Assisted Medication Management in Elderly Care Using Miniaturised Near-Infrared Spectroscopy

Near-infrared spectroscopy (NIRS) measures the light reflected from objects to infer highly detailed information about their molecular composition. Traditionally, NIRS has been an instrument reserved for laboratory usage, but recently affordable and smaller devices for NIRS have proliferated. Pairing this technology with the ubiquitous smartphone opens up a plethora of new use cases. In this paper, we explore one such use case, namely medication management in a nursing home/elderly care centre. First, we conducted a qualitative user study with nurses working in an elderly care centre to examine the protocols and workflows involved in administering medication, and the nurses' perceptions on using this technology. Based on our findings, we identify the main impact areas that would benefit from introducing miniaturised NIRS. Finally, we demonstrate via a user study in a realistic scenario that miniaturised NIRS can be effectively used for medication management when leveraging appropriate machine learning techniques. Specifically, we assess the performance of multiple pre-processing and classification algorithms for a selected set of pharmaceuticals. In addition, we compare our solution with currently used methods for pharmaceutical identification in a local care centre. We hope that our reflection on the multiple aspects associated with the introduction of this device in an elderly care setting can help both academics and practitioners working on related problems.

[1]  Sara Woods Drug consumption rooms in Europe: Organisational overview. , 2014 .

[2]  Lan Sun,et al.  Pharmaceutical Raw Material Identification Using Miniature Near-Infrared (MicroNIR) Spectroscopy and Supervised Pattern Recognition Using Support Vector Machine , 2016, Applied spectroscopy.

[3]  Telmo Adão,et al.  HelpmePills: A Mobile Pill Recognition Tool for Elderly Persons☆ , 2014 .

[4]  James Rodgers,et al.  Impact of temperature and relative humidity on the near infrared spectroscopy measurements of cotton fiber micronaire , 2018 .

[5]  H. Martens,et al.  Extended multiplicative signal correction and spectral interference subtraction: new preprocessing methods for near infrared spectroscopy. , 1991, Journal of pharmaceutical and biomedical analysis.

[6]  Jorge Gonçalves,et al.  Instrumenting smartphones with portable NIRS , 2016, UbiComp Adjunct.

[7]  Ethan V. Munson,et al.  40 Years of Searching for the Best Computer System Response Time , 2011, Interact. Comput..

[8]  P. Barber Absorption and scattering of light by small particles , 1984 .

[9]  Matthias Bethge,et al.  Comparing deep neural networks against humans: object recognition when the signal gets weaker , 2017, ArXiv.

[10]  K Ohe,et al.  A Smartphone-based Medication Self-management System with Real-time Medication Monitoring , 2013, Applied Clinical Informatics.

[11]  Frans van den Berg,et al.  Review of the most common pre-processing techniques for near-infrared spectra , 2009 .

[12]  Luc Van Gool,et al.  Hough Forests for Object Detection, Tracking, and Action Recognition , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Jorge Gonçalves,et al.  Towards Commoditised Near Infrared Spectroscopy , 2017, Conference on Designing Interactive Systems.

[14]  N. MacKinnon,et al.  Identifying, understanding and overcoming barriers to medication error reporting in hospitals: a focus group study , 2012, BMJ quality & safety.

[15]  Olavi Junttila,et al.  Effects of red, far-red and blue light in maintaining growth in latitudinal populations of Norway spruce (Picea abies). , 2006, Plant, cell & environment.

[16]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[17]  Jorge Gonçalves,et al.  Crowdsourcing situated & subjective knowledge for decision support , 2016, UbiComp Adjunct.

[18]  Matti Kinnunen,et al.  Measurements of fundamental properties of homogeneous tissue phantoms , 2015, Journal of biomedical optics.

[19]  Jorge Gonçalves,et al.  Modelling smartphone usage: a markov state transition model , 2016, UbiComp.

[20]  Francisco J. García-Peñalvo,et al.  Situational impairments to mobile interaction in cold environments , 2016, Ubiquitous Computing.

[21]  Risto A. Myllyla,et al.  Measurements of glucose content in scattering media with time-of-flight technique: comparison with Monte Carlo simulations , 2004, Saratov Fall Meeting.

[22]  Wei-Chih Hsu,et al.  A smart medication system using wireless sensor network technologies , 2011 .

[23]  R. Barnes,et al.  Standard Normal Variate Transformation and De-Trending of Near-Infrared Diffuse Reflectance Spectra , 1989 .

[24]  C. Ruckebusch,et al.  Quantitative Analysis of Cotton—Polyester Textile Blends from Near-Infrared Spectra , 2006, Applied spectroscopy.

[25]  Chunjiang Zhao,et al.  Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging , 2016, Comput. Electron. Agric..

[26]  Jorge Gonçalves,et al.  A data hiding approach for sensitive smartphone data , 2016, UbiComp.

[27]  Roman M. Balabin,et al.  Variable selection in near-infrared spectroscopy: benchmarking of feature selection methods on biodiesel data. , 2011, Analytica chimica acta.

[28]  Yves Roggo,et al.  Near infrared spectroscopy for counterfeit detection using a large database of pharmaceutical tablets. , 2016, Journal of pharmaceutical and biomedical analysis.

[29]  R. Verbrugge,et al.  Impact of Medication Adherence on Hospitalization Risk and Healthcare Cost , 2005, Medical care.

[30]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[31]  Igor V Meglinski,et al.  Influence of probe pressure on diffuse reflectance spectra of human skin measured in vivo. , 2017, Journal of biomedical optics.

[32]  Emil W. Ciurczak,et al.  Handbook of Near-Infrared Analysis , 1992 .

[33]  Risto Myllylä,et al.  Glucose Sensing in Flowing Blood and Intralipid by Laser Pulse Time-of-Flight and Optical Coherence Tomography Techniques , 2012, IEEE Journal of Selected Topics in Quantum Electronics.

[34]  Jorge Gonçalves,et al.  Designing a context-aware assistive infrastructure for elderly care , 2017, UbiComp/ISWC Adjunct.

[35]  Ing-Long Wu,et al.  The adoption of mobile healthcare by hospital's professionals: An integrative perspective , 2011, Decis. Support Syst..

[36]  Regina M. Benjamin,et al.  Medication Adherence: Helping Patients Take Their Medicines as Directed , 2012, Public health reports.

[37]  Paul N Newton,et al.  Poor-quality antimalarial drugs in southeast Asia and sub-Saharan Africa. , 2012, The Lancet. Infectious diseases.

[38]  C. Pasquini Near Infrared Spectroscopy: fundamentals, practical aspects and analytical applications , 2003 .

[39]  M. Manley Near-infrared spectroscopy and hyperspectral imaging: non-destructive analysis of biological materials. , 2014, Chemical Society reviews.

[40]  Shasha Wang,et al.  Deep feature weighting for naive Bayes and its application to text classification , 2016, Eng. Appl. Artif. Intell..

[41]  H. Siesler,et al.  Near-infrared spectroscopy:principles,instruments,applications , 2002 .

[42]  Nick Barber,et al.  Evaluation of the scale, causes and costs of waste medicines. Report of DH funded national project. , 2010 .

[43]  M. Jamrógiewicz Application of the near-infrared spectroscopy in the pharmaceutical technology. , 2012, Journal of pharmaceutical and biomedical analysis.

[44]  M. Dyrby,et al.  Chemometric Quantitation of the Active Substance (Containing C≡N) in a Pharmaceutical Tablet Using Near-Infrared (NIR) Transmittance and NIR FT-Raman Spectra , 2002 .

[45]  D L Massart,et al.  Identification of pharmaceutical excipients using NIR spectroscopy and SIMCA. , 1999, Journal of pharmaceutical and biomedical analysis.

[46]  Jorge Gonçalves,et al.  Informing Caregivers Through an Assistive Tool: An Investigation of Elderly Care Metrics , 2017, BCS HCI.

[47]  Jorge Gonçalves,et al.  TestAWARE: A Laboratory-Oriented Testing Tool for Mobile Context-Aware Applications , 2017, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[48]  Heinz W. Siesler,et al.  Qualitative and Quantitative Pharmaceutical Analysis with a Novel Hand-Held Miniature near Infrared Spectrometer , 2013 .

[49]  Geoffrey I. Webb,et al.  Encyclopedia of Machine Learning , 2011, Encyclopedia of Machine Learning.

[50]  Niels van Berkel,et al.  Understanding elderly care: a field-study for designing future homes , 2017, iiWAS.

[51]  Dieter Schmalstieg,et al.  Instant Medical Pill Recognition on Mobile Phones , 2011, RA 2011.

[52]  A. W. M. van den Enden,et al.  Discrete Time Signal Processing , 1989 .

[53]  Eija Metsälä,et al.  Medication errors in elderly acute care--a systematic review. , 2014, Scandinavian journal of caring sciences.

[54]  Danfei Xu,et al.  Tactile identification of objects using Bayesian exploration , 2013, 2013 IEEE International Conference on Robotics and Automation.

[55]  María Martínez Pérez,et al.  Application of RFID Technology in Patient Tracking and Medication Traceability in Emergency Care , 2012, Journal of Medical Systems.

[56]  J. Hernández-Hierro,et al.  Chilean flour and wheat grain: tracing their origin using near infrared spectroscopy and chemometrics. , 2014, Food chemistry.

[57]  G M Hieftje Signal-to-Noise Enhancement Through Instrumental Techniques. , 1972, Analytical chemistry.

[58]  Theresa Dankowski,et al.  Calibrating random forests for probability estimation , 2016, Statistics in medicine.