Design, implementation and validation of a novel open framework for agile development of mobile health applications

Oresti Banos, Claudia Villalonga, Rafael Garcia, Alejandro Saez, Miguel Damas, Juan A Holgado-Terriza, Sungyong Lee, Hector Pomares, Ignacio Rojas, Oresti Banos, Claudia Villalonga, Rafael Garcia, Alejandro Saez, Miguel Damas, Juan A Holgado-Terriza, Sungyong Lee, Hector Pomares, Ignacio Rojas

Abstract

The delivery of healthcare services has experienced tremendous changes during the last years. Mobile health or mHealth is a key engine of advance in the forefront of this revolution. Although there exists a growing development of mobile health applications, there is a lack of tools specifically devised for their implementation. This work presents mHealthDroid, an open source Android implementation of a mHealth Framework designed to facilitate the rapid and easy development of mHealth and biomedical apps. The framework is particularly planned to leverage the potential of mobile devices such as smartphones or tablets, wearable sensors and portable biomedical systems. These devices are increasingly used for the monitoring and delivery of personal health care and wellbeing. The framework implements several functionalities to support resource and communication abstraction, biomedical data acquisition, health knowledge extraction, persistent data storage, adaptive visualization, system management and value-added services such as intelligent alerts, recommendations and guidelines. An exemplary application is also presented along this work to demonstrate the potential of mHealthDroid. This app is used to investigate on the analysis of human behavior, which is considered to be one of the most prominent areas in mHealth. An accurate activity recognition model is developed and successfully validated in both offline and online conditions.

Figures

Figure 1
Figure 1
mHealth Framework.
Figure 2
Figure 2
Examples of representation modes supported by mHealthApp. (Left) Tri- axial acceleration signals are represented at runtime. (Right) Monthly average heart rate data is depicted on the top, while continuous 2-leads ECG signals are plotted at the bottom.
Figure 3
Figure 3
Examples of video tutorials and guidelines for (left) demonstrating rehabilitation exercises and (right) encouraging healthy dietary habits.
Figure 4
Figure 4
Snapshots from the activity recognition functionality of mHealthApp: (left) the detection process has not been yet initiated by the user; (right) the application identifies the activity performed by the user, here, sitting and relaxing.
Figure 5
Figure 5
Study setup and sensor deployment.
Figure 6
Figure 6
Confusion matrix obtained from the offline evaluation of the activity recognition model. Activities are identified through the labels introduced in Table 1.
Figure 7
Figure 7
Activities detected by the proposed recognizer during online evaluation of the system and for various subjects. The actual activities are represented by the ground-truth labels. Activities are identified through the labels introduced in Table 1.
Figure 8
Figure 8
Confusion matrix obtained from the online evaluation of the activity recognition model. Activities are identified through the labels used in Table 1.

References

    1. Medscape©. Available online: (accessed on 22 May 2014)
    1. Epocrates©. Available online: (accessed on 22 May 2014)
    1. QxMD©. Available online: (accessed on 22 May 2014)
    1. MPR©. Available online: (accessed on 22 May 2014)
    1. Havelka S. Mobile resources for nursing students and nursing faculty. Journal of Electronic Resources in Medical Libraries. 2012;8(2):194–199.
    1. Taking the pulse© (us) Technical report, Manhattan Research. 2014.
    1. LoseIt©. Available online: (accessed on 22 May 2014)
    1. MyFitnessPal©. Available online: (accessed on 22 May 2014)
    1. Habib MA, Mohktar MS, Kamaruzzaman SB, Lim KS, Pin TM, Ibrahim F. Smartphone-based solutions for fall detection and prevention: challenges and open issues. Sensors. 2014;14(4):7181–7208. doi: 10.3390/s140407181.
    1. Mazilu S, Hardegger M, Zhu Z, Roggen D, Troester G, Plotnik M, Hausdorff JM. Online detection of freezing of gait with smartphones and machine learning techniques. 6th International Conference on Pervasive Computing Technologies for Healthcare. 2012. pp. 123–130.
    1. Bsoul M, Minn H, Tamil L. Apnea medassist: Real-time sleep apnea monitor using single-lead ecg. IEEE Transactions on Information Technology in Biomedicine. 2011;15(3):416–427.
    1. Oresko JJ, Jin Z, Cheng J, Huang S, Sun Y, Duschl H, Cheng AC. A wearable smartphone-based platform for real-time cardiovascular disease detection via electrocardiogram processing. IEEE Transactions on Information Technology in Biomedicine. 2010;14(3):734–740.
    1. Banos O, Villalonga C, Damas M, Gloesekoetter P, Pomares H, Rojas I. Physiodroid: Combining wearable health sensors and mobile devices for a ubiquitous, continuous, and personal monitoring. The Scientific World Journal. 2014;2014(490824):1–11.
    1. Patel S, Mancinelli C, Healey J, Moy M, Bonato P. Proceedings of 6th International Workshop on Wearable and Implantable Body Sensor Networks. Washington, DC, USA; 2009. Using wearable sensors to monitor physical activities of patients with copd: A comparison of classifier performance; pp. 234–239.
    1. Oster J, Behar J, Colloca R, Li Q, Li Q, Clifford GD. Open source Java-based ECG analysis software and Android app for Atrial Fibrillation screening. Computing in Cardiology Conference. 2013;2012:731–734.
    1. Gaggioli A, Pioggia G, Tartarisco G, Baldus G, Corda D, Cipresso P, Riva G. A mobile data collection platform for mental health research. Personal Ubiquitous Comput. 2013;17(2):241–251. doi: 10.1007/s00779-011-0465-2.
    1. Spina G, Roberts F, Weppner J, Lukowicz P, Amft O. CRNTC+: A smartphone-based sensor processing framework for prototyping personal healthcare applications. 7th International Conference on Pervasive Computing Technologies for Healthcare. 2013. pp. 252–255.
    1. Fortino G, Giannantonio R, Gravina R, Kuryloski P, Jafari R. Enabling effective programming and flexible management of efficient body sensor network applications. IEEE Transactions on Human-Machine Systems. 2013;43(1):115–133.
    1. Chen PH, Chen HM. Framework design-integrating an android open platform with multi-interface biomedical modules for physiological measurement. Journal of Convergence Information Technology. 2012;7(12):310–319. doi: 10.4156/jcit.vol7.issue12.35.
    1. Prasad A, Peterson R, Mare S, Sorber J, Paul K, Kotz D. Provenance framework for mhealth. 5th International Conference on Communication Systems and Networks. 2013. pp. 1–6.
    1. mHealthDroid. Available online: (accessed on 16 June 2014)
    1. Burns A, Greene BR, McGrath MJ, O'Shea TJ, Kuris B, Ayer SM, Stroiescu F, Cionca V. Shimmer. a wireless sensor platform for noninvasive biomedical research. IEEE Sensors Journal. 2010;10(9):1527–1534.
    1. SQLite. Available online: (accessed on 16 June 2014)
    1. JSON: JavaScript Object Notation. Available online: (accessed on 16 June 2014)
    1. MySQL. Available online: (accessed on 16 June 2014)
    1. MySQLi. Available online: (accessed on 16 June 2014)
    1. Marsan RJ. Weka-for-Android. Available online: (accessed on 16 June 2014)
    1. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH. The weka data mining software: An update. SIGKDD Explor Newsl. 2009;11(1):10–18. doi: 10.1145/1656274.1656278.
    1. Bishop CM. Pattern Recognition and Machine Learning. Vol. 1. Springer; 2006.
    1. Freund Y, Schapire RE. 13th International Conference on Machine Learning. Morgan Kaufmann, San Francisco; 1996. Experiments with a new boosting algorithm; pp. 148–156.
    1. Quinlan JR. C4.5: Programs for Machine Learning. Vol. 1. Morgan Kaufmann; 1993.
    1. Neter J, Kutner MH, Nachtsheim CJ, Wasserman W. Applied Linear Statistical Models. Vol. 4. Irwin Chicago; 1996.
    1. Lam L, Suen CY. Application of majority voting to pattern recognition: an analysis of its behavior and performance. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans. 1997;27(5):553–568. doi: 10.1109/3468.618255.
    1. Gehring J. Graphview. Available online: (accessed on 16 June 2014)
    1. Android API. Available online: (accessed on 16 June 2014)
    1. Media Player Android API. Available online: (accessed on 16 June 2014)
    1. Youtube Android Player API. Available online: (accessed on 16 June 2014)
    1. mHealthDroid App (Google Play) Available online: (accessed on 16 June 2014)
    1. Lin JJ, Mamykina L, Lindtner S, Delajoux G, Strub HB. Fish'n'steps: Encouraging physical activity with an interactive computer game. Proceedings of the 8th International Conference on Ubiquitous Computing. 2006;4206:261–278.
    1. Consolvo S, McDonald DW, Toscos T, Chen MY, Froehlich J, Harrison B, Activity sensing in the wild: a field trial of ubifit garden. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2008. pp. 1797–1806.
    1. Sazonov ES, Makeyev O, Schuckers S, Lopez-Meyer P, Melanson EL, Neuman MR. Automatic detection of swallowing events by acoustical means for applications of monitoring of ingestive behavior. IEEE Transactions on Biomedical Engineering. 2010;57(3):626–633.
    1. Sazonov E, Metcalfe K, Lopez-Meyer P, Tiffany S. Rf hand gesture sensor for monitoring of cigarette smoking. 2011 Fifth International Conference on Sensing Technology. 2011. pp. 426–430.
    1. Luštrek M, Kaluža B. Fall detection and activity recognition with machine learning. Informatica. 2009;33(2):197–204.
    1. Tamura T, Yoshimura T, Sekine M, Uchida M, Tanaka O. A wearable airbag to prevent fall injuries. IEEE Transactions on Information Technology in Biomedicine. 2009;13(6):910–914.
    1. Bianchi F, Redmond SJ, Narayanan MR, Cerutti S, Lovell NH. Barometric pressure and triaxial accelerometry-based falls event detection. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2010;18(6):619–627.
    1. Chen KY, Harniss M, Patel S, Johnson K. Implementing technology-based embedded assessment in the home and community life of individuals aging with disabilities: a participatory research and development study. Disability and Rehabilitation: Assistive Technology. 2014;9(2):112–120. doi: 10.3109/17483107.2013.805824.
    1. Banos O, Garcia R, Saez A. MHEALTH dataset. 2014.
    1. Banos O, Damas M, Pomares H, Rojas F, Delgado-Marquez B, Valenzuela O. Human activity recognition based on a sensor weighting hierarchical classifier. Soft Computing. 2013;17(2):333–343. doi: 10.1007/s00500-012-0896-3.
    1. Chen L, Hoey J, Nugent CD, Cook DJ, Yu Z. Sensor-based activity recognition. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions. 2012;42(6):790–808.
    1. Lara O, Labrador M. A survey on human activity recognition using wearable sensors. Communications Surveys Tutorials, IEEE, 2012. 2012;15(3):1192–1209.
    1. Banos O, Galvez JM, Damas M, Pomares H, Rojas I. Window size impact in human activity recognition. Sensors. 2014;14(4):6474–6499. doi: 10.3390/s140406474.
    1. Bao L, Intille SS. Activity recognition from user-annotated acceleration data. Pervasive Computing. 2004;3001:1–17. doi: 10.1007/978-3-540-24646-6_1.
    1. Ravi N, Mysore P, Littman ML. Activity recognition from accelerometer data. Proceedings of the 17th Conference on Innovative Applications of Artificial Intelligence. 2005. pp. 1541–1546.
    1. Figo D, Diniz PC, Ferreira DR, Cardoso JMP. Preprocessing techniques for context recognition from accelerometer data. Personal and Ubiquitous Computing. 2010;14(7):645–662. doi: 10.1007/s00779-010-0293-9.
    1. Kwapisz JR, Weiss GM, Moore SA. Activity recognition using cell phone accelerometers. 17th Conference on Knowledge Discovery and Data Mining. 2011;12(2):74–82.
    1. Banos O, Damas M, Pomares H, Rojas I. On the use of sensor fusion to reduce the impact of rotational and additive noise in human activity recognition. Sensors. 2012;12(6):8039–8054.
    1. Banos O, Toth MA, Damas M, Pomares H, Rojas I. Dealing with the effects of sensor displacement in wearable activity recognition. Sensors. 2014;14(6):9995–10023. doi: 10.3390/s140609995.
    1. Maurer U, Smailagic A, Siewiorek DP, Deisher M. Activity recognition and monitoring using multiple sensors on different body positions. International Workshop on Wearable and Implantable Body Sensor Networks. 2006. pp. 113–116.
    1. Parkka J, Ermes M, Korpipaa P, Mantyjarvi J, Peltola J, Korhonen I. Activity classification using realistic data from wearable sensors. IEEE Transactions on Information Technology in Biomedicine. 2006;10(1):119–128. doi: 10.1109/TITB.2005.856863.
    1. Arlot S, Celisse A. A survey of cross-validation procedures for model selection. Statistics Surveys. 2010;4:40–79. doi: 10.1214/09-SS054.
    1. Stone M. Asymptotics for and against cross-validation. Biometrika. 1977;64(1):29–35. doi: 10.1093/biomet/64.1.29.
    1. Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Information Processing and Management. 2009;45(4):427–437. doi: 10.1016/j.ipm.2009.03.002.
    1. Bulling A, Blanke U, Schiele B. A tutorial on human activity recognition using body-worn inertial sensors. ACM Comput Surv. 2014;46(3):1–33.

Source: PubMed

Sponsorer og samarbeidspartnere

Medisinsk tilstand

Legemiddelintervensjoner

3
Abonnere