Meng Li

Meng Li

Auto-generated profile, based on publicly available information

Meng Li

University of Illinois at Urbana-Champaign

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
27 April 2021 in JMIR Cancer
Verified
Journal Article
Open access
CLCarissa A Low
Carissa A Low
MLMeng Li
Meng Li
JVJulio Vega
Julio Vega
KDKrina C Durica
Krina C Durica
DFDenzil Ferreira
Denzil Ferreira
ADAnind Dey
Anind Dey
Background: Cancer treatments can cause a variety of symptoms that impair quality of life and functioning but are frequently missed by clinicians. Smartphone and wearable sensors may capture behavioral and physiological changes indicative of symptom burden, enabling passive and remote real-time monitoring of fluctuating symptoms Objective: The aim of this study was to examine whether smartphone and Fitbit data could be used to estimate daily symptom burden before and after pancreatic surgery. Methods: A total of 44 patients scheduled for pancreatic surgery participated in this prospective longitudinal study and provided sufficient sensor and self-reported symptom data for analyses. Participants collected smartphone sensor and Fitbit data and completed daily symptom ratings starting at least two weeks before surgery, throughout their inpatient recovery, and for up to 60 days after postoperative discharge. Day-level behavioral features reflecting mobility and activity patterns, sleep, screen time, heart rate, and communication were extracted from raw smartphone and Fitbit data and used to classify the next day as high or low symptom burden, adjusted for each individual’s typical level of reported symptoms. In addition to the overall symptom burden, we examined pain, fatigue, and diarrhea specifically. Results: Models using light gradient boosting machine (LightGBM) were able to correctly predict whether the next day would be a high symptom day with 73.5% accuracy, surpassing baseline models. The most important sensor features for discriminating high symptom days were related to physical activity bouts, sleep, heart rate, and location. LightGBM models predicting next-day diarrhea (79.0% accuracy), fatigue (75.8% accuracy), and pain (79.6% accuracy) performed similarly. Conclusions: Results suggest that digital biomarkers may be useful in predicting patient-reported symptom burden before and after cancer surgery. Although model performance in this small sample may not be adequate for clinical implementation, findings support the feasibility of collecting mobile sensor data from older patients who are acutely ill as well as the potential clinical value of mobile sensing for passive monitoring of patients with cancer and suggest that data from devices that many patients already own and use may be useful in detecting worsening perioperative symptoms and triggering just-in-time symptom management interventions.

12 January 2023 in JMIR Perioperative Medicine
Verified
Journal Article
Open access
CLCarissa A Low
Carissa A Low
MDMichaela Danko
Michaela Danko
KDKrina C Durica
Krina C Durica
JVJulio Vega
Julio Vega
MLMeng Li
Meng Li
JJJohn M. M. Jakicic
John M. M. Jakicic
Background: Sedentary behavior (SB) is prevalent after abdominal cancer surgery, and interventions targeting perioperative SB could improve postoperative recovery and outcomes. We conducted a pilot study to evaluate the feasibility and preliminary effects of a real-time mobile intervention that detects and disrupts prolonged SB before and after cancer surgery, relative to a monitoring-only control condition. Objective: Our aim was to evaluate the feasibility and preliminary effects of a perioperative SB intervention on objective activity behavior, patient-reported quality of life and symptoms, and 30-day readmissions. Methods: Patients scheduled for surgery for metastatic gastrointestinal cancer (n=26) were enrolled and randomized to receive either the SB intervention or activity monitoring only. Both groups used a Fitbit smartwatch and companion smartphone app to rate daily symptoms and collect continuous objective activity behavior data starting from at least 10 days before surgery through 30 days post discharge. Participants in the intervention group also received prompts to walk after any SB bout that exceeded a prespecified threshold, with less frequent prompts on days that patients reported more severe symptoms. Participants completed end-of-study ratings of acceptability, and we also examined adherence to assessments and to walking prompts. In addition, we examined effects of the intervention on objective SB and step counts, patient-reported quality of life and depressive and physical symptoms, as well as readmissions. Results: Accrual (74%), retention (88%), and acceptability ratings (mean overall satisfaction 88.5/100, SD 9.1) were relatively high. However, adherence to assessments and engagement with the SB intervention decreased significantly after surgery and did not recover to preoperative levels after postoperative discharge. All participants exhibited significant increases in SB and symptoms and decreases in steps and quality of life after surgery, and participants randomized to the SB intervention unexpectedly had longer maximum SB bouts relative to the control group. No significant benefits of the intervention with regard to activity, quality of life, symptoms, or readmission were observed. Conclusions: Perioperative patients with metastatic gastrointestinal cancer were interested in a real-time SB intervention and rated the intervention as highly acceptable, but engagement with the intervention and with daily symptom and activity monitoring decreased significantly after surgery. There were no significant effects of the intervention on step counts, patient-reported quality of life or symptoms, and postoperative readmissions, and there was an apparent adverse effect on maximum SB. Results highlight the need for additional work to modify the intervention to make reducing SB and engaging with mobile health technology after abdominal cancer surgery more feasible and beneficial. Trial Registration: ClinicalTrials.gov NCT03211806; https://tinyurl.com/3napwkkt

18 August 2020 in JMIR Preprints
Verified
Preprint
Open access
JVJulio Vega
Julio Vega
MLMeng Li
Meng Li
KAKwesi Aguillera
Kwesi Aguillera
NGNikunj Goel
Nikunj Goel
EJEchhit Joshi
Echhit Joshi
CLCarissa A Low
Carissa A Low
BACKGROUND Smartphone and wearable devices are widely used in behavioral and clinical research to collect longitudinal data that, along with ground truth data, are used to create models of human behavior. Mobile sensing researchers often program analysis code from scratch even though many research teams collect data from similar mobile sensors, platforms and devices. As a result, the quality of code varies, code is often not shared alongside publications, and when it is, it might not be stored on a version control system and most of the time there is no guarantee the development environment can be replicated. This makes it difficult for other scientists to read, reuse, audit, and reproduce a publication’s code and its results. OBJECTIVE We present RAPIDS, a reproducible pipeline to standardize the preprocessing, feature extraction, analysis, visualization, and reporting of data streams coming from mobile sensors. METHODS RAPIDS is formed by a group of R and Python scripts that are executed on top of reproducible virtual environments, orchestrated by Snakemake and organized following the cookiecutter data science project. Its development has been and will be informed by public discussions with the mobile sensing research community. RESULTS We share open source, documented, extensible and tested code to preprocess and extract behavioral features from data collected with the AWARE Framework in Android and iOS smartphones as well as Fitbit devices. We also provide a file structure and development environment that other researchers can follow to publish their own models, visualizations, and reports. CONCLUSIONS RAPIDS allows researchers to process mobile sensor data in a rigorous and reproducible way. This saves time and effort during the data analysis phase of a project and makes it easier to share an analysis workflow alongside publications.

26 July 2022 in JMIR Preprints
Verified
Preprint
Open access
CLCarissa A. Low
Carissa A. Low
MDMichaela Danko
Michaela Danko
KDKrina C. Durica
Krina C. Durica
JVJulio Vega
Julio Vega
MLMeng Li
Meng Li
JJJohn M. Jakicic
John M. Jakicic
BACKGROUND Sedentary behavior (SB) is prevalent after abdominal cancer surgery, and interventions targeting perioperative SB could improve postoperative recovery and outcomes. We conducted a pilot study to evaluate the feasibility and preliminary effects of a real-time mobile intervention that detects and disrupts prolonged SB before and after cancer surgery, relative to a monitoring-only control condition. OBJECTIVE To evaluate the feasibility and preliminary effects of a perioperative SB intervention on objective activity behavior, patient-reported quality of life and symptoms, and 30-day readmissions. METHODS Patients scheduled for surgery for metastatic gastrointestinal cancer (n = 26) were enrolled and randomized to receive either the SB intervention or activity-monitoring only. Both groups used a Fitbit smartwatch and companion smartphone app to rate daily symptoms and to collect continuous objective activity behavior data starting from at least 10 days before surgery through 30 days post-discharge. Participants in the Intervention group also received prompts to walk after any SB bout that exceeded a prespecified threshold, with less frequent prompts on days that patients reported more severe symptoms. Participants completed end-of-study ratings of acceptability, and we also examined adherence to assessments and to walking prompts. In addition, we examined effects of the intervention on objective SB and step counts, patient-reported quality of life and depressive and physical symptoms and readmissions. RESULTS Accrual (74%), retention (88%), and acceptability ratings were relatively high. However, adherence to assessments and engagement with the SB intervention decreased significantly after surgery and did not recover to preoperative levels after postoperative discharge. All participants exhibited significant increases in SB and symptoms and decreases in steps and quality of life after surgery, and participants randomized to the SB intervention unexpectedly had longer maximum SB bouts relative to the control group. No significant benefits of the intervention with regard to activity, quality of life, symptoms, or readmission were observed. CONCLUSIONS Perioperative patients with metastatic gastrointestinal were interested in a real-time SB intervention and rated the intervention as highly acceptable, but engagement with the intervention and with daily symptom and activity monitoring decreased significantly after surgery. There were no significant effects of the intervention on step counts, patient-reported quality of life or symptoms, or postoperative readmissions and there was an apparent adverse effect on maximum SB. Results highlight the need for additional work to modify the intervention to make reducing SB and engaging with mobile health technology after abdominal cancer surgery more feasible and beneficial. CLINICALTRIAL NCT03211806

10 July 2024
Verified
Dataset
Open access
PDF file
MLMeng Li
Meng Li
TMTimothy McPhillips
Timothy McPhillips
BLBertram Ludäscher
Bertram Ludäscher
Geist is a new templating language for declarative data manipulation, query, and report generation. Building on the Jinja template engine, Geist is designed to support diverse data backends and query engines via predefined tags and filters, and may be extended with custom tags. A single Geist template may include multiple queries expressed in different languages, e.g. SQL and SPARQL, to leverage the strengths of each for clarity and ease of maintenance. Because Geist both can generate reports in diverse formats and perform inserts and updates on new or existing databases during template expansion, Geist templates may orchestrate data extraction, transformation, and load operations spanning multiple tools and data storage systems. Geist also enables modularity in query languages and eliminates messy procedural programs. Geist aims to enable developers to use whatever language or tools they like regardless of where the data is stored.

15 February 2021 in JMIR Preprints
Verified
Preprint
Open access
CLCarissa A Low
Carissa A Low
MLMeng Li
Meng Li
JVJulio Vega
Julio Vega
KDKrina C Durica
Krina C Durica
DFDenzil Ferreira
Denzil Ferreira
ADAnind Dey
Anind Dey
BACKGROUND Cancer treatments can cause a variety of symptoms that impair quality of life and functioning but are frequently missed by clinicians. Smartphone and wearable sensors may capture behavioral and physiological changes indicative of symptom burden, enabling passive and remote real-time monitoring of fluctuating symptoms OBJECTIVE The aim of this study was to examine whether smartphone and Fitbit data could be used to estimate daily symptom burden before and after pancreatic surgery. METHODS A total of 44 patients scheduled for pancreatic surgery participated in this prospective longitudinal study and provided sufficient sensor and self-reported symptom data for analyses. Participants collected smartphone sensor and Fitbit data and completed daily symptom ratings starting at least two weeks before surgery, throughout their inpatient recovery, and for up to 60 days after postoperative discharge. Day-level behavioral features reflecting mobility and activity patterns, sleep, screen time, heart rate, and communication were extracted from raw smartphone and Fitbit data and used to classify the next day as high or low symptom burden, adjusted for each individual’s typical level of reported symptoms. In addition to the overall symptom burden, we examined pain, fatigue, and diarrhea specifically. RESULTS Models using light gradient boosting machine (LightGBM) were able to correctly predict whether the next day would be a high symptom day with 73.5% accuracy, surpassing baseline models. The most important sensor features for discriminating high symptom days were related to physical activity bouts, sleep, heart rate, and location. LightGBM models predicting next-day diarrhea (79.0% accuracy), fatigue (75.8% accuracy), and pain (79.6% accuracy) performed similarly. CONCLUSIONS Results suggest that digital biomarkers may be useful in predicting patient-reported symptom burden before and after cancer surgery. Although model performance in this small sample may not be adequate for clinical implementation, findings support the feasibility of collecting mobile sensor data from older patients who are acutely ill as well as the potential clinical value of mobile sensing for passive monitoring of patients with cancer and suggest that data from devices that many patients already own and use may be useful in detecting worsening perioperative symptoms and triggering just-in-time symptom management interventions.