@misc{DellepianeVaidJaladankietal.2021, author = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K. and Coca, Steven and Fayad, Zahi A. and Charney, Alexander W. and B{\"o}ttinger, Erwin and He, John Cijiang and Glicksberg, Benjamin S. and Chan, Lili and Nadkarni, Girish}, title = {Acute kidney injury in patients hospitalized with COVID-19 in New York City}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {5}, issn = {2590-0595}, doi = {10.25932/publishup-58541}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585415}, pages = {5}, year = {2021}, language = {en} } @article{DellepianeVaidJaladankietal.2021, author = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K. and Coca, Steven and Fayad, Zahi A. and Charney, Alexander W. and B{\"o}ttinger, Erwin and He, John Cijiang and Glicksberg, Benjamin S. and Chan, Lili and Nadkarni, Girish}, title = {Acute kidney injury in patients hospitalized with COVID-19 in New York City}, series = {Kidney medicine}, volume = {3}, journal = {Kidney medicine}, number = {5}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2590-0595}, doi = {10.1016/j.xkme.2021.06.008}, pages = {877 -- 879}, year = {2021}, language = {en} } @article{ChanChaudharySahaetal.2021, author = {Chan, Lili and Chaudhary, Kumardeep and Saha, Aparna and Chauhan, Kinsuk and Vaid, Akhil and Zhao, Shan and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and Miotto, Riccardo and Lala, Anuradha and Kia, Arash and Timsina, Prem and Li, Li and Freeman, Robert and Chen, Rong and Narula, Jagat and Just, Allan C. and Horowitz, Carol and Fayad, Zahi and Cordon-Cardo, Carlos and Schadt, Eric and Levin, Matthew A. and Reich, David L. and Fuster, Valentin and Murphy, Barbara and He, John C. and Charney, Alexander W. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.}, title = {AKI in hospitalized patients with COVID-19}, series = {Journal of the American Society of Nephrology : JASN}, volume = {32}, journal = {Journal of the American Society of Nephrology : JASN}, number = {1}, publisher = {American Society of Nephrology}, address = {Washington}, organization = {Mt Sinai COVID Informatics Ct}, issn = {1046-6673}, doi = {10.1681/ASN.2020050615}, pages = {151 -- 160}, year = {2021}, abstract = {Background: Early reports indicate that AKI is common among patients with coronavirus disease 2019 (COVID-19) and associatedwith worse outcomes. However, AKI among hospitalized patients with COVID19 in the United States is not well described. Methods: This retrospective, observational study involved a review of data from electronic health records of patients aged >= 18 years with laboratory-confirmed COVID-19 admitted to the Mount Sinai Health System from February 27 to May 30, 2020. We describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aORs) with mortality. Results: Of 3993 hospitalized patients with COVID-19, AKI occurred in 1835 (46\%) patients; 347 (19\%) of the patientswith AKI required dialysis. The proportionswith stages 1, 2, or 3 AKIwere 39\%, 19\%, and 42\%, respectively. A total of 976 (24\%) patients were admitted to intensive care, and 745 (76\%) experienced AKI. Of the 435 patients with AKI and urine studies, 84\% had proteinuria, 81\% had hematuria, and 60\% had leukocyturia. Independent predictors of severe AKI were CKD, men, and higher serum potassium at admission. In-hospital mortality was 50\% among patients with AKI versus 8\% among those without AKI (aOR, 9.2; 95\% confidence interval, 7.5 to 11.3). Of survivors with AKI who were discharged, 35\% had not recovered to baseline kidney function by the time of discharge. An additional 28 of 77 (36\%) patients who had not recovered kidney function at discharge did so on posthospital follow-up. Conclusions: AKI is common among patients hospitalized with COVID-19 and is associated with high mortality. Of all patients with AKI, only 30\% survived with recovery of kidney function by the time of discharge.}, language = {en} } @article{SigelSwartzGoldenetal.2020, author = {Sigel, Keith Magnus and Swartz, Talia H. and Golden, Eddye and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and De Freitas, Jessica K. and Miotto, Riccardo and Zhao, Shan and Polak, Paz and Mutetwa, Tinaye and Factor, Stephanie and Mehandru, Saurabh and Mullen, Michael and Cossarini, Francesca and B{\"o}ttinger, Erwin and Fayad, Zahi and Merad, Miriam and Gnjatic, Sacha and Aberg, Judith and Charney, Alexander and Nadkarni, Girish and Glicksberg, Benjamin S.}, title = {Coronavirus 2019 and people living with human immunodeficiency virus}, series = {Clinical infectious diseases : electronic edition}, volume = {71}, journal = {Clinical infectious diseases : electronic edition}, number = {11}, publisher = {Oxford Univ. Press}, address = {Cary, NC}, issn = {1058-4838}, doi = {10.1093/cid/ciaa880}, pages = {2933 -- 2938}, year = {2020}, abstract = {Background: There are limited data regarding the clinical impact of coronavirus disease 2019 (COVID-19) on people living with human immunodeficiency virus (PLWH). In this study, we compared outcomes for PLWH with COVID-19 to a matched comparison group. Methods: We identified 88 PLWH hospitalized with laboratory-confirmed COVID-19 in our hospital system in New York City between 12 March and 23 April 2020. We collected data on baseline clinical characteristics, laboratory values, HIV status, treatment, and outcomes from this group and matched comparators (1 PLWH to up to 5 patients by age, sex, race/ethnicity, and calendar week of infection). We compared clinical characteristics and outcomes (death, mechanical ventilation, hospital discharge) for these groups, as well as cumulative incidence of death by HIV status. Results: Patients did not differ significantly by HIV status by age, sex, or race/ethnicity due to the matching algorithm. PLWH hospitalized with COVID-19 had high proportions of HIV virologic control on antiretroviral therapy. PLWH had greater proportions of smoking (P < .001) and comorbid illness than uninfected comparators. There was no difference in COVID-19 severity on admission by HIV status (P = .15). Poor outcomes for hospitalized PLWH were frequent but similar to proportions in comparators; 18\% required mechanical ventilation and 21\% died during follow-up (compared with 23\% and 20\%, respectively). There was similar cumulative incidence of death over time by HIV status (P = .94). Conclusions: We found no differences in adverse outcomes associated with HIV infection for hospitalized COVID-19 patients compared with a demographically similar patient group.}, language = {en} } @article{LewkowiczWohlbrandtBoettinger2022, author = {Lewkowicz, Daniel and Wohlbrandt, Attila M. and B{\"o}ttinger, Erwin}, title = {Digital therapeutic care apps with decision-support interventions for people with low back pain in Germany}, series = {JMIR mhealth and uhealth}, volume = {10}, journal = {JMIR mhealth and uhealth}, number = {2}, publisher = {JMIR Publications}, address = {Toronto}, issn = {2291-5222}, doi = {10.2196/35042}, pages = {17}, year = {2022}, abstract = {Background: Digital therapeutic care apps provide a new effective and scalable approach for people with nonspecific low back pain (LBP). Digital therapeutic care apps are also driven by personalized decision-support interventions that support the user in self-managing LBP, and may induce prolonged behavior change to reduce the frequency and intensity of pain episodes. However, these therapeutic apps are associated with high attrition rates, and the initial prescription cost is higher than that of face-to-face physiotherapy. In Germany, digital therapeutic care apps are now being reimbursed by statutory health insurance; however, price targets and cost-driving factors for the formation of the reimbursement rate remain unexplored. Objective: The aim of this study was to evaluate the cost-effectiveness of a digital therapeutic care app compared to treatment as usual (TAU) in Germany. We further aimed to explore under which circumstances the reimbursement rate could be modified to consider value-based pricing. Methods: We developed a state-transition Markov model based on a best-practice analysis of prior LBP-related decision-analytic models, and evaluated the cost utility of a digital therapeutic care app compared to TAU in Germany. Based on a 3-year time horizon, we simulated the incremental cost and quality-adjusted life years (QALYs) for people with nonacute LBP from the societal perspective. In the deterministic sensitivity and scenario analyses, we focused on diverging attrition rates and app cost to assess our model's robustness and conditions for changing the reimbursement rate. All costs are reported in Euro (euro1=US \$1.12). Results: Our base case results indicated that the digital therapeutic care strategy led to an incremental cost of euro121.59, but also generated 0.0221 additional QALYs compared to the TAU strategy, with an estimated incremental cost-effectiveness ratio (ICER) of euro5486 per QALY. The sensitivity analysis revealed that the reimbursement rate and the capability of digital therapeutic care to prevent reoccurring LBP episodes have a significant impact on the ICER. At the same time, the other parameters remained unaffected and thus supported the robustness of our model. In the scenario analysis, the different model time horizons and attrition rates strongly influenced the economic outcome. Reducing the cost of the app to euro99 per 3 months or decreasing the app's attrition rate resulted in digital therapeutic care being significantly less costly with more generated QALYs, and is thus considered to be the dominant strategy over TAU. Conclusions: The current reimbursement rate for a digital therapeutic care app in the statutory health insurance can be considered a cost-effective measure compared to TAU. The app's attrition rate and effect on the patient's prolonged behavior change essentially influence the settlement of an appropriate reimbursement rate. Future value-based pricing targets should focus on additional outcome parameters besides pain intensity and functional disability by including attrition rates and the app's long-term effect on quality of life.}, language = {en} } @article{DattaSachsFreitasdaCruzetal.2021, author = {Datta, Suparno and Sachs, Jan Philipp and Freitas da Cruz, Harry and Martensen, Tom and Bode, Philipp and Morassi Sasso, Ariane and Glicksberg, Benjamin S. and B{\"o}ttinger, Erwin}, title = {FIBER}, series = {JAMIA open}, volume = {4}, journal = {JAMIA open}, number = {3}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {2574-2531}, doi = {10.1093/jamiaopen/ooab048}, pages = {10}, year = {2021}, abstract = {Objectives: The development of clinical predictive models hinges upon the availability of comprehensive clinical data. Tapping into such resources requires considerable effort from clinicians, data scientists, and engineers. Specifically, these efforts are focused on data extraction and preprocessing steps required prior to modeling, including complex database queries. A handful of software libraries exist that can reduce this complexity by building upon data standards. However, a gap remains concerning electronic health records (EHRs) stored in star schema clinical data warehouses, an approach often adopted in practice. In this article, we introduce the FlexIBle EHR Retrieval (FIBER) tool: a Python library built on top of a star schema (i2b2) clinical data warehouse that enables flexible generation of modeling-ready cohorts as data frames. Materials and Methods: FIBER was developed on top of a large-scale star schema EHR database which contains data from 8 million patients and over 120 million encounters. To illustrate FIBER's capabilities, we present its application by building a heart surgery patient cohort with subsequent prediction of acute kidney injury (AKI) with various machine learning models. Results: Using FIBER, we were able to build the heart surgery cohort (n = 12 061), identify the patients that developed AKI (n = 1005), and automatically extract relevant features (n = 774). Finally, we trained machine learning models that achieved area under the curve values of up to 0.77 for this exemplary use case. Conclusion: FIBER is an open-source Python library developed for extracting information from star schema clinical data warehouses and reduces time-to-modeling, helping to streamline the clinical modeling process.}, language = {en} } @article{CopeBaukmannKlingeretal.2021, author = {Cope, Justin L. and Baukmann, Hannes A. and Klinger, J{\"o}rn E. and Ravarani, Charles N. J. and B{\"o}ttinger, Erwin and Konigorski, Stefan and Schmidt, Marco F.}, title = {Interaction-based feature selection algorithm outperforms polygenic risk score in predicting Parkinson's Disease status}, series = {Frontiers in genetics}, volume = {12}, journal = {Frontiers in genetics}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {1664-8021}, doi = {10.3389/fgene.2021.744557}, pages = {9}, year = {2021}, abstract = {Polygenic risk scores (PRS) aggregating results from genome-wide association studies are the state of the art in the prediction of susceptibility to complex traits or diseases, yet their predictive performance is limited for various reasons, not least of which is their failure to incorporate the effects of gene-gene interactions. Novel machine learning algorithms that use large amounts of data promise to find gene-gene interactions in order to build models with better predictive performance than PRS. Here, we present a data preprocessing step by using data-mining of contextual information to reduce the number of features, enabling machine learning algorithms to identify gene-gene interactions. We applied our approach to the Parkinson's Progression Markers Initiative (PPMI) dataset, an observational clinical study of 471 genotyped subjects (368 cases and 152 controls). With an AUC of 0.85 (95\% CI = [0.72; 0.96]), the interaction-based prediction model outperforms the PRS (AUC of 0.58 (95\% CI = [0.42; 0.81])). Furthermore, feature importance analysis of the model provided insights into the mechanism of Parkinson's disease. For instance, the model revealed an interaction of previously described drug target candidate genes TMEM175 and GAPDHP25. These results demonstrate that interaction-based machine learning models can improve genetic prediction models and might provide an answer to the missing heritability problem.}, language = {en} } @article{VaidSomaniRussaketal.2020, author = {Vaid, Akhil and Somani, Sulaiman and Russak, Adam J. and De Freitas, Jessica K. and Chaudhry, Fayzan F. and Paranjpe, Ishan and Johnson, Kipp W. and Lee, Samuel J. and Miotto, Riccardo and Richter, Felix and Zhao, Shan and Beckmann, Noam D. and Naik, Nidhi and Kia, Arash and Timsina, Prem and Lala, Anuradha and Paranjpe, Manish and Golden, Eddye and Danieletto, Matteo and Singh, Manbir and Meyer, Dara and O'Reilly, Paul F. and Huckins, Laura and Kovatch, Patricia and Finkelstein, Joseph and Freeman, Robert M. and Argulian, Edgar and Kasarskis, Andrew and Percha, Bethany and Aberg, Judith A. and Bagiella, Emilia and Horowitz, Carol R. and Murphy, Barbara and Nestler, Eric J. and Schadt, Eric E. and Cho, Judy H. and Cordon-Cardo, Carlos and Fuster, Valentin and Charney, Dennis S. and Reich, David L. and B{\"o}ttinger, Erwin and Levin, Matthew A. and Narula, Jagat and Fayad, Zahi A. and Just, Allan C. and Charney, Alexander W. and Nadkarni, Girish N. and Glicksberg, Benjamin S.}, title = {Machine learning to predict mortality and critical events in a cohort of patients with COVID-19 in New York City: model development and validation}, series = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR}, volume = {22}, journal = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR}, number = {11}, publisher = {Healthcare World}, address = {Richmond, Va.}, issn = {1439-4456}, doi = {10.2196/24018}, pages = {19}, year = {2020}, abstract = {Background: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. Objective: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. Methods: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. Results: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. Conclusions: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.}, language = {en} } @article{ChanJaladankiSomanietal.2021, author = {Chan, Lili and Jaladanki, Suraj K. and Somani, Sulaiman and Paranjpe, Ishan and Kumar, Arvind and Zhao, Shan and Kaufman, Lewis and Leisman, Staci and Sharma, Shuchita and He, John Cijiang and Murphy, Barbara and Fayad, Zahi A. and Levin, Matthew A. and B{\"o}ttinger, Erwin and Charney, Alexander W. and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.}, title = {Outcomes of patients on maintenance dialysis hospitalized with COVID-19}, series = {Clinical journal of the American Society of Nephrology : CJASN}, volume = {16}, journal = {Clinical journal of the American Society of Nephrology : CJASN}, number = {3}, publisher = {American Society of Nephrology}, address = {Washington}, organization = {Mount Sinai Covid I}, issn = {1555-9041}, doi = {10.2215/CJN.12360720}, pages = {452 -- 455}, year = {2021}, language = {en} } @article{DeFreitasJohnsonGoldenetal.2021, author = {De Freitas, Jessica K. and Johnson, Kipp W. and Golden, Eddye and Nadkarni, Girish N. and Dudley, Joel T. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin S. and Miotto, Riccardo}, title = {Phe2vec}, series = {Patterns}, volume = {2}, journal = {Patterns}, number = {9}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2666-3899}, doi = {10.1016/j.patter.2021.100337}, pages = {9}, year = {2021}, abstract = {Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.}, language = {en} }