Citations

Clear

12 citation(s) found for "Chen, Chieh-I".

Longevity biotechnology: bridging AI, biomarkers, geroscience and clinical applications for healthy longevity
Lyu, Yu-Xuan, Wilczok, Dominika , Antebi, Adam , Vojta, Aleksandar , Stolzing, Alexandra , Moskalev, Alexey , Georgievskaya, Anastasia , Maier, Andrea B. , Olsen, Andrea, Groth, Anja , Brunet, Anne , Jamil, Aisyah, Kulaga, Anton , Bhatti, A.R., Yaden, Benjamin C., Djordjevic, Boris, Chen, Chieh, Huang, Christine Yuan, Chen, Danica , Sołdacki, Dariusz, Meyer, David H. , Chini, Eduardo N. , Morgen, Eric , Vernet, Erik , Pinilla, Estefano, Mercken, Evi M. , Finger, Fabian , Kuipers, Folkert , Gyülvészi, Gábor, Zmudze, Garri, Blander, Gil , Pincus, Harold A., McClure, Joshua, Kirkland, James L. , Peyer, James , McLaughlin, Jerry L., Mannick, Joan B. , Betts-LaCroix, Joe , Sedivy, John M. , Speakman, John R. , Shlain, Jordan, Maltzahn, Julia von , Andreasson, Katrin I. , Moody, Kelsey , Fortney, Kristen , Niedernhofer, Laura J., Veenhoff, Liesbeth M. , Melton, Lisa , Quarta, Marco , Koval, Maria, Marinova, Maria B., Hamalainen, Mark, Unfried, Maximilian , Ringel, Michael S. , Filipović, Miloš R. , Topors, Mourad, Mitin, Natalia , Roy, N. N., Pintar, Nika, Barzilai, Nir , Binetti, Paolo, Kohlhaas, Paul, Rubin, Paul , Kamya, Petrina, Muñoz‐Cánoves, Pura , Конрад, Р. , Ripa, Roberto , Mansukhani, Robin, Büttner, Sabrina , Brunemeier, Sebastian, Jakimov, Sergey, Rosenzweig‐Lipson, Sharon, Tsai, Shih‐Yin , Rando, Thomas A. , Peterson, Timothy R. , Woods, Tina , Wyss‐Coray, Tony , Finkel, Toren , Strauss, Tzipora , Longo, Valter D. , Sorrentino, Vincenzo , Sebastiano, Vittorio , Li, Wenbin , Suh, Yousin , Niedernhofer, Laura J. , Lu, Yuxuan , Passos, Joao, Niedernhofer, Laura J , Wyss-Coray, Tony , Bakula, Daniela , Lyu, Yu-Xuan, Fu, Qiang , Ying, Kejun , King, Aaron, Olsen, Andrea, Simon, Anna Katharina , Jamil, Aisyah, Bhatti, Asif, Pedersen, Bente Klarlund , Schumacher, Björn , Kennedy, Brian Keith , Huang, Christine Yuan, Correll, Christoph Ulrich , Murphy, Coleen Tara , Ewald, Collin Y. , Valenzano, Dario Riccardo , Erritzøe, David , Sinclair, David , Teeling, Emma C. , Verdin, Eric , Pinilla, Estéfano , Fang, Evandro Fei , Bischof, Evelyne Y. , Pun, Frank W. , Civiletto, Gabriele , Justice, Jamie N. , Vijg, Jan , Gruhn, Jennifer R. , McLaughlin, Jerry, Passos, João F. , Baur, Joseph A. , Shlain, Jordan, Palikaras, Konstantinos , Rasmussen, Lene Juel , Ferrucci, Luigi , Koval, Maria, Topors, Mourad, Roy, Nawal, Pintar, Nika , Singh, Parminder Pal , Robbins, Paul D. , Fedichev, Peter O. , Cabo, Rafael de , Faragher, Richard , Konrad, Rob, Wickström, Sara A. , Brunemeier, Sebastian A., Luo, Shan , Dimmeler, Stefanie , Gladyshev, Vadim N. , Dwaraka, Varun B. , Gorbunova, Vera , Acosta-Rodríguez, Victoria A. , Suh, Yousin , Zhavoronkov, Alex , Scheibye‐Knudsen, Morten

Mayo Clinic

Aging | October 16, 2024 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.18632/aging.206135 | PMID 39418098 Get It

Advancing toward precision migraine treatment: Predicting responses to preventive medications with machine learning models based on patient and migraine features
Chiang, Chia‐Chun , Schwedt, Todd J. , Dumkrieger, Gina , Chao, Chieh‐Ju , Ouellette, Heather A., Chen, Yi‐Chieh , Burke, Krista M., Wang, Han , Murray, Ann , Montenegro, Monique M. , Stern, Jennifer I. , Whealy, Mark , Cutrer, F. Michael , Chao, Chieh-Ju , Jones, Brandon M, Wang, Han , Murray, Ann M, Cutrer, Fred M, Chiang, Chia-Chun , Schwedt, Todd J , Dumkrieger, Gina , Wang, Liguo , Banerjee, Imon , Jones, Brandon M., Kissoon, Narayan

Mayo Clinic

Headache: The Journal of Head and Face Pain | August 23, 2024 | Volume: 64 | Issue: 9 | Pages: 1094-1108

10.1111/head.14806 | PMID 39176658 Get It

Abstract Objective To develop machine learning models using patient and migraine features that can predict treatment responses to commonly used migraine preventive medications. Background Currently, there is no accurate way to predict response to migraine preventive medications, and the standard trial‐and‐error approach is inefficient. Methods In this cohort study, we analyzed data from the Mayo Clinic Headache database prospectively collected from 2001 to December 2023. Adult patients with migraine completed questionnaires during their initial headache consultation to record detailed clinical features and then at each follow‐up to track preventive medication changes and monthly headache days. We included patients treated with at least one of the following migraine preventive medications: topiramate, beta‐blockers (propranolol, metoprolol, atenolol, nadolol, timolol), tricyclic antidepressants (amitriptyline, nortriptyline), verapamil, gabapentin, onabotulinumtoxinA, and calcitonin gene‐related peptide (CGRP) monoclonal antibodies (mAbs) (erenumab, fremanezumab, galcanezumab, eptinezumab). We pre‐trained a deep neural network, “TabNet,” using 145 variables, then employed TabNet‐embedded data to construct prediction models for each medication to predict binary outcomes (responder vs. non‐responder). A treatment responder was defined as having at least a 30% reduction in monthly headache days from baseline. All model performances were evaluated, and metrics were reported in the held‐out test set (train 85%, test 15%). SHapley Additive exPlanations (SHAP) were conducted to determine variable importance. Results Our final analysis included 4260 patients. The responder rate for each medication ranged from 28.7% to 34.9%, and the mean time to treatment outcome for each medication ranged from 151.3 to 209.5 days. The CGRP mAb prediction model achieved a high area under the receiver operating characteristics curve (AUC) of 0.825 (95% confidence interval [CI] 0.726, 0.920) and an accuracy of 0.80 (95% CI 0.70, 0.88). The AUCs of prediction models for beta‐blockers, tricyclic antidepressants, topiramate, verapamil, gabapentin, and onabotulinumtoxinA were: 0.664 (95% CI 0.579, 0.745), 0.611 (95% CI 0.562, 0.682), 0.605 (95% CI 0.520, 0.688), 0.673 (95% CI 0.569, 0.724), 0.628 (0.533, 0.661), and 0.581 (95% CI 0.550, 0.632), respectively. Baseline monthly headache days, age, body mass index (BMI), duration of migraine attacks, responses to previous medication trials, cranial autonomic symptoms, family history of headache, and migraine attack triggers were among the most important variables across all models. A variable could have different contributions; for example, lower BMI predicts responsiveness to CGRP mAbs and beta‐blockers, while higher BMI predicts responsiveness to onabotulinumtoxinA, topiramate, and gabapentin. Conclusion We developed an accurate prediction model for CGRP mAbs treatment response, leveraging detailed migraine features gathered from a headache questionnaire before starting treatment. Employing the same methods, the model performances for other medications were less impressive, though similar to the machine learning models reported in the literature for other diseases. This may be due to CGRP mAbs being migraine‐specific. Incorporating medical comorbidities, genomic, and imaging factors might enhance the model performance. We demonstrated that migraine characteristics are important in predicting treatment responses and identified the most crucial predictors for each of the seven types of preventive medications. Our results suggest that precision migraine treatment is feasible.
Health‐related quality of life in patients with metastatic basal cell carcinoma treated with cemiplimab: Analysis of a phase 2 trial
Peris, Ketty , Inocencio, Timothy J. , Stratigos, Alexander , Lewis, Karl D. , Eroglu, Zeynep , Chang, Anne Lynn S. , Ivanescu, Cristina, Fury, Matthew G., Chen, C., Quek, Ruben G.W. , Sekulić, Aleksandar , Inocencio, Timothy J , Sekulic, Aleksander , Chen, Chieh-I

Mayo Clinic

Cancer Medicine | July 20, 2024 | Volume: 13 | Issue: 14 | Pages: No page available

10.1002/cam4.7360 | PMID 39031963 Get It

AbstractBackgroundA phase 2 cemiplimab study (NCT03132636) demonstrated a 24.1% objective response rate in patients diagnosed with metastatic basal cell carcinoma (mBCC) who were not candidates for continued hedgehog inhibitor (HHI) therapy due to intolerance to previous HHI therapy, disease progression while receiving HHI therapy, or having not better than stable disease on HHI therapy after 9 months. Here, health‐related quality of life (QoL) for this patient population is reported.MethodsAdult patients with mBCC were treated with intravenous cemiplimab at a dose of 350 mg every 3 weeks for 5 treatment cycles of 9 weeks/cycle then 4 treatment cycles of 12 weeks/cycle. Patients completed the European Organisation for Research and Treatment of Cancer Quality of Life‐Core 30 (QLQ‐C30) and Skindex‐16 questionnaires at baseline and Day 1 of each cycle. Across Cycles 2 to 9, the overall change from baseline was analyzed using a mixed model with repeated measures. Responder analyses determined clinically meaningful improvement or deterioration (changes ≥10 points) or maintenance across all scales.ResultsPatients reported low symptom burden and moderate‐to‐high functioning at baseline. Maintenance for QLQ‐C30 global health status (GHS)/QoL and across all functioning and symptom scales was indicated by overall mean changes from baseline. Clinically meaningful improvement or maintenance was reported at Cycle 2 for GHS/QoL (77%), functioning scales (77% to 86%), and symptom scales (70% to 93%), with similar proportions of improvement or maintenance at Cycles 6 and 9, excluding fatigue. On the Skindex‐16, clinically meaningful improvement or maintenance was reported across the emotional, symptom, and functional subscales, in 76%–88% of patients at Cycle 2, which were generally maintained at Cycles 6 and 9. Overall mean changes from baseline showed maintenance across these subscales.ConclusionsThe majority of patients treated with cemiplimab reported improvement or maintenance in GHS/QoL and functioning while maintaining a low symptom burden.
A large language model–based generative natural language processing framework fine‐tuned on clinical notes accurately extracts headache frequency from electronic health records
Chiang, Chia‐Chun , Luo, Man , Dumkrieger, Gina , Trivedi, Shubham , Chen, Yi‐Chieh , Chao, Chieh‐Ju , Schwedt, Todd J. , Sarker, Abeed , Banerjee, Imon , Banerjee, Imon , Chiang, Chia-Chun , Schwedt, Todd J , Dumkrieger, Gina , Chao, Chieh-Ju , Chen, Yi-Chieh

Mayo Clinic

Headache: The Journal of Head and Face Pain | March 25, 2024 | Volume: 64 | Issue: 4 | Pages: 400-409

10.1111/head.14702 | PMID 38525734 Get It

Abstract Objective To develop a natural language processing (NLP) algorithm that can accurately extract headache frequency from free‐text clinical notes. Background Headache frequency, defined as the number of days with any headache in a month (or 4 weeks), remains a key parameter in the evaluation of treatment response to migraine preventive medications. However, due to the variations and inconsistencies in documentation by clinicians, significant challenges exist to accurately extract headache frequency from the electronic health record (EHR) by traditional NLP algorithms. Methods This was a retrospective cross‐sectional study with patients identified from two tertiary headache referral centers, Mayo Clinic Arizona and Mayo Clinic Rochester. All neurology consultation notes written by 15 specialized clinicians (11 headache specialists and 4 nurse practitioners) between 2012 and 2022 were extracted and 1915 notes were used for model fine‐tuning (90%) and testing (10%). We employed four different NLP frameworks: (1) ClinicalBERT (Bidirectional Encoder Representations from Transformers) regression model, (2) Generative Pre‐Trained Transformer‐2 (GPT‐2) Question Answering (QA) model zero‐shot, (3) GPT‐2 QA model few‐shot training fine‐tuned on clinical notes, and (4) GPT‐2 generative model few‐shot training fine‐tuned on clinical notes to generate the answer by considering the context of included text. Results The mean (standard deviation) headache frequency of our training and testing datasets were 13.4 (10.9) and 14.4 (11.2), respectively. The GPT‐2 generative model was the best‐performing model with an accuracy of 0.92 (0.91, 0.93, 95% confidence interval [CI]) and R 2 score of 0.89 (0.87, 0.90, 95% CI), and all GPT‐2–based models outperformed the ClinicalBERT model in terms of exact matching accuracy. Although the ClinicalBERT regression model had the lowest accuracy of 0.27 (0.26, 0.28), it demonstrated a high R 2 score of 0.88 (0.85, 0.89), suggesting the ClinicalBERT model can reasonably predict the headache frequency within a range of ≤ ± 3 days, and the R 2 score was higher than the GPT‐2 QA zero‐shot model or GPT‐2 QA model few‐shot training fine‐tuned model. Conclusion We developed a robust information extraction model based on a state‐of‐the‐art large language model, a GPT‐2 generative model that can extract headache frequency from EHR free‐text clinical notes with high accuracy and R 2 score. It overcame several challenges related to different ways clinicians document headache frequency that were not easily achieved by traditional NLP models. We also showed that GPT‐2–based frameworks outperformed ClinicalBERT in terms of accuracy in extracting headache frequency from clinical notes. To facilitate research in the field, we released the GPT‐2 generative model and inference code with open‐source license of community use in GitHub. Additional fine‐tuning of the algorithm might be required when applied to different health‐care systems for various clinical use cases.
The Effect of Pharmacogenomic Data on Adequate Dosages of Verapamil for The Prevention of Primary Headache Disorders-a pilot exploratory study (P11-2.004)
Chen, Yi‐Chieh , Wang, Han , Mandrekar, Jayawant N. , Starling, Amaal J. , Cutrer, F. Michael , Robertson, Carrie E. , Chiang, Chia‐Chun

Mayo Clinic

Neurology | December 6, 2023 | Volume: 98 | Issue: 18_supplement | Pages: No page available

10.1212/wnl.98.18_supplement.2390 Get It

Challenges and solutions of echocardiography generalization for deep learning: a study in patients with constrictive pericarditis
Jeong, Jiwoong , Pelkey, Melissa N. , Chen, Yi‐Chieh , Ramzan, Raheel N., Elbahnasawy, Mohammad , Sleem, Mohamed, Grogan, Martha , Kane, Garvan C. , Patel, Bhavik N. , Oh, Jae K. , Banerjee, Imon , Chao, Chieh-Ju , Arsanjani, Reza , Kim, Kihong, Pelkey, Melissa N , Chen, Yi-Chieh , Farina, Juan Maria M, Banerjee, Imon , Chao, Chieh‐Ju , Arsanjani, Reza , Kim, Kihong , Farina, Juan M.

Mayo Clinic

Journal of Medical Imaging | October 12, 2023 | Volume: 10 | Issue: 05 | Pages: No page available

10.1117/1.jmi.10.5.054502 | PMID 37840850 Get It

HSR23-097: Health-Related Quality of Life in Patients With Metastatic Basal Cell Carcinoma Treated With Cemiplimab: Analysis of a Phase 2 Open-Label Clinical Trial
Lewis, Karl D. , Quek, Ruben G.W. , Eroglu, Zeynep, Ivanescu, Cristina, Stratigos, Alexander , Sekulić, Aleksandar , Fury, Matthew G., Chen, Chieh-I, Inocencio, Timothy J. , LaFontaine, Patrick R. , Eroglu, Zeynep , Chang, Anne Lynn S. , Peris, Ketty

Mayo Clinic

Journal of the National Comprehensive Cancer Network | March 31, 2023 | Volume: 21 | Issue: 3.5 | Pages: HSR23-097

10.6004/jnccn.2022.7161 Get It

Pharmacogenomic Study—A Pilot Study of the Effect of Pharmacogenomic Phenotypes on the Adequate Dosing of Verapamil for Migraine Prevention
Chen, Yi‐Chieh , Mandrekar, Jayawant N. , Robertson, Carrie E. , Starling, Amaal J. , Cutrer, F. Michael , Robertson, Carrie E , Chen, Yi-Chieh , Wang, Han , Chiang, Chia‐Chun

Mayo Clinic

No container title available | December 15, 2022 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.21203/rs.3.rs-2365333/v1 Get It

Abstract OBJECTIVE Using individual pharmacogenomic phenotypes to investigate the factors affecting the efficacy and tolerability of verapamil for migraine prevention. BACKGROUND Verapamil has a wide range of dosing in headache disorders without reliable tools to predict the optimal doses for an individual. METHODS This is a retrospective chart review examining adults with existing pharmacogenomic reports at Mayo Clinic who had used verapamil for migraine. Effects of six cytochrome P450 phenotypes on the minimum effective and maximum tolerable verapamil doses for migraine prevention were assessed. RESULTS The mean minimum effective and maximum tolerable doses for the 33 patients in final analysis were 178.2(20–320) mg and 227.9(20–480) mg. A variety of CYP2C9, CYP2D6, and CYP3A5 phenotypes were found, without significant association with the verapamil doses after adjusting for age, sex, body mass index, and smoking status. CONCLUSIONS We demonstrated a wide range of effective and tolerable verapamil doses used for migraine in a cohort with various pharmacogenomic phenotypes.
Health-related quality of life (HRQoL) in patients (pts) with locally advanced basal cell carcinoma (laBCC) treated with cemiplimab: Analysis of a phase II, open-label clinical trial.
Stratigos, Alexander , Chen, Chieh-I, Ivanescu, Cristina, Lewis, Karl D. , Bechter, Oliver , Mastey, Vera, Konidaris, Gerasimos, Bury, Denise, Yoo, Suk Young, Mohan, Kosalai Kal, Coates, Ebony, Bowler, Timothy G., Fury, Matthew G., Sekulić, Aleksandar , Peris, Ketty , Harnett, James , Reaney, Matthew D. , Daskalopoulou, Christina , LaFontaine, Patrick R.

Mayo Clinic

Journal of Clinical Oncology | June 2, 2021 | Volume: 39 | Issue: 15_suppl | Pages: 9566-9566

10.1200/jco.2021.39.15_suppl.9566 Get It

9566 Background: Cemiplimab-rwlc is the first immunotherapy to receive approval in the US, fully for pts with laBCC and accelerated for metastatic BCC, post hedgehog inhibitors or for whom hedgehog inhibitors are not appropriate. Cemiplimab resulted in clinically meaningful anti-tumor activity in pts with laBCC who progressed on or were intolerant to hedgehog inhibitor therapy (NCT03132636). This analysis evaluated HRQoL in these pts. Methods: Adults with laBCC and ECOG performance status ≤1 (n=84) received IV cemiplimab 350 mg Q3W for up to 9 treatment cycles. At baseline (BL) and day 1 of each cycle (C), pts completed EORTC QLQ-C30 and SKINDEX-16 questionnaires that assess Global Health Status (GHS)/QoL, functioning, and BCC-related symptoms. Mixed-effects repeated measures (MMRM) models were used to estimate least squares (LS) mean (standard error [SE]) change from BL during treatment (i.e., across C2 to C9); changes ≥|10| points were considered clinically meaningful. Responder analyses were conducted in pts with non-missing data from BL to determine the proportions with clinically meaningful improvement or deterioration, or stability on QLQ-C30 and SKINDEX-16 at C2 and C9; a 10-point threshold was considered meaningful for both instruments. Results: BL scores showed moderate to high levels of functioning and low symptom burden. In MMRM models, overall changes from BL on QLQ-C30 indicated stability for GHS/QoL and all scales except for clinically meaningful worsening of fatigue (LS mean [SE] change 12.5 [3.9]; P<.05). In responder analysis, the majority of pts reported clinically meaningful improvement or stability at C2 and C9 on all QLQ-C30 functioning scales and the key symptom of pain but not fatigue (Table). On SKINDEX-16, MMRM models showed clinically meaningful improvement on the emotional subscale (LS mean [SE] change –13.2 [3.9]; P<.05) and stability on the symptom and functional subscales. Responder analysis showed clinically meaningful improvements or stability across the SKINDEX-16 subscales in approximately 80% of pts at C2, and 70–80% of pts at C9. Conclusions: In laBCC pts treated with cemiplimab, the majority reported clinically meaningful improvement or stability in GHS/QoL and functional status while maintaining a low symptom burden except for fatigue. Clinical trial information: NCT03132636. [Table: see text]