-fold cross-validation and SMOTE oversampling. Interpretability was assessed via ablation and Accumulated Local Effects (ALE) analysis. Results: Logistic regression achieved the best performance (AUROC: 0.825; 95% CI: 0.779-0.867), surpassing more complex models. Key predictors included RAS, age, bilirubin, and extubation. ALE plots showed intuitive, non-linear effects such as age-related risk acceleration and bilirubin thresholds. Conclusion: This interpretable ML model offers accurate risk prediction and clinical insights for early ICU triage in patients with DM and AF.

12 March 2026 in Viruses
Verified
Journal Article
Open access
PDF file
KAKamiar Alaei
Kamiar Alaei
BKBrian Kwan
Brian Kwan
CLChristopher P. Lounsbery
Christopher P. Lounsbery
AAArash Alaei
Arash Alaei
SYSalomudin J. Yusufi
Salomudin J. Yusufi
AAArash Alaei
Arash Alaei
Viral suppression is a cornerstone of HIV management, essential for improving health outcomes and preventing transmission. However, varying definitions of suppression, ranging from ≤1000 copies/mL (controlled) to ≤200 (clinically suppressed) and ≤50 (untransmittable), complicate the assessment of progress toward global UNAIDS 95–95–95 goals. Our study evaluated progress in achieving viral suppression among people living with HIV (PLHIV) in Tajikistan between 2010 and 2024 using cross-sectional data from the Ministry of Health and Social Protection of Population registry. Viral load was measured using real-time PCR, and suppression was assessed across three thresholds (≤1000, ≤200, ≤50 copies/mL). We examined associations between viral suppression and demographic factors using Chi-square tests and logistic regression models. Across all thresholds, suppression rates remained below the UNAIDS 95-95-95 target goals. At the ≤50 copies/mL threshold, 77% of males and 83% of females achieved suppression, with males demonstrating lower odds of achieving viral suppression. Regional disparities were evident, with Khatlon and Sughd showing the lowest viral suppression rate (72.2% and 76.8%, respectively) and lower odds of achieving viral suppression compared to Dushanbe. Urban–rural differences were also observed (78.3% vs. 81.1%), though odds ratios using logistic regression models were not significant. Findings highlight persistent demographic and regional disparities, underscoring the need for targeted interventions to achieve equitable viral suppression in Tajikistan. Our findings also highlight associations and do not imply causal inference. In addition, authors acknowledge that interpretation of viral suppression outcomes is limited by the absence of data on treatment regimens, duration, adherence, CD4 counts, and behavioral factors.