Dr. Wei-Hsuan “Jenny” Lo-Ciganic is a pharmacoepidemiologist whose research focuses on improving drug safety, medication adherence, and the quality of prescribing, especially among vulnerable populations (e.g., older adults, Medicaid). Dr. Lo-Ciganic has extensive experience applying advanced predictive analytics, including machine learning and group-based trajectory modeling with large healthcare datasets. Since 2015, she has served as Principal Investigator (PI) and Co-Investigator (Co-I) on more than 17 extramurally-funded grants and contracts. Currently, she is the PI for the R01 study entitled “Developing and Evaluating a Machine-Learning Opioid Prediction & Risk-Stratification E-Platform (DEMONSTRATE)” and a lead investigator for the R01 grant entitled “Machine-Learning Prediction and Reducing Overdoses with EHR Nudges (mPROVEN)” funded by the National Institutes on Drug Abuse (NIDA). She has published more than 90 peer-reviewed manuscripts and has an h-index of 21. She has extensive and successful experience mentoring PharmD, MS, and PhD students, post-doctoral fellows, residents, and junior faculty.
In her personal time, Dr. Lo-Ciganic enjoys cooking, swimming, and spending time with her four children. Dr. Lo-Ciganic has a profound love for research and exploration and enjoys embarking on international journeys to disseminate her research findings and explore different places and cultures (and getting lost).
Education & Training
- BS, Pharmacy (Minor in Horticulture), National Taiwan University, 2003
- MS, Clinical Pharmacy, National Cheng-Kung University, 2005
- MS, Biostatistics, University of Pittsburgh, 2010
- PhD, Epidemiology, University of Pittsburgh, 2013
- Geriatric Pharmaceutical Outcomes & Gero-Informatics Research & Training Program, University of Pittsburgh, 2013
- Pharmaceutical Health Service Research Postdoctoral Fellowship, CP3, University of Pittsburgh, 2014
Representative Publications
Lo-Ciganic W, Huang JL, Zhang HH, Weiss JC, Wu Y, Kwoh CK, Donohue JM, Cochran G, Gordon AJ, Malone DC, Kuza CC, Gellad WF. Evaluation of machine-learning algorithms for predicting opioid overdose risk among Medicare beneficiaries with opioid prescriptions. JAMA Netw Open. 2019; 2(3):e190968.
This study aimed to develop and validate a machine-learning algorithm for predicting opioid overdose risk among Medicare beneficiaries. The results indicated that machine-learning algorithms, particularly deep neural networks (DNN) and gradient boosting machines (GBM), outperformed traditional methods in predicting opioid overdose risk and identifying low-risk subgroups with minimal risk of overdose.
Lo-Ciganic W, Donohue JM, Hulsey EG, Barnes S, Li Y, Kuza CC, Yang Q, Buchanich J, Huang JL, Mair C, Wilson DL, Gellad WF. Integrating human services and criminal justice data with claims data to predict risk of opioid overdose among Medicaid beneficiaries: A machine-learning approach. PLoS One. 2021;16(3): e0248360.
This study aimed to enhance the accuracy of predicting opioid overdose risk by integrating human services and criminal justice data with health claims data. Using a gradient boosting machine, the integrated model improved opioid overdose prediction compared to a Medicaid claims-only model, with approximately 70% of overdose cases occurring in the top risk decile, offering valuable insights for addressing the opioid crisis in a large county in the United States.
Lo-Ciganic W, Donohue JM, Yang Q, Huang JL, Chang C-Y(g), Weiss JC, Guo J, Zhang HH, Cochran G, Gordon AJ, Malone DC, Kwoh CK, Wilson DL, Kuza CC, Gellad WF. Developing and validating a machine-learning algorithm to predict opioid overdose among Medicaid beneficiaries in two US states: A prognostic modeling study. Lancet Digit Health. 2022 Jun;4(6):e455-e465.
This study focuses on developing and validating a machine-learning algorithm to predict opioid overdose risk in Medicaid beneficiaries across different states. The algorithm, initially developed using Pennsylvania Medicaid data, demonstrated strong performance in external validation with both more recent Pennsylvania data and data from Arizona Medicaid, offering potential value for overdose risk prediction and stratification in Medicaid beneficiaries.
Lo-Ciganic W, Hincapie-Castillo J, Wang T(p), Ge Y, Jones BL, Huang JL, Chang CY(g), Wilson DL, Lee JK, Reisfield GM, Kwoh CK, Delcher C, Nguyen KA, Zhou L, Shorr RI, Guo J, Marcum ZA, Harle CA, Park H, Winterstein A, Yang S(g), Huang PL, Adkins L, Gellad WF. Dosing profiles of concurrent opioid and benzodiazepine use associated with overdose risk among US Medicare beneficiaries: Group-based multi-trajectory models. Addiction. 2022 Jul;117(7):1982-1997.
This study identified distinct patterns of concurrent opioid and benzodiazepine use over time and investigated which were most associated with overdose risk among fee-for-service United States Medicaid beneficiaries who initiated opioid prescriptions. The findings revealed that among the nine identified trajectories, trajectories characterized by either any very high-dose opioid use (MME > 150), any high-dose benzodiazepine use (DME > 40), or medium-dose opioid with low-dose benzodiazepine use were associated with three to seven times increased opioid overdose risks compared to the lowest-dose opioid and benzodiazepine trajectory. Identifying opioid and benzodiazepine trajectory groups characterized by longitudinal dose and duration with distinct risk magnitudes provides more clinically actionable information than current approaches (e.g. examining any overlapping prescription) for detecting unsafe opioid and benzodiazepine use.
Click here for a more complete bibliography of Dr. Lo-Ciganic’s works.
Research Interests
- Pharmacoepidemiology
- Health outcomes research
- Medication adherence
- Machine learning
- Predictive analytics