In-Lu Amy Liu

In-Lu Amy Liu

Auto-generated profile, based on publicly available information

In-Lu Amy Liu

Kaiser Permanente Department of Research and Evaluation, Pasadena, California

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
24 May 2022 in JMIR Public Health and Surveillance
Verified
Journal Article
Open access
CZChengyi Zheng
Chengyi Zheng
JDJonathan Duffy
Jonathan Duffy
ILIn-Lu Amy Liu
In-Lu Amy Liu
LSLina S Sy
Lina S Sy
RNRonald A. A. Navarro
Ronald A. A. Navarro
SJSteven J Jacobsen
Steven J Jacobsen
Background: Shoulder injury related to vaccine administration (SIRVA) accounts for more than half of all claims received by the National Vaccine Injury Compensation Program. However, due to the difficulty of finding SIRVA cases in large health care databases, population-based studies are scarce. Objective: The goal of the research was to develop a natural language processing (NLP) method to identify SIRVA cases from clinical notes. Methods: We conducted the study among members of a large integrated health care organization who were vaccinated between April 1, 2016, and December 31, 2017, and had subsequent diagnosis codes indicative of shoulder injury. Based on a training data set with a chart review reference standard of 164 cases, we developed an NLP algorithm to extract shoulder disorder information, including prior vaccination, anatomic location, temporality and causality. The algorithm identified 3 groups of positive SIRVA cases (definite, probable, and possible) based on the strength of evidence. We compared NLP results to a chart review reference standard of 100 vaccinated cases. We then applied the final automated NLP algorithm to a broader cohort of vaccinated persons with a shoulder injury diagnosis code and performed manual chart confirmation on a random sample of NLP-identified definite cases and all NLP-identified probable and possible cases. Results: In the validation sample, the NLP algorithm had 100% accuracy for identifying 4 SIRVA cases and 96 cases without SIRVA. In the broader cohort of 53,585 vaccinations, the NLP algorithm identified 291 definite, 124 probable, and 52 possible SIRVA cases. The chart-confirmation rates for these groups were 95.5% (278/291), 67.7% (84/124), and 17.3% (9/52), respectively. Conclusions: The algorithm performed with high sensitivity and reasonable specificity in identifying positive SIRVA cases. The NLP algorithm can potentially be used in future population-based studies to identify this rare adverse event, avoiding labor-intensive chart review validation.

8 May 2021 in Infectious Diseases
Verified
Journal Article
Closed access
CHCheng-Wei Huang
Cheng-Wei Huang
PDPrashant P. Desai
Prashant P. Desai
KWKenneth K. Wei
Kenneth K. Wei
ILIn-Lu Amy Liu
In-Lu Amy Liu
JLJanet S. Lee
Janet S. Lee
HNHuong Q. Nguyen
Huong Q. Nguyen
Limited studies have explored post-discharge outcomes following Coronavirus Disease 2019 (COVID-19) hospitalisation. We sought to characterise patients discharged following a COVID-19 hospitalisati...

6 May 2024 in Clinical Journal of the American Society of Nephrology
Verified
Journal Article
Closed access
KNKhalid Namoos
Khalid Namoos
CHCheng-Wei Huang
Cheng-Wei Huang
ILIn-Lu Amy Liu
In-Lu Amy Liu
JLJanet S. Lee
Janet S. Lee
DYDavid K. Yi
David K. Yi
JSJohn J. Sim
John J. Sim
An abstract is unavailable. This article is available as a PDF only.

22 July 2024 in Kidney360
Verified
Journal Article
Open access
DLDeborah Lu
Deborah Lu
HSHubert Song
Hubert Song
ILIn-Lu Amy Liu
In-Lu Amy Liu
JSJiaxiao Shi
Jiaxiao Shi
RTRichard M. Treger
Richard M. Treger
Key Points: The mean delta anion gap (ΔAG)/delta bicarbonate (ΔHCO3) calculated using an albumin-corrected anion gap and each patient's individual baseline AG and serum HCO3 was 1.20. The ΔAG/ΔHCO3 using mean normal AG and serum HCO3 was 1.6–1.8; use of mean normal values can result in misdiagnosis of complex acid-base disorders. The elevated ΔAG/ΔHCO3 is likely due to unmeasured anions. Background: The ratio of delta anion gap and delta bicarbonate (ΔAG/ΔHCO3) is used to detect coexisting acid-base disorders in patients with high anion gap metabolic acidosis. The ΔAG/ΔHCO3 ratio of 1.6–1.8:1 in lactic acidosis is derived from limited data using mean normal values for anion gap (AG) and serum HCO3. The objective of this study was to be the first to examine the ΔAG/ΔHCO3 using each patient's individual baseline AG and serum HCO3. Methods: This was a retrospective cohort study of adult intensive care unit (ICU) patients with sepsis. Laboratory data from simultaneously drawn chemistry panel, including anion gap and serum lactate on admission to the ICU, were obtained. Baseline AG, HCO3, and albumin measurements were obtained 1–24 months before ICU admission. The ΔAG/ΔHCO3 was calculated using an albumin-corrected anion gap and each patient's individual baseline AG and serum HCO3. Results: Three hundred forty-four patients were included. One hundred twenty-eight patients had normal serum lactate levels (≤1.9 mmol/L), and 216 patients had elevated serum lactate levels (>1.9 mmol/L). ΔAG/ΔHCO3 was calculated for the 216 patients who had elevated serum lactate levels (>1.9 mmol/L). The mean ΔAG/ΔHCO3 for all patients with elevated serum lactate levels was 1.20 (SD 1.50). Conclusions: The mean ΔAG/ΔHCO3 calculated using an albumin-corrected anion gap and each patient's individual baseline AG and serum HCO3 was 1.20. The ΔAG/ΔHCO3 reported in prior literature that used mean normal AG and serum HCO3 was 1.6–1.8, highlighting that use of mean normal values affects the calculation of the ΔAG/ΔHCO3 and subsequent conclusions about underlying pathophysiology. The use of these mean normal values can result in misdiagnosis of complex acid-base disorders and inappropriate treatment. Our analysis indicates that the elevated ΔAG/ΔHCO3 is likely due to unmeasured anions contributing to an elevation in AG.

13 May 2021 in JMIR Preprints
Verified
Preprint
Open access
CZChengyi Zheng
Chengyi Zheng
JDJonathan Duffy
Jonathan Duffy
ILIn-Lu Amy Liu
In-Lu Amy Liu
LSLina S Sy
Lina S Sy
RNRonald A. A. Navarro
Ronald A. A. Navarro
SJSteven J Jacobsen
Steven J Jacobsen
BACKGROUND Shoulder injury related to vaccine administration (SIRVA) accounts for more than half of all claims received by the National Vaccine Injury Compensation Program. However, due to the difficulty of finding SIRVA cases in large health care databases, population-based studies are scarce. OBJECTIVE The goal of the research was to develop a natural language processing (NLP) method to identify SIRVA cases from clinical notes. METHODS We conducted the study among members of a large integrated health care organization who were vaccinated between April 1, 2016, and December 31, 2017, and had subsequent diagnosis codes indicative of shoulder injury. Based on a training data set with a chart review reference standard of 164 cases, we developed an NLP algorithm to extract shoulder disorder information, including prior vaccination, anatomic location, temporality and causality. The algorithm identified 3 groups of positive SIRVA cases (definite, probable, and possible) based on the strength of evidence. We compared NLP results to a chart review reference standard of 100 vaccinated cases. We then applied the final automated NLP algorithm to a broader cohort of vaccinated persons with a shoulder injury diagnosis code and performed manual chart confirmation on a random sample of NLP-identified definite cases and all NLP-identified probable and possible cases. RESULTS In the validation sample, the NLP algorithm had 100% accuracy for identifying 4 SIRVA cases and 96 cases without SIRVA. In the broader cohort of 53,585 vaccinations, the NLP algorithm identified 291 definite, 124 probable, and 52 possible SIRVA cases. The chart-confirmation rates for these groups were 95.5% (278/291), 67.7% (84/124), and 17.3% (9/52), respectively. CONCLUSIONS The algorithm performed with high sensitivity and reasonable specificity in identifying positive SIRVA cases. The NLP algorithm can potentially be used in future population-based studies to identify this rare adverse event, avoiding labor-intensive chart review validation.

7 May 2021 in medRxiv
Verified
Preprint
Open access
PDF file
CZChengyi Zheng
Chengyi Zheng
JDJonathan Duffy
Jonathan Duffy
ILIn-Lu Amy Liu
In-Lu Amy Liu
LSLina S. Sy
Lina S. Sy
RNRonald A. A. Navarro
Ronald A. A. Navarro
SJSteven J. Jacobsen
Steven J. Jacobsen
Background Shoulder injury related to vaccine administration (SIRVA) accounts for more than half of all claims received by the National Vaccine Injury Compensation Program. However, there is a lack of population-based studies due to the challenge of identifying SIRVA cases in large health care databases. Objective To develop a natural language processing (NLP) method to identify SIRVA cases from clinical notes. Methods We conducted the study among members of a large integrated health care organization who were vaccinated between 04/1/2016 and 12/31/2017 and had subsequent diagnosis codes indicative of shoulder injury. Based on a training dataset with a chart review reference standard of 164 individuals, we developed an NLP algorithm to extract shoulder disorder information, including prior vaccination, anatomic location, temporality and causality. The algorithm identified three groups of positive SIRVA cases (definite, probable and possible) based on the strength of evidence. We compared NLP results to a chart review reference standard of 100 vaccinated individuals. We then applied the final automated NLP algorithm to a broader cohort of vaccinated individuals with a shoulder injury diagnosis code and performed manual chart confirmation on a random sample of NLP-identified definite cases and all NLP-identified probable and possible cases. Results In the validation sample, the NLP algorithm had 100% accuracy for identifying 4 SIRVA cases and 96 individuals without SIRVA. In the broader cohort of 53,585 individuals, the NLP algorithm identified 291 definite, 124 probable, and 52 possible SIRVA cases. The chart-confirmation rates for these groups were 95.3%, 67.7% and 18.9%, respectively. Conclusions The algorithm performed with high sensitivity and reasonable specificity in identifying positive SIRVA cases. The NLP algorithm can potentially be used in future population-based studies to identify this rare adverse event, avoiding labor-intensive chart review validation.