Ziqi Xu

Ziqi Xu

Auto-generated profile, based on publicly available information

Ziqi Xu

Washington University in St. Louis, Department of Computer Science and Engineering; AI for Health Institute, St. Louis, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
4 May 2023 in Artificial Organs
Verified
Journal Article
Closed access
NSNeel Shah
Neel Shah
BXBing Xue
Bing Xue
ZXZiqi Xu
Ziqi Xu
HYHanqing Yang
Hanqing Yang
EMEva Marwali
Eva Marwali
STSofia Tejada
Sofia Tejada

22 August 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
CNClaire Najjuuko
Claire Najjuuko
ZXZiqi Xu
Ziqi Xu
SKSamuel Kizito
Samuel Kizito
CLChenyang Lu
Chenyang Lu
FSFred M. Ssewamala
Fred M. Ssewamala
Under-five mortality remains a global health issue, especially in sub-Saharan Africa, where preventable conditions largely drive the high mortality rates. Understanding the heterogeneity in utilization of reproductive, maternal, newborn, and child health services is crucial for reducing under-five mortality. Here we show that among 9307 under-five mortality cases across 31 sub-Saharan African countries (2014–2024), maternal and child health service utilization falls into three distinct patterns—lowest, medium, and highest. Socioeconomic status strongly predicts subgroup membership: higher maternal education, employment, urban residence, and wealth are associated with lower odds of being in the lowest utilization group. Inequality indices further reveal disparities by education, wealth, residence, and employment. Our findings show a strong link between socioeconomic status and maternal and child health services utilization. To address under-five mortality in sub-Saharan Africa, targeted strategies are needed to improve access and uptake of essential health services among socioeconomically disadvantaged groups.

13 May 2024 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
ZXZiqi Xu
Ziqi Xu
JZJingwen Zhang
Jingwen Zhang
JGJacob K. Greenberg
Jacob K. Greenberg
MFMadelyn Frumkin
Madelyn Frumkin
SJSaad Javeed
Saad Javeed
CLChenyang Lu
Chenyang Lu
Pre-operative prediction of post-surgical recovery for patients is vital for clinical decision-making and personalized treatments, especially with lumbar spine surgery, where patients exhibit highly heterogeneous outcomes. Existing predictive tools mainly rely on traditional Patient-Reported Outcome Measures (PROMs), which fail to capture the long-term dynamics of patient conditions before the surgery. Moreover, existing studies focus on predicting a single surgical outcome. However, recovery from spine surgery is multi-dimensional, including multiple distinctive but interrelated outcomes, such as pain interference, physical function, and quality of recovery. In recent years, the emergence of smartphones and wearable devices has presented new opportunities to capture longitudinal and dynamic information regarding patients' conditions outside the hospital. This paper proposes a novel machine learning approach, Multi-Modal Multi-Task Learning (M3TL), using smartphones and wristbands to predict multiple surgical outcomes after lumbar spine surgeries. We formulate the prediction of pain interference, physical function, and quality of recovery as a multi-task learning (MTL) problem. We leverage multi-modal data to capture the static and dynamic characteristics of patients, including (1) traditional features from PROMs and Electronic Health Records (EHR), (2) Ecological Momentary Assessment (EMA) collected from smartphones, and (3) sensing data from wristbands. Moreover, we introduce new features derived from the correlation of EMA and wearable features measured within the same time frame, effectively enhancing predictive performance by capturing the interdependencies between the two data modalities. Our model interpretation uncovers the complementary nature of the different data modalities and their distinctive contributions toward multiple surgical outcomes. Furthermore, through individualized decision analysis, our model identifies personal high risk factors to aid clinical decision making and approach personalized treatments. In a clinical study involving 122 patients undergoing lumbar spine surgery, our M3TL model outperforms a diverse set of baseline methods in predictive performance, demonstrating the value of integrating multi-modal data and learning from multiple surgical outcomes. This work contributes to advancing personalized peri-operative care with accurate pre-operative predictions of multi-dimensional outcomes.

9 June 2025 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
ZXZiqi Xu
Ziqi Xu
JZJingwen Zhang
Jingwen Zhang
SHSimon Haroutounian
Simon Haroutounian
HLHanyang Liu
Hanyang Liu
ZCZihan Cao
Zihan Cao
CLChenyang Lu
Chenyang Lu
Persistent postoperative pain (PPSP) is a significant concern in perioperative care, affecting patient quality of life and clinical outcomes. While traditional clinical data may capture patient-reported and objective physiological data in clinical settings, Ecological Momentary Assessment (EMA) collected using smartphones offers dynamic insights into patients' mental and emotional states in their natural environments. However, the self-reported nature of EMA introduces significant variability in both data quality and patient compliance. This variability is often overlooked in studies, where EMA data is treated as contributing equally for all patients. In this paper, we propose an end-to-end approach that addresses this challenge by first quantifying the prediction uncertainty for each data source, including both EMA and clinical data. Next, we integrate the uncertainties into the final decision-making process by assigning more weight to more reliable data sources at the individual level, improving overall predictive performance. Compared to traditional models, our model provides uncertainty estimates for each decision, offering clinicians critical insight into the trustworthiness of predictions. Finally, we conduct both qualitative and quantitative analysis to demonstrate the impact of our uncertainty estimates. Validated through a prospective clinical study involving 782 patients undergoing surgery, our approach achieves superior predictive performance and calibration in PPSP prediction. This work is expected to contribute to personalized perioperative care by effectively integrating traditional clinical and mobile sensing data through an end-to-end uncertainty-aware framework.

4 August 2023
Verified
Conference Paper
Open access
BXBing Xue
Bing Xue
@AhmedSaidICU Said@AhmedSaidICU Said
@AhmedSaidICU Said
ZXZiqi Xu
Ziqi Xu
HLHanyang Liu
Hanyang Liu
NSNeel Shah
Neel Shah
CLChenyang Lu
Chenyang Lu
Extracorporeal membrane oxygenation (ECMO) is an essential life-supporting modality for COVID-19 patients who are refractory to conventional therapies. However, the proper treatment decision has been the subject of significant debate and it remains controversial about who benefits from this scarcely available and technically complex treatment option. To support clinical decisions, it is a critical need to predict the treatment need and the potential treatment and no-treatment responses. Targeting this clinical challenge, we propose Treatment Variational AutoEncoder (TVAE), a novel approach for individualized treatment analysis. TVAE is specifically designed to address the modeling challenges like ECMO with strong treatment selection bias and scarce treatment cases. TVAE conceptualizes the treatment decision as a multi-scale problem. We model a patient's potential treatment assignment and the factual and counterfactual outcomes as part of their intrinsic characteristics that can be represented by a deep latent variable model. The factual and counterfactual prediction errors are alleviated via a reconstruction regularization scheme together with semi-supervision, and the selection bias and the scarcity of treatment cases are mitigated by the disentangled and distribution-matched latent space and the label-balancing generative strategy. We evaluate TVAE on two real-world COVID-19 datasets: an international dataset collected from 1651 hospitals across 63 countries, and a institutional dataset collected from 15 hospitals. The results show that TVAE outperforms state-of-the-art treatment effect models in predicting both the propensity scores and factual outcomes on heterogeneous COVID-19 datasets. Additional experiments also show TVAE outperforms the best existing models in individual treatment effect estimation on the synthesized IHDP benchmark dataset.

19 December 2025 in The Journal of Pain
Verified
Journal Article
Open access
MFMadelyn R. Frumkin
Madelyn R. Frumkin
JZJingwen Zhang
Jingwen Zhang
ZXZiqi Xu
Ziqi Xu
SYSalim Yakdan
Salim Yakdan
BBBraeden Benedict
Braeden Benedict
JGJacob K. Greenberg
Jacob K. Greenberg
Movement-evoked pain (MEP) may be a useful metric for phenotyping musculoskeletal pain conditions. However, there is significant disagreement over operationalization, and no studies have assessed stability of MEP over time. Fitbit and Ecological Momentary Assessment (EMA) data were collected from adults with moderate-to-severe chronic pain schedule to receive lumbar/thoracolumbar fusion surgery (N=114). On average, participants provided 323 h of Fitbit data and 74 EMA surveys (84% completion rate). To mimic task-based assessment of MEP using the 6-minute walk test, EMA pain ratings completed within 3 h of walking at a speed ≥70spm for at least 6 min were extracted. Of the full sample, 91 individuals (80%) had any instances of pain ratings following 6-minute activity bouts (Median=6, SD=11). Post-activity pain scores exhibited good within-person consistency (ICC=.76). However, between-person differences in average pain accounted for >70% of the variance in post-activity pain. MEP change scores defined as the difference between post-activity and pre-activity pain scores had poor reliability (ICC =.08). MEP change scores were not associated with average pain or factors related to the uncontrolled nature of digital assessment (e.g., activity amount, time from activity to pain report). However, MEP change scores tended to be lower when the preceding pain rating was elevated (β = -7.96, 95% Credible Interval: -9.28, -6.66), suggesting ceiling effects. Small effects of time of day and prior activity were also observed, which could contaminate MEP assessed in the lab or clinic. Continued development of digital methodologies for assessing MEP is recommended. PERSPECTIVE: Existing movement-evoked pain assessments have limitations. Post-activity pain ratings capture overall disability and day-to-day fluctuations in pain, rather than the relationship between movement and pain. Pre-to-post activity change scores had poor reliability when assessed naturalistically and over time. Digital methodologies capture movement-evoked pain continuously across time, contexts, and real-world environments.