Browsing by Author "Schadow, Gunther"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    An Automated System for Generating Situation-Specific Decision Support in Clinical Order Entry from Local Empirical Data
    (2011-10-19) Klann, Jeffrey G.; Schadow, Gunther; Downs, Stephen M.; Finnell, John T.; Palakal, Mathew J.; Szolovits, Peter
    Clinical Decision Support is one of the only aspects of health information technology that has demonstrated decreased costs and increased quality in healthcare delivery, yet it is extremely expensive and time-consuming to create, maintain, and localize. Consequently, a majority of health care systems do not utilize it, and even when it is available it is frequently incorrect. Therefore it is important to look beyond traditional guideline-based decision support to more readily available resources in order to bring this technology into widespread use. This study proposes that the wisdom of physicians within a practice is a rich, untapped knowledge source that can be harnessed for this purpose. I hypothesize and demonstrate that this wisdom is reflected by order entry data well enough to partially reconstruct the knowledge behind treatment decisions. Automated reconstruction of such knowledge is used to produce dynamic, situation-specific treatment suggestions, in a similar vein to Amazon.com shopping recommendations. This approach is appealing because: it is local (so it reflects local standards); it fits into workflow more readily than the traditional local-wisdom approach (viz. the curbside consult); and, it is free (the data are already being captured). This work develops several new machine-learning algorithms and novel applications of existing algorithms, focusing on an approach called Bayesian network structure learning. I develop: an approach to produce dynamic, rank-ordered situation-specific treatment menus from treatment data; statistical machinery to evaluate their accuracy using retrospective simulation; a novel algorithm which is an order of magnitude faster than existing algorithms; a principled approach to choosing smaller, more optimal, domain-specific subsystems; and a new method to discover temporal relationships in the data. The result is a comprehensive approach for extracting knowledge from order-entry data to produce situation-specific treatment menus, which is applied to order-entry data at Wishard Hospital in Indianapolis. Retrospective simulations find that, in a large variety of clinical situations, a short menu will contain the clinicians' desired next actions. A prospective survey additionally finds that such menus aid physicians in writing order sets (in completeness and speed). This study demonstrates that clinical knowledge can be successfully extracted from treatment data for decision support.
  • Thumbnail Image
    Item
    Decision Support from Local Data: Creating Adaptive Order Menus from Past Clinician Behavior
    (Elsevier, 2014-04) Klann, Jeffrey G.; Szolovits, Peter; Downs, Stephen; Schadow, Gunther; Department of Pediatrics, IU School of Medicine
    Objective Reducing care variability through guidelines has significantly benefited patients. Nonetheless, guideline-based clinical decision support (CDS) systems are not widely implemented or used, are frequently out-of-date, and cannot address complex care for which guidelines do not exist. Here, we develop and evaluate a complementary approach - using Bayesian network (BN) learning to generate adaptive, context-specific treatment menus based on local order-entry data. These menus can be used as a draft for expert review, in order to minimize development time for local decision support content. This is in keeping with the vision outlined in the US Health Information Technology Strategic Plan, which describes a healthcare system that learns from itself. Materials and Methods We used the Greedy Equivalence Search algorithm to learn four 50-node domain-specific BNs from 11,344 encounters: abdominal pain in the emergency department, inpatient pregnancy, hypertension in the urgent visit clinic, and altered mental state in the intensive care unit. We developed a system to produce situation-specific, rank-ordered treatment menus from these networks. We evaluated this system with a hospital-simulation methodology and computed Area Under the Receiver-Operator Curve (AUC) and average menu position at time of selection. We also compared this system with a similar association-rule-mining approach. Results A short order menu on average contained the next order (weighted average length 3.91–5.83 items). Overall predictive ability was good: average AUC above 0.9 for 25% of order types and overall average AUC .714–.844 (depending on domain). However, AUC had high variance (.50–.99). Higher AUC correlated with tighter clusters and more connections in the graphs, indicating importance of appropriate contextual data. Comparison with an association rule mining approach showed similar performance for only the most common orders with dramatic divergence as orders are less frequent. Discussion and Conclusion This study demonstrates that local clinical knowledge can be extracted from treatment data for decision support. This approach is appealing because: it reflects local standards; it uses data already being captured; and it produces human-readable treatment-diagnosis networks that could be curated by a human expert to reduce workload in developing localized CDS content. The BN methodology captured transitive associations and co-varying relationships, which existing approaches do not. It also performs better as orders become less frequent and require more context. This system is a step forward in harnessing local, empirical data to enhance decision support.
  • Thumbnail Image
    Item
    A HYBRID APPROACH FOR TRANSLATIONAL RESEARCH
    (2010-06-01T17:00:11Z) Webster, Yue Wang; Jones, Josette F.; Palakal, Mathew J.; Schadow, Gunther; Dow, Ernst R.
    Translational research has proven to be a powerful process that bridges the gap between basic science and medical practice. The complexity of translational research is two-fold: integration of vast amount of information in disparate silos, and dissemination of discoveries to stakeholders with different interests. We designed and implemented a hybrid knowledge discovery framework. We developed strategies to leverage both traditional biomedical databases and Health Social Network Communities content in the discovery process. Heuristic and quantitative evaluations were carried out in Colorectal Cancer and Amyotrophic Lateral Sclerosis disease areas. The results demonstrate the potential of our approach to bridge silos and to identify hidden links among clinical observations, drugs, genes and diseases, which may eventually lead to the discovery of novel disease targets, biomarkers and therapies.
  • Thumbnail Image
    Item
    A PROBABILISTIC APPROACH TO DATA INTEGRATION IN BIOMEDICAL RESEARCH: THE IsBIG EXPERIMENTS
    (2011-03-16) Anand, Vibha; Palakal, Mathew J.; Downs, Stephen M.; McDaniel, Anna M.; Schadow, Gunther
    Biomedical research has produced vast amounts of new information in the last decade but has been slow to find its use in clinical applications. Data from disparate sources such as genetic studies and summary data from published literature have been amassed, but there is a significant gap, primarily due to a lack of normative methods, in combining such information for inference and knowledge discovery. In this research using Bayesian Networks (BN), a probabilistic framework is built to address this gap. BN are a relatively new method of representing uncertain relationships among variables using probabilities and graph theory. Despite their computational complexity of inference, BN represent domain knowledge concisely. In this work, strategies using BN have been developed to incorporate a range of available information from both raw data sources and statistical and summary measures in a coherent framework. As an example of this framework, a prototype model (In-silico Bayesian Integration of GWAS or IsBIG) has been developed. IsBIG integrates summary and statistical measures from the NIH catalog of genome wide association studies (GWAS) and the database of human genome variations from the international HapMap project. IsBIG produces a map of disease to disease associations as inferred by genetic linkages in the population. Quantitative evaluation of the IsBIG model shows correlation with empiric results from our Electronic Medical Record (EMR) – The Regenstrief Medical Record System (RMRS). Only a small fraction of disease to disease associations in the population can be explained by the linking of a genetic variation to a disease association as studied in the GWAS. None the less, the model appears to have found novel associations among some diseases that are not described in the literature but are confirmed in our EMR. Thus, in conclusion, our results demonstrate the potential use of a probabilistic modeling approach for combining data from disparate sources for inference and knowledge discovery purposes in biomedical research.
  • Thumbnail Image
    Item
    Signature Center for Computational Diagnostics Translating Experimental Technologies into Clinical Research
    (Office of the Vice Chancellor for Research, 2010-04-09) Ragg, Susanne; Schadow, Gunther
    The goal of the Center for Computational Diagnostics [http://www.iupui.edu/~compdiag] is to serve as a “reactor” of innovative research for the integration of diverse high throughput technology into clinical trials to allow clinical researchers to obtain a more comprehensive view of the disease states. It has become clear that to better understand diseases we cannot continue to only focus on single genes, proteins or metabolites operating in single linear ordered pathways. Large scale high throughput technologies such as applied in genomics, proteomics and metabolomics allow for a more comprehensive view of the complex interactions occurring within body fluids or tissues at any one time. The Center operates by addressing the three different areas that are required to successfully integrate high throughput methodologies into translational research: 1) High throughput biospecimen banking; 2) Generation of high quality datasets and 3) Workflow development for data storage and analysis. To support high throughput bio-specimen banking we have co-developed caTissue Suite under the national caBIG effort. The key developments of the Center have been: 1. CaTrack, an intelligent barcode-based automatic data capture system 2. protocol-driven Study Calendar 3. xCaCORE, an innovative XML-based data import and export software program 4. Scalable, globally unique specimen identification utilizing an ISO Object Identifiers encoding scheme 5. Barcode generator and label printing We have implemented the Pediatric Biospecimen Repository to be able to develop and test these informatics tools. In addition to functioning as the development and test site for informatics research, the repository also develops research protocols and stores biospecimens for Pediatrics, Ophthalmology and Obstetrics. We also support protocol and data management related to biospecimens for the CTSI and the Fairbanks Institute. We currently have 92 active protocols and data on 119,319 specimens in our production instance of caTissue Suite. This includes specimens from 1200 well-defined healthy control subjects across all age groups including 600 children. To develop the computational and statistical workflows for data storage and analysis, we have generated large well-designed datasets for coronary artery disease (LC-MS/MS, NMR, protein antibody arrays); cancer (osteosarcoma and Wilms tumor; LC-MS/MS, NMR, protein antibody arrays) and ophthalmologic diseases (glaucoma; protein antibody arrays). Our main focus is to develop analytical workflows that translate the large datasets into relevant information for clinical researchers, focusing on the biological interpretation of the results. In this context we developed statistical models for protein quantification for LC-MS/MS and protein antibody arrays. These workflows were implemented in the open source statistical software R and published under the R-based project Bioconductor.