OAIC Data Science and Applied Technology Core

Todd Manini

Todd Manini Ph.D.

Professor; Chief, Division Of EDGE
Phone: (352) 273-5914

Sanjay Ranka, Ph.D.

Phone: (352) 514-4213
Email: ranka@cise.ufl.edu

Data science and applied technology core presentation

Understanding Research Statistics

The UF Older American’s Independence Center’s Data Science and Applied Technology (DSAT) Core is a recent addition to the University of Florida (UF) Older Americans Independence Center (OAIC), created 2 years ago as an interactive data ecosystem to meet the new demands for data-driven approaches and health technologies (e.g. mobile health). The overarching goals are to harvest, warehouse, repurpose, analyze, and reduce complex data while implementing new technology in an applied manner to preserve mobility and prevent disability in older adults.  These goals are perfectly lined with large NIH initiatives such as the Big Data to Knowledge (BD2K) and The Precision Medicine Initiative Cohort Program. The core has specific expertise in analyzing and modeling multimodal (e.g. sensor data, images, and medical records) as well as “unstructured data” (e.g. facial expressions from video) that is atypical of most clinical research, but is rapidly expected to become an important research tool.3 Unstructured data require a significant amount of data reorganization to ensure feature identification and extraction, model generation, validation, and visualization to obtain medically relevant relations. DSAT also leverages new technologies by developing wearable and mobile applications (“apps”) that assess and characterize mobility, while simultaneously allowing researchers to interact with participants, e.g., in a closed-loop system.

Technology and big data are becoming essential elements for the future of large-scale assessment of mobility in research and clinical settings. DSAT provides a central hub of expertise in computer engineering, mHealth, data science, applied technology, epidemiology, informatics, and content expertise to achieve the following:

  • Advance interactive monitoring using mobile devices for deriving and assessing mobility phenotypes
    • Develop new software and mobile technology to monitor and evaluate mobility
    • Validate new technology for monitoring mobility and interacting with participants/patients
    • Develop open-source software frameworks for collecting, monitoring, and interacting with large numbers of participants and patients
  • Warehouse and integrate multimodal data
    • Harvest electronic health record (EHR) data from the Common Data Model used in OneFlorida/PCORnet for secondary data analyses evaluating geriatric medical programs
    • Design and implement a mobility-impairment phenotype in OneFlorida—a statewide clinical data network—for querying, identifying, and recruiting research participants
    • Develop a cloud-based computing and analytics environment for supporting mobile technology
  • Conduct machine learning and pattern discovery analyses
    • Repurpose high-resolution biomedical data and physiological signals to derive mobility phenotypes
    • Apply innovative machine learning methods (e.g., deep learning, elastic networks) to a variety of big data sources (genomics, sensor output, electronic health records (EHR))
    • Identify hidden patterns in high-resolution time-series data (e.g., wearable sensors)
    • Extract important features as possible from the data to build high-performing prediction models
  • Support OAIC cores, educate OAIC Junior Scholars and other junior investigators and provide outreach
    • Provide access and background knowledge of existing data for secondary data analyses
    • Conduct secondary data analyses on epidemiological and public data with the Biostatistics Core (RC3) to support grant applications (e.g., preliminary data, eligibility-criteria refinement)
    • Build common data elements in OneFlorida (a statewide EHR data repository) to identify and recruit mobility-impaired older adults into research studies (jointly with the Clinical Research Core)

DSAT core investigators collaborate with:

  1. All OAIC investigators, to ensure they can harvest, warehouse, and use big data and use new technology optimally to meet their own research goals;
  2. The Clinical Research Core, to help recruit participants through clinical data networks and help design “in clinic” mobility assessments that integrate with patient data repositories;
  3. The Metabolism and Biomarkers Core, to use machine-learning techniques to discover patterns in genomic data and make available biospecimens via the OneFlorida Data Trust;
  4. The RC3, to prepare and warehouse big data for statistical analysis; and
  5. Junior Scholars in the Research Education Core, to conduct secondary data analyses, use new mobility technology, and customize interactive software for their research.


  1. A.Davoudi, D. B. Corbett, T. Ozrazgat-Baslanti, A. Bihorac, S. C. Brakenridge, T. M. Manini, P. Rashidi, ‘Activity and Circadian Rhythm of Sepsis Patients in the Intensive Care Unit’, in IEEE Biomedical and Health Informatics (BHI), Las Vegas, NV, 2018 (accepted 12/15/17)
  2. Nair S, Kheirkhahan M, Davoudi A, Rashidi P, Wanigatunga AA, Corbett DB, Manini TM and Ranka S, 2016, September. Roamm: A software infrastructure for real-time monitoring of personal health. In Proceedings of 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom), pp. 1-6. IEEE. DOI: 10.1109/HealthCom.2016.7749479
  3. Kheirkhahan M, Chen Z, Corbett DB, Wanigatunga AA, Manini TM and Ranka S. 2017, February. Adaptive walk detection algorithm using activity counts. In Proceedings of 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), pp. 161-164. IEEE. DOI: 10.1109/BHI.2017.7897230
  4. Davoudi A, Kheirkhahan M, Nair S, Ranka S, Manini TM, Rashidi P. Validation of Accelerometer Data from Samsung Gear S Smartwatch. 38th International Conference of the IEEE Engineering in Medicine and Biology Society; 2016; Orlando, FL: IEEE.
  5. Kheirkhahan M, Wanigatunga AA, Corbett DC, Ranka S, Manini TM. Detecting Sedentary Behavior from Wrist Accelerometer Data. 2016 IEEE 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.
  6. Matin Kheirkhahan, Sanjay Nair, Sanjay Ranka, Todd Manini, and Parisa Rashidi. Validation of Accelerometer Data from Samsung Gear S Anis Davoodi. Proceedings of the IEEE 38th Annual International Conference in Medicine and Biology Society (EMBC’16), Orlando, USA, 2016.
  7. Wanigatunga AA, Ambrosius WT, Rejeski WJ, Gill TM, Glynn NW, Tudor-Locke C, Manini TM. Association Between Structured Physical Activity and Sedentary Time in Older Adults. Journal of the American Medical Association (JAMA). 2017 Jul 18;318(3):297-299. PubMed PMID: 28719683.
  8. Corbett DB, Valiani V, Knaggs JD, Manini TM. Evaluating Walking Intensity with Hip-Worn Accelerometers in Elders. Med Sci Sports Exerc. 2016 Nov;48(11):2216-2221. PubMed Central PMCID: PMC5069122.
  9. Kheirkhahan M, Tudor-Locke C, Axtell R, Buman MP, Fielding RA, Glynn NW, Guralnik JM, King AC, White DK, Miller ME, Siddique J, Brubaker P, Rejeski WJ, Ranshous S, Pahor M, Ranka S, Manini TM. Actigraphy features for predicting mobility disability in older adults. Physiol Meas. Physiol Meas. 2016 Sep 21;37(10):1813-1833. PubMed Central PMCID: PMC5360536.
  10. Rejeski WJ, Marsh AP, Brubaker PH, Buman M, Fielding RA, Hire D, Manini TM, Rego A, Miller ME; LIFE Study Investigators. Analysis and Interpretation of Accelerometry Data in Older Adults: The LIFE Study. 2016 Apr;71(4):521-8. PubMed Central PMCID: PMC5175451.
  11. Valiani V, Corbett DB, Knaggs JD, Manini TM. Metabolic Rate and Perceived Exertion of Walking in Older Adults with Idiopathic Chronic Fatigue. J Gerontol A Biol Sci Med Sci. 016 Nov; 71(11): 1444-1450.
  12. Tighe PJ, Nickerson P, Fillingim RB, Rashidi P. Characterizations of Temporal Postoperative Pain Signatures With Symbolic Aggregate Approximations. Clin J Pain. 2017 Jan;33(1):1-11. PubMed PMID: 27153359; PubMed Central PMCID: PMC5097898.
  13. Valiani V, Sourdet S, Schoeller DA, Mackey DC, Bauer DC, Glynn NW, Yamada Y, Harris TB, Manini TM; Health, Aging and Body Composition Study. Surveying predictors of late-life longitudinal change in daily activity energy expenditure. PLoS One. 2017 Oct 17;12(10):e0186289. PubMed PMID: 29040301; PubMed Central PMCID: PMC5645098.
  14. Valiani V, Chen Z, Lipori G, Pahor M, Sabbá C, Manini TM. Prognostic Value of Braden Activity Subscale for Mobility Status in Hospitalized Older Adults. J Hosp Med. 2017 Jun;12(6):396-401. PubMed PMID: 28574527; PubMed Central PMCID: PMC5551676.
  15. Nickerson P, Baharloo R, Wanigatunga AA, Manini TD, Tighe PJ, Rashidi P. Transition Icons for Time Series Visualization and Exploratory Analysis. IEEE J Biomed Health Inform. 2017 May 16. doi: 10.1109/JBHI.2017.2704608. [Epub ahead of print] PubMed PMID: 28534797.
  16. Wanigatunga AA, Nickerson PV, Manini TM, Rashidi P. Using symbolic aggregate approximation (SAX) to visualize activity transitions among older adults. Physiol Meas. 2016 Nov;37(11):1981-1992. Epub 2016 Oct 18. PubMed PMID: 27754973; PubMed Central PMCID: PMC5099975.
  17. Wanigatunga AA, Tudor-Locke C, Axtell RS, Glynn NW, King AC, McDermott MM, Fielding RA, Lu X, Pahor M, Manini TM. Effects of a Long-Term Physical Activity Program on Activity Patterns in Older Adults. Med Sci Sports Exerc. 2017 Nov;49(11):2167-2175. PubMed PMID: 29045323; PubMed Central PMCID: PMC5653284.