Context-Aware Medication Device
Keywords: Medication adherence, cognitive device, cognitive orthosis, smart homes, assisted cognition, context-aware design
Overview of Research
Non-compliance and improper usage of medication is a common problem among older adults due to decreased cognition associated with the natural aging process and other disabilities such as dementia. Examples of non-compliance and improper usage include not taking medication at the required time, or as prescribed.
Several techniques and interventions have been used to help increase medication adherence including social support, education about the impact of adherence, improved design of medication labels and instructions, and various prospective reminding devices. However, medication non-compliance still remains one of the primary reasons for the hospitalization of older adults, accounting for approximately 20 percent of elderly hospital admissions for acute care.
Reminding devices range from low-tech solutions, such as plastic boxes divided into sections labelled by times and day, to electronic devices that have various levels of sophistication. The simplest of the electronic devices are timers on medication container caps that are reset for the same interval every time the cap is opened. The more complex are systems that dispense the drugs at the correct time and sound an alarm if the drugs are not taken within a given length of time. The user is required to push a button on the device to indicate when the medication has been taken successfully . Providing this manual feedback may be achievable for a "healthier" user, but most likely is not acceptable for a user with poor memory, or impairments in planning and execution functions, to complete.
Existing automated reminding systems are sometimes ineffective because they do not take into consideration the user's context when making decisions regarding how and when to provide reminders. For example, often a medication device is located in a user's bathroom. If the person is in the kitchen when the alarm on the device is sounded, the person most likely will not hear the reminder rendering the device ineffective. This lack of "intelligence" may also result in unnecessary prompts to be provided and frustration and further confusion on the part of the user.
Context can be defined as any information that can be used to characterize the situation of a person, place, or object. This information may include the location, identity, and state of people, groups and computational and physical objects. Context can be used to interpret explicit acts, making communication, such as reminders, much more efficient and naturally fitting with a user's activities. The use of this type of information and other context-aware design principles has rapidly been emerging is several fields including robotics, mobile computing devices, online help systems, web browsing technologies, and more recently, supportive environments and smart homes.
System Overview
We are applying context-aware design principles to the design of a new medication reminding system. The system will be able to determine user-specific information and characteristics in order to provide reminders that are more appropriate for that particular person's preferences and habits.
At this stage of our design, we will begin by incorporating simple examples of contextual information into our prototype:
1) The system will provide various types of reminders, such as pre-recorded verbal messages, when it is time for the person to take the required medication. These prompts will be customized for each user; e.g. use of first or last names in the prompts, gender of the recorded voice, etc.
2) The system will be able to automatically determine where in the home the person is located and provide reminders in that location.
3) The system will be able to automatically determine if the person has taken the medication.
4) If the person does not respond to the issued reminders by the system within an appropriate time frame, the system will provide this feedback to an external source, such as a neighbour or family member in order for further assistance to be provided to the user.
Three modules will be developed: 1) A main control unit; 2) An indoor positioning and reminding system; and 3) A medication uptake sensor module.
At a specified time prior to medication, the system will determine the location of the person within the house by reading wireless outputs from the motion sensors located in each room. The main control unit will then process these inputs to determine an appropriate reminder to be played or action to be carried out. The reminder, which will be a pre-recorded verbal prompt digitally stored by the main control unit, will be played via a speaker installed in the room in which the person is located. Once the required reminder has been issued, the medication uptake module will then monitor whether the person takes the medication. If it is detected that the person has not taken the medication after a set period of time, the system will re-assess the person's location and another reminder will be issued in the required location. If the medication is not taken after a certain number of reminders, the main control unit will activate its automatic emergency contact function in order to notify a family member, doctor, or neighbour that the person has not complied.
At this stage of our development we are not concerned with the dispensing of the medication. As there are numerous dispensing devices already available on the market, we are focusing solely on the reminding system. Subsequent development phases will include incorporating our new technology into an existing dispensing unit, or developing our own if we feel this is more appropriate.
Selected References Related to this Project
Mihailidis, A., Tse, L., and Rawicz, A. (June 21 - 23, 2003). A context-aware medication reminding system: Preliminary design and development, Rehabilitation Engineering and Assistive Technology Society of North America, Atlanta (CD-ROM Proceedings).
Mihailidis, A., and Fernie, G. (2002). Context-aware assistive devices for older adults with dementia. Gerontechnology, 2(2), 173-189.
Research Team
Alex Mihailidis, Ph.D. P.Eng. (University of Toronto)
Lydia Tse (Simon Fraser University)
