RESUMO
Inhalers are devices which deliver medication to the airways in the treatment of chronic respiratory diseases. When used correctly inhalers relieve and improve patients' symptoms. However, adherence to inhaler medication has been demonstrated to be poor, leading to reduced clinical outcomes, wasted medication, and higher healthcare costs. There is a clinical need for a system that can accurately monitor inhaler adherence as currently no method exists to evaluate how patients use their inhalers between clinic visits. This paper presents a method of automatically evaluating inhaler adherence through acoustic analysis of inhaler sounds. An acoustic monitoring device was employed to record the sounds patients produce while using a Diskus dry powder inhaler, in addition to the time and date patients use the inhaler. An algorithm was designed and developed to automatically detect inhaler events from the audio signals and provide feedback regarding patient adherence. The algorithm was evaluated on 407 audio files obtained from 12 community dwelling asthmatic patients. Results of the automatic classification were compared against two expert human raters. For patient data for whom the human raters Cohen's kappa agreement score was [Formula: see text], results indicated that the algorithm's accuracy was 83% in determining the correct inhaler technique score compared with the raters. This paper has several clinical implications as it demonstrates the feasibility of using acoustics to objectively monitor patient inhaler adherence and provide real-time personalized medical care for a chronic respiratory illness.
RESUMO
BACKGROUND: Cognitive assessments are valuable tools in assessing neurological conditions. They are critical in measuring deficits in cognitive function in an array of neurological disorders and during the ageing process. Automation of cognitive assessments is one way to address the increasing burden on medical resources for an ever increasing ageing population. OBJECTIVE: This study investigated the suitability of using automated Interactive Voice Response (IVR) technology to deliver a suite of cognitive assessments to older adults using speech as the input modality. METHODS: Several clinically valid and gold-standard cognitive assessments were selected for implementation in the IVR application. The IVR application was designed using human centred design principles to ensure the experience was as user friendly as possible. Sixty one participants completed two IVR assessments and one face to face (FF) assessment with a neuropsychologist. Completion rates for individual tests were inspected to identify those tests that are most suitable for administration via IVR technology. Interclass correlations were calculated to assess the reliability of the automated administration of the cognitive assessments across delivery modes. RESULTS: While all participants successfully completed all automated assessments, variability in the completion rates for different cognitive tests was observed. Statistical analysis found significant interclass correlations for certain cognitive tests between the different modes of administration. Analysis also suggests that an initial FF assessment reduces the variability in cognitive test scores when introducing automation into such an assessment. CONCLUSION: [corrected] This study has demonstrated the functional and cognitive reliability of administering specific cognitive tests using an automated, speech driven application. This study has defined the characteristics of existing cognitive tests that are suitable for such an automated delivery system and also informs on the limitations of other cognitive tests for this modality. This study presents recommendations for developing future large scale cognitive assessments.