Wiki-Health: From Quantified Self to Self-Understanding

Author(s):

Abstract:

Today, healthcare providers are experiencing explosive growth in data. Although the dramatic increase in the use of medical imagingtechnologies has been a major contributor to healthcare data growth in the past decade, more recently the rising adoption of sensing devices, enabling people to collect health-related data independently at any time or place is leading to a torrent of sensor data. The scale and richness of the sensor data currently being collected and analysed is rapidly growing. The key challenges that we will be facing are how to effectively manage and make use of this abundance of easily generated and diverse health data.

This paper explores the potential for sensors use in healthcare data acquisition and presents the next evolution in the on-going development of Wiki-Health, a big data service platform, designed to address the larger problem of explosive growth in healthcare information by providing a unified solution for collecting, storing, tagging, retrieving, searching and analysing personal health sensor data. Additionally, the platform is designed to allow users to reuse and remix data, along with analysis results and analysis models, to make health-related knowledge discovery more available to individual users–including health professionals, patients or even individuals who desire to maintain an optimum level of personal health–on a massive scale.

To tackle the challenge of efficiently managing the high volume and diversity of big data, Wiki-Health introduces a hybrid data storage model capable of storing structured, semi-structured and unstructured sensor data and sensor metadata separately. The design of such a hybrid model allows Wiki-Health to potentially handle heterogeneous formats of sensor data. In addition to its data management capabilities, we envision the potential for Wiki-Health as a system that also enables health sensor data monitoring and analysis, not only as a method of tracking existing health conditions but also as a means of encouraging a more pro-active approach to healthcare through early detection. To tackle the scalability and performance challenges of real-time analysis, the Analysis Tasks Allocation Scheme proposed in the research aids the management of data analysis tasks on a large scale and utilises the elastic nature of cloud infrastructure by considering the aspects of performance and cost.

To evaluate the proposed Wiki-Health approach, we have developed an ECG-based health monitoring service on top of the Wiki-Health platform. The positive performance of the approach is supported by the results obtained in our experimental trials and shows significant potential for real-world applications.

Documentation:

https://doi.org/10.1016/j.future.2015.08.008

References:

[1] B. Feldman, E.M. Martin, T. Skotnes, Big Data in healthcare hype and hope, 2012.Google Scholar

[2]L. Yang, G. Li, G. Yike, Enabling health monitoring as a service in the cloud, in: 2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing, UCC, 2014, pp. 127–136.Google Scholar

[3]Fitbit. Available: http://www.fitbit.com  (accessed July 2015).Google Scholar

[4]Zephyr. Available: http://www.zephyranywhere.com  (accessed July 2015).Google Scholar

[5]NIKE+ FUELBAND. Available: http://www.nike.com  (accessed July 2015).Google Scholar

[6]Withings. Available: www.withings.com  (accessed July 2015).Google Scholar

[7]AliveCor heart monitor. Available: http://www.alivecor.com  (accessed July 2015).Google Scholar

[8]C.A. Volgman, S. Wang, D. Mehta, N. Nazir, S. Alexander, K. Krishnan, et al.O016 AliveCor Heart Monitoring: Is it a practical alternative to a traditional ECG monitor for a developing nation?Global Heart, 9 (2014), pp. e4-e5ArticleDownload PDFCrossRefView Record in ScopusGoogle Scholar

[9]D.J. Abadi, D. Carney, U. Çetintemel, M. Cherniack, C. Convey, S. Lee, et al.Aurora: a new model and architecture for data stream managementVLDB J.—Int. J. Very Large Data Bases, 12 (2003), pp. 120-139CrossRefView Record in ScopusGoogle Scholar

[10]Y. Yao, J. GehrkeThe cougar approach to in-network query processing in sensor networksACM SIGMOD Rec., 31 (2002), pp. 9-18CrossRefView Record in ScopusGoogle Scholar

[11]M. Yuriyama, T. Kushida, Sensor-cloud infrastructure-physical sensor management with virtualized sensors on cloud computing, in: 2010 13th International Conference on Network-Based Information Systems, NBiS, 2010, pp. 1–8.Google Scholar

[12]ThingSpeak. Available: http://thingspeak.com  (accessed 2015).Google Scholar

[13]Xively. Available: https://xively.com  (accessed July 2015).Google Scholar

[14]HealthVault. Available: http://www.healthvault.com  (accessed July 2015).Google Scholar

[15]WebMD. Available: http://www.webmd.com  (accessed July 2015).Google Scholar

[16]S.R. Madden, M.J. Franklin, J.M. Hellerstein, W. HongTinyDB: an acquisitional query processing system for sensor networksACM Trans. Database Syst. (TODS), 30 (2005), pp. 122-173CrossRefView Record in ScopusGoogle Scholar

[17]R.N. Murty, G. Mainland, I. Rose, A.R. Chowdhury, A. Gosain, J. Bers, et al. Citysense: An urban-scale wireless sensor network and testbed, in: 2008 IEEE Conference on Technologies for Homeland Security, 2008, pp. 583–588.Google Scholar

[18]G. Wolf, A. Carmichael, K. Kelly, The quantified self, TED, 2010. http://www.ted.com/talks/gary_wolf_the_quantified_self.html.Google Scholar

[19]M. SwanThe quantified self: Fundamental disruption in big data science and biological discoveryBig Data, 1 (2013), pp. 85-99CrossRefView Record in ScopusGoogle Scholar

[20]R. Luengo-Fernandez, J. Leal, A. Gray, S. Petersen, M. RaynerCost of cardiovascular diseases in the United KingdomHeart, 92 (2006), pp. 1384-1389CrossRefView Record in ScopusGoogle Scholar

[21]A. Pantelopoulos, N.G. BourbakisA survey on wearable sensor-based systems for health monitoring and prognosisIEEE Trans. Syst. Man Cybern. Part C Appl. Rev., 40 (2010), pp. 1-12CrossRefView Record in ScopusGoogle Scholar

[22]J.J. Oresko, Z. Jin, J. Cheng, S. Huang, Y. Sun, H. Duschl, et al.A wearable smartphone-based platform for real-time cardiovascular disease detection via electrocardiogram processingIEEE Trans. Inf. Technol. Biomed., 14 (2010), pp. 734-740CrossRefView Record in ScopusGoogle Scholar

[23]E. Nemati, M.J. Deen, T. MondalA wireless wearable ECG sensor for long-term applicationsIEEE Commun. Mag., 50 (2012), pp. 36-43View Record in ScopusGoogle Scholar

[24]Propeller Health. Available: http://propellerhealth.com/  (accessed July 2015).Google Scholar

[25]E.J. TopolThe Creative Destruction of Medicine: How the Digital Revolution will Create Better Health CareBasic Books (2012)Google Scholar

[26]M. Bsoul, H. Minn, L. TamilApnea MedAssist: real-time sleep apnea monitor using single-lead ECGIEEE Trans. Inf. Technol. Biomed., 15 (2011), pp. 416-427CrossRefView Record in ScopusGoogle Scholar

[27]T.Q. Le, C. Cheng, A. Sangasoongsong, S.T. Bukkapatnam, Prediction of sleep apnea episodes from a wireless wearable multisensor suite, in: Point-of-Care Healthcare Technologies, PHT, 2013 IEEE, 2013, pp. 152–155.Google Scholar

[28]S. AdibiWireless-based sleep technology for monitoring sleep apneaAdv. Sci. Eng. Med., 6 (2014), pp. 111-113CrossRefView Record in ScopusGoogle Scholar

[29]I.S. Mackenzie, S.V. Morant, G.A. Bloomfield, T.M. MacDonald, J.I.O’RiordanChanging face of multiple sclerosis in the United Kingdom 1990–2010. An incidence and prevalence studyJ. Neurol. Neurosurg. Psychiatry, 84 (2013)p. e2Google Scholar

[30]D. Gijbels, U. Dalgas, A. Romberg, V. de Groot, F. Bethoux, C. Vaney, et al.Which walking capacity tests to use in multiple sclerosis? A multicentre study providing the basis for a core setMult. Scler. J., 18 (2012), pp. 364-371CrossRefView Record in ScopusGoogle Scholar

[31]B.H. Dobkin, A. DorschThe promise of mHealth daily activity monitoring and outcome assessments by wearable sensorsNeurorehabil. Neural Repair, 25 (2011), pp. 788-798CrossRefView Record in ScopusGoogle Scholar

[32]L. Shammas, T. Zentek, B. von Haaren, S. Schlesinger, S. Hey, A. RashidHome-based system for physical activity monitoring in patients with multiple sclerosis (Pilot study)Biomed. Eng. Online, 13 (2014), p. 10CrossRefView Record in ScopusGoogle Scholar

[33]T. Square, B. Lane, Enhanced Service-Facilitating timely diagnosis and support for people with dementia, 2013. Available: http://www.hscic.gov.uk/article/3489/IAG-documents  (accessed July 2015).Google Scholar

[34]Google Glass. Available: http://www.google.com/glass  (accessed January 2014).Google Scholar[35]Narrative Clip. Available: http://getnarrative.com/  (accessed July 2015).Google Scholar

[36]Autographer Camera. Available: http://www.autographer.com/  (accessed July 2015).Google Scholar

[37]B. Kikhia, J. Hallberg, K. Synnes, Z. Sani, Context-aware life-logging for persons with mild dementia, in: Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE, 2009, pp. 6183–6186.Google Scholar

[38]P. Wang, A.F. SmeatonUsing visual lifelogs to automatically characterize everyday activitiesInform. Sci., 230 (2013), pp. 147-1615/1/ArticleDownload PDFView Record in ScopusGoogle Scholar

[39]J. Hallberg, B. Kikhia, J. Bengtsson, S. Sävenstedt, K. Synnes, Reminiscence processes using life-log entities for persons with mild dementia, in: Proceedings of the First International Workshop on Reminiscence Systems, 2009, pp. 16–21.Google Scholar

[40]R. Cracknell, The ageing population, House of Commons Library Research, 2010.Google Scholar

[41]P. Scuffham, S. Chaplin, R. LegoodIncidence and costs of unintentional falls in older people in the United KingdomJ. Epidemiol. Community Health, 57 (2003), pp. 740-744View Record in ScopusGoogle Scholar

[42]S. Borland, More than 500,000 elderly sent to A&E every year because of failures in care: Needless admissions among older people up 40% in five years, ed., 2013.Google Scholar

[43]A. Arcelus, M.H. Jones, R. Goubran, F. Knoefel, Integration of smart home technologies in a health monitoring system for the elderly, in: 21st International Conference on Advanced Information Networking and Applications Workshops, 2007, AINAW’07. 2007, pp. 820–825.Google Scholar

[44]F. Portet, M. Vacher, C. Golanski, C. Roux, B. MeillonDesign and evaluation of a smart home voice interface for the elderly: acceptability and objection aspectsPers. Ubiquitous Comput., 17 (2013), pp. 127-144CrossRefView Record in ScopusGoogle Scholar

[45]J.-V. Lee, Y.-D. Chuah, K.T. ChiengSmart elderly home monitoring system with an android phoneInt. J. Smart Home, 7 (2013), pp. 17-32CrossRefView Record in ScopusGoogle Scholar

[46]Y. Charlon, W. Bourennane, F. Bettahar, E. CampoActivity monitoring system for elderly in a context of smart homeIRBM, 34 (2013), pp. 60-63ArticleDownload PDFView Record in ScopusGoogle Scholar

[47]N. Ogawa, Y. Imai, H. Morita, R. NagaiGenome-wide association study of coronary artery diseaseInt. J. Hypertens., 2010 (2010)Google Scholar

[48]A. Helgadottir, G. Thorleifsson, A. Manolescu, S. Gretarsdottir, T. Blondal, A. Jonasdottir, et al.A common variant on chromosome 9p21 affects the risk of myocardial infarctionScience, 316 (2007), pp. 1491-1493CrossRefView Record in ScopusGoogle Scholar

[49]R. McPherson, A. Pertsemlidis, N. Kavaslar, A. Stewart, R. Roberts, D.R.Cox, et al.A common allele on chromosome 9 associated with coronary heart diseaseScience, 316 (2007), pp. 1488-1491CrossRefView Record in ScopusGoogle Scholar

[50]D.F. Gudbjartsson, U.S. Bjornsdottir, E. Halapi, A. Helgadottir, P. Sulem, G.M. Jonsdottir, et al.Sequence variants affecting eosinophil numbers associate with asthma and myocardial infarctionNature Genet., 41 (2009), pp. 342-347CrossRefView Record in ScopusGoogle Scholar

[51]J. Erdmann, A. Großhennig, P.S. Braund, I.R. König, C. Hengstenberg, A.S.Hall, et al.New susceptibility locus for coronary artery disease on chromosome 3q22. 3Nature Genet., 41 (2009), pp. 280-282CrossRefView Record in ScopusGoogle Scholar

[52]A.E. Guttmacher, A.L. McGuire, B. Ponder, K. StefánssonPersonalized genomic information: preparing for the future of genetic medicineNature Rev. Genet., 11 (2010), pp. 161-165CrossRefView Record in ScopusGoogle Scholar

[53]E. Stern, A. Vacic, N.K. Rajan, J.M. Criscione, J. Park, B.R. Ilic, et al.Label-free biomarker detection from whole bloodNature Nanotechnol., 5 (2009), pp. 138-142View Record in ScopusGoogle Scholar

[54]B. Godin, J.H. Sakamoto, R.E. Serda, A. Grattoni, A. Bouamrani, M. FerrariEmerging applications of nanomedicine for the diagnosis and treatment of cardiovascular diseasesTrends Pharmacol. Sci., 31 (2010), pp. 199-205ArticleDownload PDFView Record in ScopusGoogle Scholar

[55]Y. Li, L. Guo, Y. Guo, CACSS: Towards a generic cloud storage service, in: Presented at the CLOSER, 2012.Google Scholar

[56]Y. Li, L. Guo, Y. GuoAn efficient and performance-aware big data storage systemCloud Computing and Services Science, Springer (2013), pp. 102-116CrossRefView Record in ScopusGoogle Scholar

[57]Y. Li, L. Guo, A. Supratak, Y. Guo, Enabling performance as a service for a cloud storage system, in: Presented at the 7th IEEE International Conference on Cloud Computing, Alaska, USA, 2014.Google Scholar

[58]N. LeavittWill NoSQL databases live up to their promise?Computer, 43 (2010), pp. 12-14CrossRefView Record in ScopusGoogle Scholar[59]I.T. Varley, A. Aziz, C.-s.A. Aziz, D. Miranker, No relation: The mixed blessings of non-relational databases, 2009.Google Scholar[60]M. StonebrakerSQL databases v. NoSQL databasesCommun. ACM, 53 (2010), pp. 10-11CrossRefView Record in ScopusGoogle Scholar[61]R. CattellScalable SQL and NoSQL data storesACM SIGMOD Rec., 39 (2011), pp. 12-27CrossRefView Record in ScopusGoogle Scholar[62]D. Carstoiu, A. Cernian, A. Olteanu, Hadoop Hbase-0.20.2 performance evaluation, in: 2010 4th International Conference on New Trends in Information Science and Service Science, NISS, 2010, pp. 84–87.Google Scholar

[63]A. Khetrapal, V. Ganesh, HBase and Hypertable for large scale distributed storage systems, Dept. of Computer Science, Purdue University, 2006.Google Scholar

[64]A. HBase. Available: http://hbase.apache.org  (accessed July 2015).Google Scholar

[65]I. MathWorks, MATLAB: the language of technical computing. Desktop tools and development environment, version 7, vol. 9: MathWorks, 2005.Google Scholar

[66]Octave. Available: http://www.gnu.org/software/octave/  (accessed July 2015).Google Scholar[67]R. C. Team, R: A language and environment for statistical computing, 2012.Google Scholar

[68]A. Vukotic, J. GoodwillApache Tomcat 7Springer (2011)Google Scholar

[69]Quartz Scheduler. Available: http://quartz-scheduler.org/  (accessed July 2015).Google Scholar

[70]L. Guo, Y. Guo, X. Tian, IC cloud: a design space for composable cloud computing, in: 2010 IEEE 3rd International Conference on Cloud Computing, CLOUD, 2010, pp. 394–401.Google Scholar

[71]Y.-K. Guo, L. GuoIC cloud: Enabling compositional cloudInt. J. Autom. Comput., 8 (2011), pp. 269-279CrossRefView Record in ScopusGoogle Scholar

[72]B. Schwartz, P. Zaitsev, V. TkachenkoHigh Performance MySQL: Optimization, Backups, and ReplicationO’Reilly Media, Inc. (2012)Google Scholar

[73]D. Borthakur, The hadoop distributed file system: Architecture and design, Hadoop Project Website, 2007.Google Scholar

[74]ApacheBench. Available: http://httpd.apache.org/docs/2.4/programs/ab.html  (accessed July 2015).Google Scholar

[75]A.L. Goldberger, L.A. Amaral, L. Glass, J.M. Hausdorff, P.C. Ivanov, R.G.Mark, et al.Physiobank, physiotoolkit, and physionet components of a new research resource for complex physiologic signalsCirculation, 101 (2000), pp. e215-e220CrossRefView Record in ScopusGoogle Scholar

[76]G.B. Moody, R.G. MarkThe impact of the MIT-BIH arrhythmia databaseIEEE Eng. Med. Biol. Mag., 20 (2001), pp. 45-50View Record in ScopusGoogle Scholar

[77]J. Pan, W.J. TompkinsA real-time QRS detection algorithmIEEE Trans. Biomed. Eng. (1985), pp. 230-236CrossRefView Record in ScopusGoogle Scholar

[78]D. Benitez, P. Gaydecki, A. Zaidi, A. FitzpatrickThe use of the Hilbert transform in ECG signal analysisComput. Biol. Med., 31 (2001), pp. 399-406ArticleDownload PDFView Record in ScopusGoogle Scholar

[79]P. De Chazal, M. O’Dwyer, R.B. ReillyAutomatic classification of heartbeats using ECG morphology and heartbeat interval featuresIEEE Trans. Biomed. Eng., 51 (2004), pp. 1196-1206View Record in ScopusGoogle Scholar

[80]T. Ince, S. Kiranyaz, M. GabboujA generic and robust system for automated patient-specific classification of ECG signalsIEEE Trans. Biomed. Eng., 56 (2009), pp. 1415-1426CrossRefView Record in ScopusGoogle Scholar

[81]C. Ye, M.T. Coimbra, B.V. Kumar, Arrhythmia detection and classification using morphological and dynamic features of ECG signals, in: Engineering in Medicine and Biology Society, EMBC, 2010 Annual International Conference of the IEEE, 2010, pp. 1918–1921.Google Scholar

[82]M.R. Homaeinezhad, S. Atyabi, E. Tavakkoli, H.N. Toosi, A. Ghaffari, R.EbrahimpourECG arrhythmia recognition via a neuro-SVM-KNN hybrid classifier with virtual QRS image-based geometrical featuresExpert Syst. Appl., 39 (2012), pp. 2047-2058ArticleDownload PDFView Record in ScopusGoogle Scholar

[83]Z. Dokur, T. ÖlmezECG beat classification by a novel hybrid neural networkComput. Methods Programs Biomed., 66 (2001), pp. 167-181ArticleDownload PDFView Record in ScopusGoogle Scholar

[84]M. EnginECG beat classification using neuro-fuzzy networkPattern Recognit. Lett., 25 (2004), pp. 1715-1722ArticleDownload PDFView Record in ScopusGoogle Scholar

[85]P. Li, K.L. Chan, S. Fu, S.M. KrishnanAn abnormal ecg beat detection approach for long-term monitoring of heart patients based on hybrid kernel machine ensembleMultiple Classifier Systems, Springer (2005), pp. 346-355CrossRefView Record in ScopusGoogle Scholar

[86]B. Babusiak, M. GalaDetection of Abnormalities in ECGInformation Technologies in Biomedicine, Springer (2012), pp. 161-171CrossRefView Record in ScopusGoogle Scholar

[87]M.C. Chuah, F. Fu, ECG anomaly detection via time series analysis, in: Frontiers of High Performance Computing and Networking ISPA 2007 Workshops, 2007, pp. 123–135.Google Scholar

[88]A. Lourenço, H. Silva, C. CarreirasOutlier detection in non-intrusive ECG biometric systemImage Analysis and Recognition, Springer (2013), pp. 43-52CrossRefView Record in ScopusGoogle Scholar

[89]R. KlabundeCardiovascular Physiology ConceptsLippincott Williams & Wilkins (2011)Google Scholar

[90]B. Schölkopf, J.C. Platt, J. Shawe-Taylor, A.J. Smola, R.C. WilliamsonEstimating the support of a high-dimensional distributionNeural Comput., 13 (2001), pp. 1443-1471View Record in ScopusGoogle Scholar

[91]C.-C. Chang, C.-J. LinLIBSVM: a library for support vector machinesACM Trans. Intell. Syst. Technol. (TIST), 2 (2011), p. 27CrossRefView Record in ScopusGoogle Scholar

[92]B. Scholkopf, A.J. SmolaLearning with Kernels: Support Vector Machines, Regularization, Optimization, and BeyondMIT Press (2001)Google Scholar[

93]Y. Freund, R.E. SchapireA decision–theoretic generalization of on-line learning and an application to boostingJ. Comput. System Sci., 55 (1997), pp. 119-139ArticleDownload PDFView Record in ScopusGoogle Scholar

[94]L. BreimanBagging predictorsMach. Learn., 24 (1996), pp. 123-140CrossRefView Record in ScopusGoogle Scholar

[95]J.R. Quinlan, Bagging, boosting, and C4. 5, in: AAAI/IAAI, vol. 1, 1996, pp. 725–730.Google Scholar

[96]O. Pearson, M. Busse, R. Van Deursen, C. WilesQuantification of walking mobility in neurological disordersQjm, 97 (2004), pp. 463-475View Record in ScopusGoogle Scholar

[97]R.W. Motl, B.M. SandroffObjective monitoring of physical activity behavior in multiple sclerosisPhys. Ther. Rev., 15 (2010), pp. 204-211CrossRefView Record in ScopusGoogle Scholar

[98]R. MotlPhysical activity and its measurement and determinants in multiple sclerosisMinerva Med., 99 (2008), pp. 157-165View Record in ScopusGoogle Scholar

[99]B.M. Sandroff, R.W. Motl, L.A. Pilutti, Y.C. Learmonth, I. Ensari, D.Dlugonski, et al.Accuracy of StepWatch™ and ActiGraph accelerometers for measuring steps taken among persons with multiple sclerosisPLoS One, 9 (2014), p. e93511CrossRefView Record in ScopusGoogle Scholar

[100]F. Agrafioti, D. Hatzinakos, A.K. AndersonECG pattern analysis for emotion detectionIEEE Trans. Affective Comput., 3 (2012), pp. 102-115View Record in ScopusGoogle Scholar

[101]Y. Xu, G. Liu, M. Hao, W. Wen, X. HuangAnalysis of affective ECG signals toward emotion recognitionJ. Electron. (China), 27 (2010), pp. 8-14CrossRefView Record in ScopusGoogle Scholar