ALAndrew Li

Andrew Li

*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


Andrew Li has a total of 208 co-authors. Here are the top co-authors by number of shared publications:

  • Jason Phua

    Division of Respiratory and Critical Care Medicine, Department of Medicine, National University Hospital, National University Health System, Singapore, Singapore

    4 shared publications
  • Amartya Mukhopadhyay

    Division of Respiratory and Critical Care Medicine, Department of Medicine, National University Hospital, National University Health System, Singapore

    3 shared publications
  • Colin Sumners

    Department of Physiology and Functional Genomics, University of Florida, Gainesville, FL, U.S.A.

    3 shared publications
  • Haifa Zheng

    3 shared publications
  • Hongyan Du

    Department of Rheumatology and Clinical Immunology, Zhujiang Hospital, Southern Medical University, Guangzhou, China

    3 shared publications
  • Jinlong Li

    Department of Clinical Laboratory, the Second Hospital of Nanjing, Nanjing University of Chinese Medicine, Nanjing, 210003, China

    3 shared publications

Latest Publications

  • Are We Closer to Predicting Radiological Progression Among ILD Patients?

    by Andrew Li, Tamera J Corte

  • Open Access

    Interpretable Forecasting of Irregular Vital Signs with a Missing-Aware Neuro-Fuzzy Inference Framework

    by Zhuoxuan Zhan, Li Rong Wang, Chang Cai, Yunkai Andrew Li, Yih Yng Ng, Xiuyi Fan

    Background and Objectives: Forecasting vital-sign trajectories from routinely collected clinical data can support patient monitoring by anticipating short-term physiological changes before predefined deterioration thresholds are crossed. In practice, however, vital-sign time series are often sparse and irregularly sampled, and missingness patterns may themselves reflect clinical processes rather than random noise. These characteristics challenge conventional forecasting models and complicate clinical interpretation. This study proposes an interpretable forecasting framework for irregular multivariate vital-sign time series.Methods: We developed a Missing-Aware Fuzzy Inference Network (MAFIN) for short-term forecasting of irregular vital signs. MAFIN explicitly distinguishes observed, missing, and padded entries during input encoding, allowing missingness patterns to contribute directly to prediction. The model combines an evolving rule-based global inference module with a lightweight local temporal estimator, and fuses the two streams using a confidence signal derived from rule support. We evaluated MAFIN on four real-world critical-care datasets, MIMIC-III, PhysioNet Challenge 2012, eICU, and INSPIRE, under both full-history and rolling forecasting protocols, and compared it with strong baselines for irregular time-series prediction.Results: Across the four datasets and two evaluation protocols, MAFIN achieved competitive and often superior forecasting performance relative to baseline methods. It obtained the best or second-best RMSE in nearly all settings, with particularly consistent performance on MIMIC-III and INSPIRE, while remaining competitive on PhysioNet 2012 and eICU. In addition to predictive performance, the model generated intrinsic clinician-readable IF–THEN rules for each prediction, supporting case-level interpretability without requiring post-hoc explanation methods.Conclusions: Explicit modeling of missingness and intrinsic rule-based reasoning can provide an effective computational approach for forecasting irregular vital-sign trajectories. The proposed framework combines competitive predictive performance with transparent case-level explanations, supporting retrospective auditability in biomedical monitoring settings and offering a useful basis for future interpretable clinical forecasting research.

  • Open Access

    Accurate contextual reporting amidst dynamic AI curricula development: A response to Zainal and colleagues

    by Li Yunkai Andrew, Quek Yong Jing Daniel, Minyang Chow, Bernett Lee, Jennifer Cleland, Chia Faith Li‐Ann

  • Open Access

    Implications of the 2022 lung function update and GLI global reference equations among patients with interstitial lung disease

    by Andrew Li, Alan Teoh, Lauren Troy, Ian Glaspole, Margaret L Wilsher, Sally de Boer, Jeremy Wrobel, Yuben P Moodley, Francis Thien, Henry Gallagher, et al.

    Background Lung function testing remains a cornerstone in the assessment and management of interstitial lung disease (ILD) patients. The clinical implications of the Global Lung function Initiative (GLI) reference equations and the updated interpretation strategies remain uncertain. Methods Adult patients with ILD with baseline forced vital capacity (FVC) were included from the Australasian ILD registry and the National Healthcare Group ILD registry, Singapore. The European Coal and Steel Community and Miller reference equations were compared with the GLI reference equations to assess (a) differences in lung function percent predicted values; (b) ILD risk prediction models and (c) eligibility for ILD clinical trial enrolment. Results Among 2219 patients with ILD, 1712 (77.2%) were white individuals. Idiopathic pulmonary fibrosis (IPF), connective tissue disease-associated ILD and unclassifiable ILD predominated. Median FVC was 2.60 (2.01–3.36) L, forced expiratory volume in 1 s was 2.09 (1.67–2.66) L and diffusing capacity of the lungs for carbon monoxide (DLCO) was 13.60 (10.16–17.60) mL/min/mm Hg. When applying the GLI reference equations, the mean FVC percentage predicted was 8.8% lower (87.7% vs 78.9%, pConclusion Applying the GLI reference equations in patients with ILD leads to higher DLCO percentage predicted values and smaller lung volume percentage predicted values. While applying the GLI reference equations did not impact on prognostication, fewer patients met the clinical trial criteria for antifibrotic agents.


  • Open Access

    Supplemental Table S1 from Angiotensin-(1-7) Decreases Cell Growth and Angiogenesis of Human Nasopharyngeal Carcinoma Xenografts

    by Nana Pei, Renqiang Wan, Xinglu Chen, Andrew Li, Yanling Zhang, Jinlong Li, Hongyan Du, Baihong Chen, Wenjin Wei, Yanfei Qi, et al.

    Supplemental Table S1. Primers for real-time RT-PCR

  • Open Access

    Supplemental Table S1 from Angiotensin-(1-7) Decreases Cell Growth and Angiogenesis of Human Nasopharyngeal Carcinoma Xenografts

    by Nana Pei, Renqiang Wan, Xinglu Chen, Andrew Li, Yanling Zhang, Jinlong Li, Hongyan Du, Baihong Chen, Wenjin Wei, Yanfei Qi, et al.

    Supplemental Table S1. Primers for real-time RT-PCR

  • Open Access

    Supplemental Figure S2 from Angiotensin-(1-7) Decreases Cell Growth and Angiogenesis of Human Nasopharyngeal Carcinoma Xenografts

    by Nana Pei, Renqiang Wan, Xinglu Chen, Andrew Li, Yanling Zhang, Jinlong Li, Hongyan Du, Baihong Chen, Wenjin Wei, Yanfei Qi, et al.

    Supplemental Figure S2. AAV8 (Y733F)-CBA-Ang-(1-7) and AAV8 (Y733F)-CBA-eGFP mediated transduction of Ang-(1-7) fusion protein and eGFP in mouse liver.

  • Open Access

    Which Endoscopic Procedure to Use and in What Patient? Valves, Coils, Foam, and Heat in COPD and Asthma

    by Andrew Li, Pyng Lee

    Despite the latest developments in therapeutic agents targeting airway endotypes, a significant proportion of patients with asthma and chronic obstructive pulmonary disease (COPD) remain symptomatic. Endoscopic therapies have a complementary role in the management of these airway diseases. The sustained efficacy of bronchial thermoplasty (BT) among patients with asthma over 10 years has been encouraging, as it has been shown to improve symptom control and reduce hospital admissions and exacerbations. Studies suggest that BT helps ameliorate airway inflammation and reduce airway smooth muscle thickness. While studies suggest that it is as effective as biologic agents, its role in the management of severe asthma has yet to be clearly defined and GINA 2022 still suggests limiting its use to patients with characteristics of the various populations studied. Conversely, bronchoscopic lung volume reduction has shown promise among patients with advanced COPD. Rigorous patient selection is important. Patients with minimal collateral ventilation (CV) and higher heterogeneity index have shown to benefit the most from endobronchial valve (EBV) therapy. For those with ongoing CV, endobronchial coils would be more appropriate. Both therapeutic modalities have demonstrated improved quality of life, effort tolerance, and lung function indices among appropriately selected patients. The emerging evidence suggests that endoscopic procedures among airway disease still have a substantial role to play despite the development of new therapeutic options.


  • Top Cited Papers

    Epidemiology, Management, and Outcomes of Sepsis in ICUs among Countries of Differing National Wealth across Asia

    by Andrew Li, Lowell Ling, Hanyu Qin, Yaseen M Arabi, Sheila Nainan Myatra, Moritoki Egi, Je Hyeong Kim, Mohd Basri Mat Nor, Do Ngoc Son, Wen-Feng Fang, et al.

    Rationale: Directly comparative data on sepsis epidemiology and sepsis bundle implementation in countries of differing national wealth remain sparse. Objectives: To evaluate across countries/regions of differing income status in Asia 1) the prevalence, causes, and outcomes of sepsis as a reason for ICU admission and 2) sepsis bundle (antibiotic administration, blood culture, and lactate measurement) compliance and its association with hospital mortality. Methods: A prospective point prevalence study was conducted among 386 adult ICUs from 22 Asian countries/regions. Adult ICU participants admitted for sepsis on four separate days (representing the seasons of 2019) were recruited. Measurements and Main Results: The overall prevalence of sepsis in ICUs was 22.4% (20.9%, 24.5%, and 21.3% in low-income countries/regions [LICs]/lower middle-income countries/regions [LMICs], upper middle-income countries/regions, and high-income countries/regions [HICs], respectively; P < 0.001). Patients were younger and had lower severity of illness in LICs/LMICs. Hospital mortality was 32.6% and marginally significantly higher in LICs/LMICs than HICs on multivariable generalized mixed model analysis (adjusted odds ratio, 1.84; 95% confidence interval, 1.00–3.37; P = 0.049). Sepsis bundle compliance was 21.5% at 1 hour (26.0%, 22.1%, and 16.2% in LICs/LMICs, upper middle-income countries/regions, and HICs, respectively; P < 0.001) and 36.6% at 3 hours (39.3%, 32.8%, and 38.5%, respectively; P = 0.001). Delaying antibiotic administration beyond 3 hours was the only element independently associated with increased mortality (adjusted odds ratio, 2.53; 95% confidence interval, 2.07–3.08; P < 0.001). Conclusions: Sepsis is a common cause of admission to Asian ICUs. Mortality remains high and is higher in LICs/LMICs after controlling for confounders. Sepsis bundle compliance remains low. Delaying antibiotic administration beyond 3 hours from diagnosis is associated with increased mortality. Clinical trial registered with www.ctri.nic.in (CTRI/2019/01/016898).


  • High-flow nasal cannula therapy: A multicentred survey of the practices among physicians and respiratory therapists in Singapore

    by Ser Hon Puah, Andrew Li, Matthew Edward Cove, Jason Phua, Vicky Ng, Amit Kansal, Qiao Li Tan, Juliet Tolentino Sahagun, Juvel Taculod, Addy Yong-Hu Tan, et al.