Peggy Peissig
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Peggy Peissig has a total of 143 co-authors. Here are the top co-authors by number of shared publications:
- David Page
Department of Biostatistics and Medical Informatics University of Wisconsin -Madison Madison WI
13 shared publications - Luke V. Rasmussen
Division of Biostatistics and Informatics, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
6 shared publications - Michael D. Caldwell
Marshfield Clinic
6 shared publications - Joshua C. Denny
National Institutes of Health
5 shared publications - Vítor Santos Costa
University of Porto
5 shared publications - Zhaobin Kuang
University of Wisconsin
5 shared publications
Latest Publications
- Open Access
High-Throughput Approach to Modeling Healthcare Costs Using Electronic Healthcare Records
Accurate estimation of healthcare costs is crucial for healthcare systems to plan and effectively negotiate with insurance companies regarding the coverage of patient-care costs. Greater accuracy in estimating healthcare costs would provide mutual benefit for both health systems and the insurers that support these systems by better aligning payment models with patient-care costs. This study presents the results of a generalizable machine learning approach to predicting medical events built from 40 years of data from >860,000 patients pertaining to >6,700 prescription medications, courtesy of Marshfield Clinic in Wisconsin. It was found that models built using this approach performed well when compared to similar studies predicting physician prescriptions of individual medications. In addition to providing a comprehensive predictive model for all drugs in a large healthcare system, the approach taken in this research benefits from potential applicability to a wide variety of other medical events.
Open AccessHigh-Throughput Approach to Modeling Healthcare Costs Using Electronic Healthcare Records
Accurate estimation of healthcare costs is crucial for healthcare systems to plan and effectively negotiate with insurance companies regarding the coverage of patient-care costs. Greater accuracy in estimating healthcare costs would provide mutual benefit for both health systems and the insurers that support these systems by better aligning payment models with patient-care costs. This study presents the results of a generalizable machine learning approach to predicting medical events built from 40 years of data from >860,000 patients pertaining to >6,700 prescription medications, courtesy of Marshfield Clinic in Wisconsin. It was found that models built using this approach performed well when compared to similar studies predicting physician prescriptions of individual medications. In addition to providing a comprehensive predictive model for all drugs in a large healthcare system, the approach taken in this research benefits from potential applicability to a wide variety of other medical events.
- Open Access
Multi-ancestry Genome- and Phenome-wide Association Studies of Diverticular Disease in Electronic Health Records with Natural Language Processing enriched phenotype algorithm
Background and aims: Diverticular disease is among the most prevalent conditions encountered by gastroenterologists, affecting ∼50% of Americans before the age of 60. Our aim was to identify genetic risk variants and clinical phenotypes associated with diverticular disease, utilizing the electronic health record (EHR) with Natural Language Processing (NLP). Methods: We developed a NLP-enriched phenotype algorithm that incorporated colonoscopy or abdominal imaging reports to accurately identify patients with diverticulosis and diverticulitis from multicenter EHRs. We performed genome-wide association studies (GWAS) of diverticular disease in European, African and multi-ancestry participants, followed by phenome-wide association studies (PheWAS) of the risk variants to identify their potential comorbid/pleiotropic effects in the clinical phenome. For more in-depth investigation of associated clinical phenotypes, we also performed PheWAS with the previously reported 52 GWAS susceptibility variants for diverticular disease. Results: Ancestry-stratified GWAS analyses confirmed the well-established associations between ARHGAP15 loci with diverticular disease in European cohorts, and found similar positive effect sizes in African cohorts but with non-significant p-values. With overall intensified GWAS signals in diverticulitis patients compared to diverticulosis patients, we found substantial genetic correlations between diverticulosis and diverticulitis, up to 0.997 in European ancestry. PheWAS analyses identified associations between the diverticular disease GWAS variants and circulatory system, genitourinary, and neoplastic EHR phenotypes. Conclusion: Our multiancestry GWAS-PheWAS study demonstrated an effective use of multidimensional EHR information in disease case/control classification with NLP for more comprehensive and scalable phenotyping, and implementation of an integrative analytical pipeline to facilitate etiological investigation of a disease from a clinical perspective.
Open AccessMulti-ancestry Genome- and Phenome-wide Association Studies of Diverticular Disease in Electronic Health Records with Natural Language Processing enriched phenotype algorithm
Background and aims: Diverticular disease is among the most prevalent conditions encountered by gastroenterologists, affecting ∼50% of Americans before the age of 60. Our aim was to identify genetic risk variants and clinical phenotypes associated with diverticular disease, utilizing the electronic health record (EHR) with Natural Language Processing (NLP). Methods: We developed a NLP-enriched phenotype algorithm that incorporated colonoscopy or abdominal imaging reports to accurately identify patients with diverticulosis and diverticulitis from multicenter EHRs. We performed genome-wide association studies (GWAS) of diverticular disease in European, African and multi-ancestry participants, followed by phenome-wide association studies (PheWAS) of the risk variants to identify their potential comorbid/pleiotropic effects in the clinical phenome. For more in-depth investigation of associated clinical phenotypes, we also performed PheWAS with the previously reported 52 GWAS susceptibility variants for diverticular disease. Results: Ancestry-stratified GWAS analyses confirmed the well-established associations between ARHGAP15 loci with diverticular disease in European cohorts, and found similar positive effect sizes in African cohorts but with non-significant p-values. With overall intensified GWAS signals in diverticulitis patients compared to diverticulosis patients, we found substantial genetic correlations between diverticulosis and diverticulitis, up to 0.997 in European ancestry. PheWAS analyses identified associations between the diverticular disease GWAS variants and circulatory system, genitourinary, and neoplastic EHR phenotypes. Conclusion: Our multiancestry GWAS-PheWAS study demonstrated an effective use of multidimensional EHR information in disease case/control classification with NLP for more comprehensive and scalable phenotyping, and implementation of an integrative analytical pipeline to facilitate etiological investigation of a disease from a clinical perspective.
- Open Access
Temporal Poisson Square Root Graphical Models
We propose temporal Poisson square root graphical models (TPSQRs), a generalization of Poisson square root graphical models (PSQRs) specifically designed for modeling longitudinal event data. By estimating the temporal relationships for all possible pairs of event types, TPSQRs can offer a holistic perspective about whether the occurrences of any given event type could excite or inhibit any other type. A TPSQR is learned by estimating a collection of interrelated PSQRs that share the same template parameterization. These PSQRs are estimated jointly in a pseudo-likelihood fashion, where Poisson pseudo-likelihood is used to approximate the original more computationally-intensive pseudo-likelihood problem stemming from PSQRs. Theoretically, we demonstrate that under mild assumptions, the Poisson pseudo-likelihood approximation is sparsistent for recovering the underlying PSQR. Empirically, we learn TPSQRs from Marshfield Clinic electronic health records (EHRs) with millions of drug prescription and condition diagnosis events, for adverse drug reaction (ADR) detection. Experimental results demonstrate that the learned TPSQRs can recover ADR signals from the EHR effectively and efficiently.
Open AccessTemporal Poisson Square Root Graphical Models
We propose temporal Poisson square root graphical models (TPSQRs), a generalization of Poisson square root graphical models (PSQRs) specifically designed for modeling longitudinal event data. By estimating the temporal relationships for all possible pairs of event types, TPSQRs can offer a holistic perspective about whether the occurrences of any given event type could excite or inhibit any other type. A TPSQR is learned by estimating a collection of interrelated PSQRs that share the same template parameterization. These PSQRs are estimated jointly in a pseudo-likelihood fashion, where Poisson pseudo-likelihood is used to approximate the original more computationally-intensive pseudo-likelihood problem stemming from PSQRs. Theoretically, we demonstrate that under mild assumptions, the Poisson pseudo-likelihood approximation is sparsistent for recovering the underlying PSQR. Empirically, we learn TPSQRs from Marshfield Clinic electronic health records (EHRs) with millions of drug prescription and condition diagnosis events, for adverse drug reaction (ADR) detection. Experimental results demonstrate that the learned TPSQRs can recover ADR signals from the EHR effectively and efficiently.
- Open Access
- 16 August 2019
- Published by MDPI AG in Algorithms
- Vol. 12 (8) , 171
An Application of Manifold Learning in Global Shape Descriptors
With the rapid expansion of applied 3D computational vision, shape descriptors have become increasingly important for a wide variety of applications and objects from molecules to planets. Appropriate shape descriptors are critical for accurate (and efficient) shape retrieval and 3D model classification. Several spectral-based shape descriptors have been introduced by solving various physical equations over a 3D surface model. In this paper, for the first time, we incorporate a specific manifold learning technique, introduced in statistics and machine learning, to develop a global, spectral-based shape descriptor in the computer graphics domain. The proposed descriptor utilizes the Laplacian Eigenmap technique in which the Laplacian eigenvalue problem is discretized using an exponential weighting scheme. As a result, our descriptor eliminates the limitations tied to the existing spectral descriptors, namely dependency on triangular mesh representation and high intra-class quality of 3D models. We also present a straightforward normalization method to obtain a scale-invariant and noise-resistant descriptor. The extensive experiments performed in this study using two standard 3D shape benchmarks—high-resolution TOSCA and McGill datasets—demonstrate that the present contribution provides a highly discriminative and robust shape descriptor under the presence of a high level of noise, random scale variations, and low sampling rate, in addition to the known isometric-invariance property of the Laplace–Beltrami operator. The proposed method significantly outperforms state-of-the-art spectral descriptors in shape retrieval and classification. The proposed descriptor is limited to closed manifolds due to its inherited inability to accurately handle manifolds with boundaries.
- 16 August 2019
- Published by MDPI AG in Algorithms
- Vol. 12 (8) , 171
Open AccessAn Application of Manifold Learning in Global Shape Descriptors
With the rapid expansion of applied 3D computational vision, shape descriptors have become increasingly important for a wide variety of applications and objects from molecules to planets. Appropriate shape descriptors are critical for accurate (and efficient) shape retrieval and 3D model classification. Several spectral-based shape descriptors have been introduced by solving various physical equations over a 3D surface model. In this paper, for the first time, we incorporate a specific manifold learning technique, introduced in statistics and machine learning, to develop a global, spectral-based shape descriptor in the computer graphics domain. The proposed descriptor utilizes the Laplacian Eigenmap technique in which the Laplacian eigenvalue problem is discretized using an exponential weighting scheme. As a result, our descriptor eliminates the limitations tied to the existing spectral descriptors, namely dependency on triangular mesh representation and high intra-class quality of 3D models. We also present a straightforward normalization method to obtain a scale-invariant and noise-resistant descriptor. The extensive experiments performed in this study using two standard 3D shape benchmarks—high-resolution TOSCA and McGill datasets—demonstrate that the present contribution provides a highly discriminative and robust shape descriptor under the presence of a high level of noise, random scale variations, and low sampling rate, in addition to the known isometric-invariance property of the Laplace–Beltrami operator. The proposed method significantly outperforms state-of-the-art spectral descriptors in shape retrieval and classification. The proposed descriptor is limited to closed manifolds due to its inherited inability to accurately handle manifolds with boundaries.
- 14 December 2018
- Published by Springer Nature
- Vol. 1903, 255-267
A Machine-Learning-Based Drug Repurposing Approach Using Baseline Regularization
We present the baseline regularization model for computational drug repurposing using electronic health records (EHRs). In EHRs, drug prescriptions of various drugs are recorded throughout time for various patients. In the same time, numeric physical measurements (e.g., fasting blood glucose level) are also recorded. Baseline regularization uses statistical relationships between the occurrences of prescriptions of some particular drugs and the increase or the decrease in the values of some particular numeric physical measurements to identify potential repurposing opportunities.
- 14 December 2018
- Published by Springer Nature
- Vol. 1903, 255-267
A Machine-Learning-Based Drug Repurposing Approach Using Baseline Regularization
We present the baseline regularization model for computational drug repurposing using electronic health records (EHRs). In EHRs, drug prescriptions of various drugs are recorded throughout time for various patients. In the same time, numeric physical measurements (e.g., fasting blood glucose level) are also recorded. Baseline regularization uses statistical relationships between the occurrences of prescriptions of some particular drugs and the increase or the decrease in the values of some particular numeric physical measurements to identify potential repurposing opportunities.
- Open Access
Relationship between Parathyroid Hormone Levels and Hazards of Fracture, Vascular Events and Death in Stage 3 and 4 Chronic Kidney Disease
Background and Objectives: Chronic kidney disease (CKD) affects ∼20% of older adults and secondary hyperparathyroidism (HPT) is a common condition in these patients. Studies have linked HPT to a greater risk of fractures, vascular events and mortality. However, the optimal parathyroid hormone (PTH) level needed to minimize these events remains uncertain. Design, setting, participants and measurements: We assessed relationships between baseline serum PTH levels and the subsequent 10-year probability of clinical fractures, vascular events and death in stage 3 and 4 CKD patients. We used Marshfield Clinic Health System electronic health records to analyze data from adult CKD patients spanning from 1985 to 2013. We required ≥2 PTH measurements at baseline and used ICD-9 codes to identify medical conditions, fractures, vascular events and death. In multivariate models, we assessed relationships between serum PTH and the three clinical outcomes, controlling for age, gender, co-morbidities and osteoporosis medication. Results: 7594 subjects had a mean age of 68±13 years and 55% were women. Fractures, vascular events and death occurred in 19%, 60% and 29% of the cohort, respectively. In multivariate models including the whole cohort regardless of PTH assay, the probability of fracture, vascular events and death were minimized at a PTH of 23, 50 and 50 pg/mL. Below these cutpoints, the probability of fractures and death dramatically increased. When confining the analysis to patients measured using a 2 nd generation PTH assay (n=5108), the hazards of fracture, vascular events and death were minimized at a PTH of zero, 60 and 58 pg/mL. Any of these clinical outcomes was minimized at a baseline PTH of 58 pg/mL. Conclusions: Our study suggests that parathyroid hormone levels around 60 pg/mL might reduce the risk of fractures, vascular events and death in CKD patients. Additional epidemiologic studies and randomized clinical trials are needed to confirm these findings.
Open AccessRelationship between Parathyroid Hormone Levels and Hazards of Fracture, Vascular Events and Death in Stage 3 and 4 Chronic Kidney Disease
Background and Objectives: Chronic kidney disease (CKD) affects ∼20% of older adults and secondary hyperparathyroidism (HPT) is a common condition in these patients. Studies have linked HPT to a greater risk of fractures, vascular events and mortality. However, the optimal parathyroid hormone (PTH) level needed to minimize these events remains uncertain. Design, setting, participants and measurements: We assessed relationships between baseline serum PTH levels and the subsequent 10-year probability of clinical fractures, vascular events and death in stage 3 and 4 CKD patients. We used Marshfield Clinic Health System electronic health records to analyze data from adult CKD patients spanning from 1985 to 2013. We required ≥2 PTH measurements at baseline and used ICD-9 codes to identify medical conditions, fractures, vascular events and death. In multivariate models, we assessed relationships between serum PTH and the three clinical outcomes, controlling for age, gender, co-morbidities and osteoporosis medication. Results: 7594 subjects had a mean age of 68±13 years and 55% were women. Fractures, vascular events and death occurred in 19%, 60% and 29% of the cohort, respectively. In multivariate models including the whole cohort regardless of PTH assay, the probability of fracture, vascular events and death were minimized at a PTH of 23, 50 and 50 pg/mL. Below these cutpoints, the probability of fractures and death dramatically increased. When confining the analysis to patients measured using a 2 nd generation PTH assay (n=5108), the hazards of fracture, vascular events and death were minimized at a PTH of zero, 60 and 58 pg/mL. Any of these clinical outcomes was minimized at a baseline PTH of 58 pg/mL. Conclusions: Our study suggests that parathyroid hormone levels around 60 pg/mL might reduce the risk of fractures, vascular events and death in CKD patients. Additional epidemiologic studies and randomized clinical trials are needed to confirm these findings.
- Open Access
- 15 January 2018
- Published by JMIR Publications Inc. in JMIR Preprints
Machine Intelligence to Assist Visually Impaired People: A Big Data Deep Neural Network Adventure
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Blindness or vision impairment, one of the top ten disabilities among men and women, targets more than 7 million Americans of almost all ages. Accessible visual information is of paramount importance to improve independence and safety of blind and visually-impaired people, and there is a pressing need to develop smart automated systems to assist their navigation, particularly in unfamiliar healthcare environments, such as clinics, hospitals, and urgent cares. Objective: The main objective of the current contribution was to develop computational vision algorithms composed with deep neural network to assist visually impaired individual's mobility in clinical environments by accurately detecting doors, stairs, and signages, the most remarkable landmarks. Methods: A dataset of indoor landmarks of interests was collected from Marshfield Clinic in Marshfield. To increase the accuracy and stability of predictive model, an augmented dataset was generated by adding several variations to the collected one. A deep convolutional neural network (CNN), namely “AlexNet” was then utilized and trained with both datasets. The CNN model was configured in two different strategies: (1) Transfer Learning (TL), (2) Feature Extraction (FEx) combined with three different classifiers, namely Support Vector Machine (SVM), Naïve Bayesian (NB) and K-Nearest Neighbor (KNN). To speed up the training process and make a real-time decision, NVIDIA GPU Quadro M5000 was employed. Results: The CNN is trained with TL and FEx approaches using 10%, 20% and 30% of both collected and augmented datasets. While training time of FEx model is in the order of a few minutes, TL model requires 10-20 times more time. The average object recognition time of both approaches is less than 0.3 seconds. The accuracy of recognizing objects of interest is more than 98% regardless of training size. However, the accuracy of TL model varies from about 60% to 99% with respect to the training size. Conclusions: Even though GPU processors extremely increase the speed of computing compared with CPUs, training time of TL approach is unbearable. However, both approaches on the stage of test sample evaluation are fast enough to be used in real-time applications. FEx accompanied with either NB, SVM or KNN classifiers achieves accuracy of greater than 98% even with small training set size. To compete with FEx approach with respect to accuracy, recall and precision, TL requires larger training set. For detecting three objects of interest that are common in any health care facility, the CNN model based on FEx is a pragmatic option. The proposed framework has the potential to recognize a variety of objects in the indoor environment, and ultimately to help visually-impaired people navigate their way in the clinic independently.
- 15 January 2018
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessMachine Intelligence to Assist Visually Impaired People: A Big Data Deep Neural Network Adventure
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Blindness or vision impairment, one of the top ten disabilities among men and women, targets more than 7 million Americans of almost all ages. Accessible visual information is of paramount importance to improve independence and safety of blind and visually-impaired people, and there is a pressing need to develop smart automated systems to assist their navigation, particularly in unfamiliar healthcare environments, such as clinics, hospitals, and urgent cares. Objective: The main objective of the current contribution was to develop computational vision algorithms composed with deep neural network to assist visually impaired individual's mobility in clinical environments by accurately detecting doors, stairs, and signages, the most remarkable landmarks. Methods: A dataset of indoor landmarks of interests was collected from Marshfield Clinic in Marshfield. To increase the accuracy and stability of predictive model, an augmented dataset was generated by adding several variations to the collected one. A deep convolutional neural network (CNN), namely “AlexNet” was then utilized and trained with both datasets. The CNN model was configured in two different strategies: (1) Transfer Learning (TL), (2) Feature Extraction (FEx) combined with three different classifiers, namely Support Vector Machine (SVM), Naïve Bayesian (NB) and K-Nearest Neighbor (KNN). To speed up the training process and make a real-time decision, NVIDIA GPU Quadro M5000 was employed. Results: The CNN is trained with TL and FEx approaches using 10%, 20% and 30% of both collected and augmented datasets. While training time of FEx model is in the order of a few minutes, TL model requires 10-20 times more time. The average object recognition time of both approaches is less than 0.3 seconds. The accuracy of recognizing objects of interest is more than 98% regardless of training size. However, the accuracy of TL model varies from about 60% to 99% with respect to the training size. Conclusions: Even though GPU processors extremely increase the speed of computing compared with CPUs, training time of TL approach is unbearable. However, both approaches on the stage of test sample evaluation are fast enough to be used in real-time applications. FEx accompanied with either NB, SVM or KNN classifiers achieves accuracy of greater than 98% even with small training set size. To compete with FEx approach with respect to accuracy, recall and precision, TL requires larger training set. For detecting three objects of interest that are common in any health care facility, the CNN model based on FEx is a pragmatic option. The proposed framework has the potential to recognize a variety of objects in the indoor environment, and ultimately to help visually-impaired people navigate their way in the clinic independently.
- Open Access
- 8 December 2017
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 5 (4) , e51
Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure
Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.
- 8 December 2017
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 5 (4) , e51
Open AccessAdverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure
Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.
- Open Access
- 13 October 2017
- Published by JMIR Publications Inc.
- Vol. 5 (4) , e51
Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure
Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.
- 13 October 2017
- Published by JMIR Publications Inc.
- Vol. 5 (4) , e51
Open AccessAdverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure
Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.
- Open Access
- 13 September 2017
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 5 (3) , e27
Prototype Development: Context-Driven Dynamic XML Ophthalmologic Data Capture Application
Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.
- 13 September 2017
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 5 (3) , e27
Open AccessPrototype Development: Context-Driven Dynamic XML Ophthalmologic Data Capture Application
Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.