Browsing by Subject "informatics"
Now showing 1 - 10 of 14
Results Per Page
Sort Options
Item AIMS Philanthropy Project: Studying AI, Machine Learning & Data Science Technology for Good(Indiana University Lilly Family School of Philanthropy and Indiana University School of Informatics and Computing, IUPUI, Indianapolis, IN., 2021-02-07) Herzog, Patricia Snell; Naik, Harshal R.; Khan, Haseeb A.This project investigates philanthropic activities related to Artificial Intelligence, Machine Learning, and Data Science technology (AIMS). Advances in AIMS technology are impacting the field of philanthropy in substantial ways. This report focuses on methods employed in analyzing and visualizing five data sources: Open Philanthropy grants database, Rockefeller Foundation grants database, Chronicle of Philanthropy article database, GuideStar Nonprofit Database, and Google AI for Social Good grant awardees. The goal was to develop an accessible website platform that engaged human-centered UX user experience design techniques to present information about AIMS Philanthropy (https://www.aims-phil.org/). Each dataset was analyzed for a set of general questions that could be answered visually. The visuals aim to provide answers to these two primary questions: (1) How much funding was invested in AIMS? and (2) What focus areas, applications, discovery, or other purposes was AIMS-funded directed toward? Cumulatively, this project identified 325 unique organizations with a total of $2.6 billion in funding for AIMS philanthropy.Item Can virtual reality be a ‘killer app’ for journalists to tell great stories?(Indianapolis Business Journal, 2015-05-30) Faklaris, CoriThe author discusses the application of virtual reality in mass media industry and notes its use in storytelling technique for journalism. Written for IBJ's first-ever Innovation issue. A distillation of research done as part of studies in IUPUI's Media Arts and Science master's degree program.Item Characteristics and Outcomes of Critically Ill Children With Multisystem Inflammatory Syndrome(Wolters Kluwer, 2022-11) Snooks, Kellie; Scanlon, Matthew C.; Remy, Kenneth E.; Shein, Steven L.; Klein , Margaret J.; Zee-Cheng, Janine; Rogerson, Colin M.; Rotta, Alexandre T.; Lin, Anna; McCluskey, Casey K.; Carroll , Christopher L.; Pediatrics, School of MedicineObjectives: To characterize the prevalence of pediatric critical illness from multisystem inflammatory syndrome in children (MIS-C) and to assess the influence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) strain on outcomes. Design: Retrospective cohort study. Setting: Database evaluation using the Virtual Pediatric Systems Database. Patients: All children with MIS-C admitted to the PICU in 115 contributing hospitals between January 1, 2020, and June 30, 2021. Measurements and Main Results: Of the 145,580 children admitted to the PICU during the study period, 1,338 children (0.9%) were admitted with MIS-C with the largest numbers of children admitted in quarter 1 (Q1) of 2021 (n = 626). The original SARS-CoV-2 viral strain and the D614G Strain were the predominant strains through 2020, with Alpha B.1.1.7 predominating in Q1 and quarter 2 (Q2) of 2021. Overall, the median PICU length of stay (LOS) was 2.7 days (25–75% interquartile range [IQR], 1.6–4.7 d) with a median hospital LOS of 6.6 days (25–75% IQR, 4.7–9.3 d); 15.2% received mechanical ventilation with a median duration of mechanical ventilation of 3.1 days (25–75% IQR, 1.9–5.8 d), and there were 11 hospital deaths. During the study period, there was a significant decrease in the median PICU and hospital LOS and a decrease in the frequency of mechanical ventilation, with the most significant decrease occurring between quarter 3 and quarter 4 (Q4) of 2020. Children admitted to a PICU from the general care floor or from another ICU/step-down unit had longer PICU LOS than those admitted directly from an emergency department. Conclusions: Overall mortality from MIS-C was low, but the disease burden was high. There was a peak in MIS-C cases during Q1 of 2021, following a shift in viral strains in Q1 of 2021. However, an improvement in MIS-C outcomes starting in Q4 of 2020 suggests that viral strain was not the driving factor for outcomes in this population.Item Community Health Information Resource Guide: Volume 1 - Data(The Polis Center at IUPUI, 2011-06) Comer, Karen F; Derr, Michelle; Seyffarth, Chris; Thomaskutty, Champ; Kandris, Sharon; Ritchey, MatthewThis resource guide contains useful information for those who would like to use data to assess the health status of an Indiana community. Targeted users include local organizations such as county health departments and community health coalitions. Being able to access and use relevant data and information resources is a common hurdle for those interested in assessing and advancing community health. As a result of this need and at the request of the Community Advisory Council of the Community Health Engagement Program, we developed this resource guide to assist individuals, organizations, and coalitions in Indiana in identifying appropriate resources that guide their community health research and evaluation activities. The term “data” is used in this volume in reference to both data and information sources. While data consist of raw facts and figures, information is formed by analyzing the data and applying knowledge to it so that the findings are more meaningful and valuable to the community. The benefit of using data is that you can often manipulate it for your specific purposes. The benefit of using information sources is that the work of generating meaning from the data might already have been done, while a potential downside is that the available sources might not answer your specific questions. There are diverse sources of data that can be used as a basis for community health evaluation and decision making. Those looking to use data must consider multiple factors before determining the appropriate data to seek and use.Item High flow nasal cannula use is associated with increased hospital length of stay for pediatric asthma(Wiley, 2023-11) Rogerson, Colin; Owora, Arthur; He, Tian; Carroll, Aaron; Schleyer, Titus; AbuSultaneh, Samer; Tu, Wanzhu; Mendonca, Eneida; Medicine, School of MedicineBackground High flow nasal cannula (HFNC) is a respiratory device increasingly used to treat asthma. Recent mechanistic studies have shown that nebulized medications may have reduced delivery with HFNC, which may impair asthma treatment. This study evaluated the association between HFNC use for pediatric asthma and hospital length of stay (LOS). Methods This was a retrospective matched cohort study. Cases included patients aged 2–18 years hospitalized between January 2010 and December 2021 with asthma and received HFNC treatment. Controls were selected using logistic regression propensity score matching based on demographics, vital signs, medications, imaging, and social and environmental determinants of health. The primary outcome was hospital LOS. Results A total of 23,659 encounters met eligibility criteria, and of these 1766 cases included HFNC treatment with a suitable matched control. Cases were well-matched in demographics, social and environmental determinants of health, and clinical characteristics including use of adjunctive asthma therapies. The median hospital LOS for study cases was significantly higher at 87 h (interquartile range [IQR]: 61–145) compared to 66 h (IQR: 43–105) in the matched controls (p < 0.01). There was no significant difference in the rate of intubation and mechanical ventilation (8.9% vs. 7.6%, p = .18); however, the use of NIV was significantly higher in the cases than the control group (21.3% vs. 6.7%, p < .01). Conclusion In this study of children hospitalized for asthma, HFNC use was associated with increased hospital LOS compared to matched controls. Further research using more granular data and additional relevant variables is needed to validate these findings.Item Information technologies that facilitate care coordination: provider and patient perspectives(Oxford, 2018-05) Dixon, Brian E.; Embi, Peter J.; Haggstrom, David A.; Epidemiology, School of Public HealthHealth information technology is a core infrastructure for the chronic care model, integrated care, and other organized care delivery models. From the provider perspective, health information exchange (HIE) helps aggregate and share information about a patient or population from several sources. HIE technologies include direct messages, transfer of care, and event notification services. From the patient perspective, personal health records, secure messaging, text messages, and other mHealth applications may coordinate patients and providers. Patient-reported outcomes and social media technologies enable patients to share health information with many stakeholders, including providers, caregivers, and other patients. An information architecture that integrates personal health record and mHealth applications, with HIEs that combine the electronic health records of multiple healthcare systems will create a rich, dynamic ecosystem for patient collaboration.Item Integrating Data Science into T32 Training Programs at IUPUI(2019-06-30) Dixon, Brian E.; Stumpff, Julia C.; Kasthurirathne, Suranga N.; Lourens, Spencer; Janga, Sarath; Liu, Yunlong; Huang, KunData science is critically important to the biomedical research enterprise. Many research efforts currently and in the future will employ advanced computational techniques to analyze extremely large datasets in order to discover insights relevant to human health. Therefore the next generation of biomedical scientists requires knowledge of and proficiency in data science. With support from the U.S. National Library of Medicine, a team of faculty from Indiana University-Purdue University Indianapolis (IUPUI) facilitated curricula enhancement for National Institutes of Health (NIH) T32 research training programs with respect to data science. In collaboration with the existing NIH T32 Program Directors at IUPUI and the IU School of Medicine, the interdisciplinary team of faculty drawn from multiple schools and departments examined the existing landscape of data science offerings on campus in parallel with an assessment of the competencies that future biomedical and clinician scientists will require to be comfortable using data science methods to advance their research. The IUPUI campus possesses a rich tapestry of data science education programs across multiple schools and departments. Furthermore, the campus is home to more than a dozen world-class T32 programs funded by the NIH to train biomedical and clinician scientists. However, existing training programs do not currently emphasize data science or provide specific curriculum designed to ensure T32 graduates possess basic competencies in data science. To position the campus for the future, robust T32 programs need to connect with the rapidly growing data science programs. This report summarizes the rationale for the importance of connection and the competencies that future biomedical and clinical scientists will require to be successful. The report further describes the curriculum mapping efforts to link competencies with available degree programs, courses and workshops on campus. The report further recommends next steps for campus leadership, including but not limited to T32 Program Directors, the Office of the Vice Chancellor for Research, the Executive Associate Dean for Research Affairs at the IU School of Medicine, and the President and CEO of the Regenstrief Institute. Together we can strengthen the IUPUI campus and help ensure its T32 graduates are successful in their research careers.Item LabVIEW™ Database Interfacing For Robotic Control(2006-07-26T14:13:05Z) Gebregziabher, Netsanet; Perry, Douglas G.The Zymark™ System is a lab automation workstation that uses the Caliper Life Sciences (Hopkinton, MA) Zymate XP robot. At Indiana University-Purdue University Indianapolis, a Zymate is used in a course, INFO I510 Data Acquisition and Laboratory Automation, to demonstrate the fundamentals of laboratory robotics. This robot has been re-engineered to function with National Instruments™ graphical software program LabVIEW™. LabVIEW is an excellent tool for robotic control. Based on changing conditions, it is able to dynamically use data from any source to modify the operating parameters of a robot. For dynamically changing information, storage of that information must be readily accessible. For example, there is a need to continuously store and update the calibration data of the robot, populate the setting of each axis and positioning inside the workplace, and also store robot positioning information. This can be achieved by using a database which allows for robotic control data to be easily searched and accessed. To address this need, an interface was developed which would allow full, dynamic communication between any LabVIEW program (called “virtual instruments,” or VIs) and the database. This has been accomplished by developing a set of subVIs that can be dropped into the calling robotic control VIs. With these subVIs, a user has the ability to create table and column information, delete a table, retrieve table information by clicking a particular table name on the user interface, or query using any SQL-specific combination of columns or tables within the database. For robot functionality, subVIs were created to store and retrieve data such as calibration data points and regression calculations.Item Legal and Ethical Implications of Mobile Live-Streaming Video Apps(ACM, 2016-09) Faklaris, Cori; Cafaro, Francesco; Hook, Sara Anne; Blevins, Asa; O'Haver, Matt; Singhal, Neha; Department of Human-Centered Computing, School of Informatics and ComputingThe introduction of mobile apps such as Meerkat, Periscope, and Facebook Live has sparked enthusiasm for live-streaming video. This study explores the legal and ethical implications of mobile live-streaming video apps through a review of public-policy considerations and the computing literature as well as analyses of a mix of quantitative and qualitative user data. We identify lines of research inquiry for five policy challenges and two areas of the literature in which the impact of these apps is so far unaddressed. The detailed data gathered from these inquiries will significantly contribute to the design and development of tools, signals or affordances to address the concerns that our study identifies. We hope our work will help shape the fields of ubiquitous computing and collaborative and social computing, jurisprudence, public policy and applied ethics in the future.Item Machine learning models to predict and benchmark PICU length of stay with application to children with critical bronchiolitis(Wiley, 2023-06) Rogerson, Colin M.; Heneghan, Julia A.; Kohne, Joseph G.; Goodman, Denise M.; Slain, Katherine N.; Cecil, Cara A.; Kane, Jason M.; Hall, Matt; Pediatrics, School of MedicineObjective To create models for prediction and benchmarking of pediatric intensive care unit (PICU) length of stay (LOS) for patients with critical bronchiolitis. Hypothesis We hypothesize that machine learning models applied to an administrative database will be able to accurately predict and benchmark the PICU LOS for critical bronchiolitis. Design Retrospective cohort study. Patients All patients less than 24-month-old admitted to the PICU with a diagnosis of bronchiolitis in the Pediatric Health Information Systems (PHIS) Database from 2016 to 2019. Methodology Two random forest models were developed to predict the PICU LOS. Model 1 was developed for benchmarking using all data available in the PHIS database for the hospitalization. Model 2 was developed for prediction using only data available on hospital admission. Models were evaluated using R2 values, mean standard error (MSE), and the observed to expected ratio (O/E), which is the total observed LOS divided by the total predicted LOS from the model. Results The models were trained on 13,838 patients admitted from 2016 to 2018 and validated on 5254 patients admitted in 2019. While Model 1 had superior R2 (0.51 vs. 0.10) and (MSE) (0.21 vs. 0.37) values compared to Model 2, the O/E ratios were similar (1.18 vs. 1.20). Institutional median O/E (LOS) ratio was 1.01 (IQR 0.90–1.09) with wide variability present between institutions. Conclusions Machine learning models developed using an administrative database were able to predict and benchmark the length of PICU stay for patients with critical bronchiolitis.