Mengou Zhu

Mengou Zhu

Auto-generated profile, based on publicly available information

Mengou Zhu

Department of Medicine, Northwestern University Feinberg School of Medicine

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
6 May 2026 in Leukemia
Verified
Journal Article
Open access
MAMichael O. Alberti
Michael O. Alberti
SSSridhar Nonavinkere Srivatsan
Sridhar Nonavinkere Srivatsan
JSJin Shao
Jin Shao
DFDennis L. Fei
Dennis L. Fei
MZMengou Zhu
Mengou Zhu
MWMatthew J. Walter
Matthew J. Walter
Recurrent somatic mutations in the spliceosome genes SF3B1 , SRSF2 , and U2AF1 are frequently identified in patients with myeloid neoplasms, such as myelodysplastic syndromes. We characterized the in vivo consequences of expressing two hotspot mutations in U2AF1 that code for the S34F and Q157R substitutions. Our results indicate that the two mutations induce distinct hematopoietic phenotypes in mice, suggesting that the U2AF1 S34F and U2AF1 Q157R mutations should not be conflated as they may impact disease pathogenesis differently in patients. Mice expressing U2af1 S34F have a more severe reduction in their blood and bone marrow cell counts and reduced stem cell repopulating ability, compared to mice expressing U2af1 Q157R . The expression and splicing of target genes are largely unique between the mutations, in both mouse and human samples, potentially driving the phenotypic differences induced by either mutation. The two mutations co-occur with different gene mutations in patients and are not equally represented across myeloid neoplasms, suggesting that multiple mechanisms likely drive U2AF1-mutant disease pathogenesis. Collectively, our results support that U2AF1 S34F and U2AF1 Q157R mutations induce distinct hematopoietic, gene expression, and RNA splicing phenotypes in vivo. Larger population studies will be needed to determine if these phenotypic changes translate into clinico-pathologic differences in patients, warranting separate classification.

10 September 2024 in medRxiv
Verified
Preprint
Open access
PDF file
MZMengou Zhu
Mengou Zhu
CPChiagozie Pickens
Chiagozie Pickens
NMNikolay S. Markov
Nikolay S. Markov
APAnna Pawlowski
Anna Pawlowski
MKMengjia Kang
Mengjia Kang
TIThe NU SCRIPT Study Investigators
The NU SCRIPT Study Investigators
Background Antibiotic stewardship in critically ill pneumonia patients is crucial yet challenging, partly due to the limited diagnostic yield of noninvasive infectious tests. In this study, we report an antibiotic prescription pattern informed by bronchoalveolar lavage (BAL) results, where clinicians de-escalate antibiotics based on the combination of quantitative cultures and multiplex PCR rapid diagnostic tests. Methods We analyzed data from SCRIPT, a single-center prospective cohort study of mechanically ventilated patients who underwent a BAL for suspected pneumonia. We used the novel Narrow Antibiotic Therapy (NAT) score to quantify day-by-day antibiotic prescription pattern for each suspected pneumonia episode etiology (bacterial, viral, mixed bacterial/viral, microbiology-negative, and non-pneumonia control). We also analyzed and compared clinical outcomes for each pneumonia etiology, including unfavorable outcomes (a composite of in-hospital mortality, discharge to hospice, or requiring lung transplantation during hospitalization), duration of ICU stay, and duration of intubation. Clinical outcomes were compared with the Mann-Whitney U test and Fisher’s exact test. Results We included 686 patients with 927 pneumonia episodes. NAT score analysis indicated that an antibiotic de-escalation pattern was evident in all pneumonia etiologies except resistant bacterial pneumonia. Microbiology-negative pneumonia was treated similarly to susceptible bacterial pneumonia in terms of antibiotic spectrum. Over a quarter of the time in viral pneumonia episodes, antibiotics were completely discontinued. Unfavorable outcomes were comparable across all pneumonia etiologies. Patients with viral and mixed bacterial/viral pneumonia had longer durations of ICU stay and intubation. Conclusions BAL quantitative cultures and multiplex PCR rapid diagnostic tests resulted in prompt antibiotic de-escalation in critically ill pneumonia patients. There was no evidence of increased incidence of unfavorable outcomes. Key points We found that bronchoalveolar lavage-based diagnostics is associated with antibiotic de-escalation, including to no antibiotics in more than a quarter of cases where only a virus is recovered.

30 June 2024 in medRxiv
Verified
Preprint
Open access
PDF file
SFSamuel W Fenske
Samuel W Fenske
APAlec Peltekian
Alec Peltekian
MKMengjia Kang
Mengjia Kang
NMNikolay S Markov
Nikolay S Markov
MZMengou Zhu
Mengou Zhu
TIthe NU SCRIPT Study Investigators
the NU SCRIPT Study Investigators
Background Criteria to identify patients who are ready to be liberated from mechanical ventilation are imprecise, often resulting in prolonged mechanical ventilation or reintubation, both of which are associated with adverse outcomes. Daily protocol-driven assessment of the need for mechanical ventilation leads to earlier extubation but requires dedicated personnel. We sought to determine whether machine learning applied to the electronic health record could predict successful extubation. Methods We examined 37 clinical features from patients from a single-center prospective cohort study of patients in our quaternary care medical ICU who required mechanical ventilation and underwent a bronchoalveolar lavage for known or suspected pneumonia. We also tested our models on an external test set from a community hospital ICU in our health care system. We curated electronic health record data aggregated from midnight to 8AM and labeled extubation status. We deployed three data encoding/imputation strategies and built XGBoost, LightGBM, logistic regression, LSTM, and RNN models to predict successful next-day extubation. We evaluated each model’s performance using Area Under the Receiver Operating Characteristic (AUROC), Area Under the Precision Recall Curve (AUPRC), Sensitivity (Recall), Specificity, PPV (Precision), Accuracy, and F1-Score. Results Our internal cohort included 696 patients and 9,828 ICU days, and our external cohort had 333 patients and 2,835 ICU days. The best model (LSTM) predicted successful extubation on a given ICU day with an AUROC 0.87 (95% CI 0.834-0.902) and the internal test set and 0.87 (95% CI 0.848-0.885) on the external test set. A Logistic Regression model performed similarly (AUROC 0.86 internal test, 0.83 external test). Across multiple model types, measures previously demonstrated to be important in determining readiness for extubation were found to be most informative, including plateau pressure and Richmond Agitation Sedation Scale (RASS) score. Our model often predicted patients to be stable for extubation in the days preceding their actual extubation, with 63.8% of predicted extubations occurring within three days of true extubation. We also tested the best model on cases of failed extubations (requiring reintubation within two days) not seen by the model during training. Our best model would have identified 35.4% (17/48) of these cases in the internal test set and 48.1% (13/27) cases in the external test set as unlikely to be successfully extubated. Conclusions Machine learning models can accurately predict the likelihood of extubation on a given ICU day from data available in the electronic health record. Predictions from these models are driven by clinical features that have been associated with successful extubation in clinical trials.

27 November 2025 in CHEST Critical Care
Verified
Journal Article
Open access
MZMengou Zhu
Mengou Zhu
WLWan-Ting Liao
Wan-Ting Liao
APAlec Peltekian
Alec Peltekian
NMNikolay S. Markov
Nikolay S. Markov
MKMengjia Kang
Mengjia Kang
CGCatherine A. Gao
Catherine A. Gao

26 December 2025 in The Joint Commission Journal on Quality and Patient Safety
Verified
Journal Article
Closed access
GMGabrielle Matias
Gabrielle Matias
MZMengou Zhu
Mengou Zhu
NNNandita R. Nadig
Nandita R. Nadig
JCJohn M. Coleman
John M. Coleman
MPMichelle Prickett
Michelle Prickett
SRSusan R. Russell
Susan R. Russell

16 July 2025 in medRxiv
Verified
Preprint
Open access
PDF file
MZMengou Zhu
Mengou Zhu
WLWan-Ting Liao
Wan-Ting Liao
APAlec Peltekian
Alec Peltekian
NMNikolay S. Markov
Nikolay S. Markov
MKMengjia Kang
Mengjia Kang
CGCatherine A. Gao
Catherine A. Gao
Severe community-acquired pneumonia (CAP) remains a major cause of critical illness, yet there are no validated early clinical criteria to predict short-term treatment outcomes in these patients. Short-term pneumonia treatment outcomes are less affected by confounding factors introduced by a prolonged hospital course, and early prediction of short-term treatment outcomes can help physicians identify those who are likely to fail the current treatment and implement adjustments to existing diagnostic and therapeutic plans. Traditional clinical stability criteria such as Halm’s criteria are not calibrated for early outcome prediction in critically ill severe pneumonia patients. We applied the XGBoost algorithm to predict pneumonia cure by day 7-8 post- intubation with clinical features from days 1-3 in mechanically ventilated patients with severe CAP from the Successful Clinical Response in Pneumonia Therapy (SCRIPT) study, a prospective cohort study at a tertiary academic center. Pneumonia episodes were adjudicated for day 7-8 cure status by a panel of critical care physicians using a structured review process. Clinical features that inform Halm’s criteria, including vital signs, oxygenation parameters, mental status, and vasopressor use, were extracted from the electronic health record. We also examined model performance by including additional features, such as laboratory data, ventilator settings, and medications. Basic demographic characteristics including age and BMI were also incorporated. Among 85 patients, 42 (49.4%) were cured by day 7–8. The best-performing model, which used Halm’s clinical features and ventilator features from days 1–3, achieved a cross-validated AUROC of 0.757. Inclusion of lab and medication data did not significantly improve performance. Key predictors included GCS, norepinephrine requirement, and BMI. We prove the feasibility of using ML models to predict short-term treatment outcomes of severe CAP among critically ill patients with basic clinical features. Future studies should focus on external validation and clinical integration to inform prognosis and early reevaluation of treatment strategy in patients with predicted poor outcomes.