Multiple Regression Analysis and Frequent Itemset Mining of Electronic Medical Records: A Visual Analytics Approach Using VISA_M3R3

Medication-induced acute kidney injury (AKI) is a well-known problem in clinical medicine. This paper reports the first development of a visual analytics (VA) system that examines how different medications associate with AKI. In this paper, we introduce and describe VISA_M3R3, a VA system designed to assist healthcare researchers in identifying medications and medication combinations that associate with a higher risk of AKI using electronic medical records (EMRs). By integrating multiple regression models, frequent itemset mining, data visualization, and human-data interaction mechanisms, VISA_M3R3 allows users to explore complex relationships between medications and AKI in such a way that would be difficult or sometimes even impossible without the help of a VA system. Through an analysis of 595 medications using VISA_M3R3, we have identified 55 AKI-inducing medications, 24,212 frequent medication groups, and 78 medication groups that are associated with AKI. The purpose of this paper is to demonstrate the usefulness of VISA_M3R3 in the investigation of medication-induced AKI in particular and other clinical problems in general. Furthermore, this research highlights what needs to be considered in the future when designing VA systems that are intended to support gaining novel and deep insights into massive existing EMRs.

[1]  Rebecca S Gruchalla,et al.  Clinical assessment of drug-induced disease , 2000, The Lancet.

[2]  Chia-Yi Wu,et al.  Cumulative Cardiovascular Polypharmacy Is Associated With the Risk of Acute Kidney Injury in Elderly Patients , 2015, Medicine.

[3]  E. Cook,et al.  Drug complications in outpatients , 2000, Journal of general internal medicine.

[4]  Brooke L. Gildon,et al.  Impact of Electronic Health Record Systems on Prescribing Errors in Pediatric Clinics , 2019, Healthcare.

[5]  Alexander Singer,et al.  The effect of electronic medical record system use on communication between pharmacists and prescribers , 2015, BMC Family Practice.

[6]  Dong Hyun Jeong,et al.  Designing a collaborative visual analytics system to support users’ continuous analytical processes , 2015, Human-centric Computing and Information Sciences.

[7]  N. Tatonetti,et al.  Artificial Intelligence for Drug Toxicity and Safety. , 2019, Trends in pharmacological sciences.

[8]  Miet Schetz,et al.  Drug-induced acute kidney injury , 2005, Current opinion in critical care.

[9]  Guang Chen,et al.  Visual analytics in the pharmaceutical industry , 2004, IEEE Computer Graphics and Applications.

[10]  Fei Wang,et al.  Mining and exploring care pathways from electronic medical records with visual analytics , 2015, J. Biomed. Informatics.

[11]  J. Kaufman,et al.  Community-acquired acute renal failure. , 1991, American journal of kidney diseases : the official journal of the National Kidney Foundation.

[12]  M. Malbrain,et al.  Acute renal failure due to bilateral lymphomatous infiltrates. Primary extranodal non-Hodgkin's lymphoma (p-EN-NHL) of the kidneys: does it really exist? , 1994, Clinical nephrology.

[13]  K. Ho,et al.  Benefits and risks of furosemide in acute kidney injury , 2010, Anaesthesia.

[14]  Fernando Perez-Ruiz,et al.  Treatment with Allopurinol is Associated with Lower Risk of Acute Kidney Injury in Patients with Gout: A Retrospective Analysis of a Nested Cohort , 2017, Rheumatology and Therapy.

[15]  N. Chen,et al.  Diuretics associated acute kidney injury: clinical and pathological analysis , 2014, Renal failure.

[16]  P. Honore,et al.  Do statins induce or protect from acute kidney injury and chronic kidney disease: An update review in 2018 , 2018, Journal of translational internal medicine.

[17]  Ognjen Gajic,et al.  Risk Factors for Development of Acute Kidney Injury in Critically Ill Patients: A Systematic Review and Meta-Analysis of Observational Studies , 2012, Critical care research and practice.

[18]  Kamran Sedig,et al.  Transactions on Human-computer Interaction Thci Design for Complex Cognitive Activities with Visual Representations: a Pattern-based Approach Sedig and Parsons Interaction Design for Complex Cognitive Activities with Visualizations , 2022 .

[19]  S. Goldstein,et al.  Acute kidney injury and increasing nephrotoxic-medication exposure in noncritically-ill children. , 2011, Clinical journal of the American Society of Nephrology : CJASN.

[20]  Jeffrey Heer,et al.  Interactive analysis of big data , 2012, XRDS.

[21]  N. Kolhe,et al.  Use of electronic results reporting to diagnose and monitor AKI in hospitalized patients. , 2012, Clinical journal of the American Society of Nephrology : CJASN.

[22]  Alok Sharma,et al.  An integrative machine learning approach for prediction of toxicity-related drug safety , 2018, Life Science Alliance.

[23]  Daniel A. Keim,et al.  Visual Analytics: Scope and Challenges , 2008, Visual Data Mining.

[24]  Jesus J. Caban,et al.  Visual analytics in healthcare - opportunities and research challenges , 2015, J. Am. Medical Informatics Assoc..

[25]  David W. Bates,et al.  A computerized method for identifying incidents associated with adverse drug events in outpatients , 2001, Int. J. Medical Informatics.

[26]  Kamran Sedig,et al.  VINCENT: A visual analytics system for investigating the online vaccine debate. , 2019, Online journal of public health informatics.

[27]  Jianying Hu,et al.  Predicting adverse drug reactions through interpretable deep learning framework , 2018, BMC Bioinformatics.

[28]  Krishan Kumar,et al.  Innovation in Pharmacovigilance: Use of Artificial Intelligence in Adverse Event Case Processing , 2018, Clinical pharmacology and therapeutics.

[29]  Robert Spence Sensitivity Encoding to Support Information Space Navigation: A Design Guideline , 2002, Inf. Vis..

[30]  S. Hou,et al.  Hospital-acquired renal insufficiency. , 2002, American journal of kidney diseases : the official journal of the National Kidney Foundation.

[31]  Kamran Sedig,et al.  Discourse with Visual Health Data: Design of Human-Data Interaction , 2018, Multimodal Technol. Interact..

[32]  Kwan-Liu Ma,et al.  A novel tool for visualizing chronic kidney disease associated polymorbidity: a 13-year cohort study in Taiwan , 2015, J. Am. Medical Informatics Assoc..

[33]  Abha Agrawal Medication errors: prevention using information technology systems. , 2009, British journal of clinical pharmacology.

[34]  T. Murdoch,et al.  The inevitable application of big data to health care. , 2013, JAMA.

[35]  Vishal R. Tandon,et al.  Drug-induced diseases (DIDs): An experience of a tertiary care teaching hospital from India , 2015, The Indian journal of medical research.

[36]  Jorge A. Gálvez,et al.  Optimization of drug-drug interaction alert rules in a pediatric hospital's electronic health record system using a visual analytics dashboard , 2015, J. Am. Medical Informatics Assoc..

[37]  Terry J. Hannan,et al.  Detecting adverse drug reactions to improve patient outcomes , 1999, Int. J. Medical Informatics.

[38]  D. Steinbrüchel,et al.  Acute kidney injury is independently associated with higher mortality after cardiac surgery. , 2014, Journal of cardiothoracic and vascular anesthesia.

[39]  A. McCoy,et al.  Using Electronic Health Records to Identify Adverse Drug Events in Ambulatory Care: A Systematic Review , 2019, Applied Clinical Informatics.

[40]  John A Kellum,et al.  Drug Class Combination–Associated Acute Kidney Injury , 2016, The Annals of pharmacotherapy.

[41]  Joseph Varon,et al.  Acute Kidney Injury and Cardiovascular Outcomes in Acute Severe Hypertension , 2010, Circulation.

[42]  M. Rosner,et al.  Drug-Induced Kidney Injury in the Elderly , 2017, Drugs & Aging.

[43]  Marcello Maggio,et al.  Medication-Induced Nephrotoxicity in Older Patients. , 2016, Current drug metabolism.

[44]  Walter Gall,et al.  Effects of Shared Electronic Health Record Systems on Drug-Drug Interaction and Duplication Warning Detection , 2015, BioMed research international.

[45]  Eric McArthur,et al.  Antihypertensive medications and the risk of kidney stones in older adults: a retrospective cohort study , 2017, Hypertension Research.

[46]  Joëlle Micallef,et al.  The drugs that mostly frequently induce acute kidney injury: a case − noncase study of a pharmacovigilance database , 2017, British journal of clinical pharmacology.

[47]  John R Wilson,et al.  Fundamentals of systems ergonomics/human factors. , 2014, Applied ergonomics.

[48]  Ann Blandford,et al.  Making sense of personal health information: Challenges for information visualization , 2013, Health Informatics J..

[49]  Jure Leskovec,et al.  Modeling polypharmacy side effects with graph convolutional networks , 2018, bioRxiv.

[50]  A. Polliack,et al.  Kidney involvement and renal manifestations in non‐Hodgkin's lymphoma and lymphocytic leukemia: a retrospective study in 700 patients , 2001, European journal of haematology.

[51]  Yuval Shahar,et al.  Exploration of patterns predicting renal damage in patients with diabetes type II using a visual temporal analysis laboratory , 2015, J. Am. Medical Informatics Assoc..

[52]  Tomasz Imielinski,et al.  Database Mining: A Performance Perspective , 1993, IEEE Trans. Knowl. Data Eng..

[53]  Silvia Miksch,et al.  Visualization methods for data analysis and planning in medical applications , 2002, Int. J. Medical Informatics.

[54]  Bin Li,et al.  Applications of machine learning in drug discovery and development , 2019, Nature Reviews Drug Discovery.

[55]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[56]  D. Swinkels,et al.  Iron metabolism in the pathogenesis of iron-induced kidney injury , 2013, Nature Reviews Nephrology.

[57]  Jarke J. van Wijk,et al.  Visualization of Medicine Prescription Behavior , 2014, Comput. Graph. Forum.

[58]  James J. Thomas,et al.  Defining Insight for Visual Analytics , 2009, IEEE Computer Graphics and Applications.

[59]  Shaun J. Grannis,et al.  Data visualization speeds review of potential adverse drug events in patients on multiple medications , 2010, J. Biomed. Informatics.

[60]  Noreen Kamal,et al.  Big Data and Visual Analytics in Health and Medicine: From Pipe Dream to Reality , 2014 .

[61]  Andrew Kusiak,et al.  Feature transformation methods in data mining , 2001 .

[62]  Helwig Hauser,et al.  Visualization and Visual Analysis of Multifaceted Scientific Data: A Survey , 2013, IEEE Transactions on Visualization and Computer Graphics.

[63]  M. Devonald,et al.  A real-time electronic alert to improve detection of acute kidney injury in a large teaching hospital. , 2014, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[64]  Daniel A. Keim,et al.  Visual analytics: how much visualization and how much analytics? , 2010, SKDD.

[65]  C. Lee,et al.  Medical big data: promise and challenges , 2017, Kidney research and clinical practice.

[66]  Wenqiang Cui,et al.  Visual Analytics: A Comprehensive Overview , 2019, IEEE Access.

[67]  Vikas Kumar,et al.  Understanding variations in pediatric asthma care processes in the emergency department using visual analytics , 2015, J. Am. Medical Informatics Assoc..

[68]  Marco D. Huesch,et al.  Health Affairs Challenges Implementing Electronic Health Care Predictive Analytics : Considerations And , 2014 .

[69]  Jimeng Sun,et al.  Multifaceted visual analytics for healthcare applications , 2012, IBM J. Res. Dev..

[70]  Ratu Ilma Indra Putri,et al.  Developing Ill-defined problem-solving for the context of “South Sumatera” , 2017 .

[71]  Rainu Kaushal,et al.  Electronic prescribing within an electronic health record reduces ambulatory prescribing errors. , 2011, Joint Commission journal on quality and patient safety.