Matches in SemOpenAlex for { <https://semopenalex.org/work/W3161343107> ?p ?o ?g. }
- W3161343107 endingPage "106165" @default.
- W3161343107 startingPage "106165" @default.
- W3161343107 abstract "• A model is developed to predict physical activity cut-points on accelerometer based on individual characteristics • Post data collection analytical process helps towards a standardised method for characterising physical activity • Multiple features calculated from raw accelerometer data was used to enrich the feature set for training machine learning • Personalisation was achieved by combining raw accelerometer data with person-specific data e.g., blood pressure Body-worn accelerometers are the most popular method for objectively assessing physical activity in older adults. Many studies have developed generic accelerometer cut-points for defining activity intensity in metabolic equivalents for older adults. However, methodological diversity in current studies has led to a great deal of variation in the resulting cut-points, even when using data from the same accelerometer. In addition, the generic cut-point approach assumes that ‘one size fits all’ which is rarely the case in real life. This study proposes a machine learning method for personalising activity intensity cut-points for older adults. Firstly, raw accelerometry data was collected from 33 older adults who performed set activities whilst wearing two accelerometer devices: GENEActive (wrist worn) and ActiGraph (hip worn). ROC analysis was applied to generate personalised cut-point for each data sample based on a device. Four cut-points have been considered: Sensitivity optimised Sedentary Behaviour; Specificity optimised Moderate to Vigorous Physical Activity; Youden optimised Sedentary Behaviour; and Youden optimised Moderate to Vigorous Physical Activity. Then, an additive regression algorithm trained on biodata features, that concern the individual characteristics of participants, was used to predict the cut-points. As the model output is a numeric cut-point value (and not discrete), evaluation was based on two error metrics, Mean Absolute Error and Root Mean Square Error. Standard Error of estimation was also calculated to measure the accuracy of prediction (goodness of fit) and this was used for performance comparison between our approach and the state-of-the-art. Hold-out and 10-Fold cross validation methods were used for performance validation and comparison. The results show that our personalised approach performed consistently better than the state-of-the-art with 10-Fold cross validation on all four cut-points considered for both devices. For the ActiGraph device, the Standard Error of estimation from our approach was lower by 0.33 (Youden optimised Sedentary Behaviour), 9.50 (Sensitivity optimised Sedentary Behaviour), 0.64 (Youden optimised Moderate to Vigorous Physical Activity) and 22.11 (Specificity optimised Moderate to Vigorous Physical Activity). Likewise, the Standard Error of estimation from our approach was lower for the GENEActiv device by 2.29 (Youden optimised Sedentary Behaviour), 41.65 (Sensitivity optimised Sedentary Behaviour), 4.31 (Youden optimised Moderate to Vigorous Physical Activity) and 347.15 (Specificity optimised Moderate to Vigorous Physical Activity). personalised cut-point can be predicted without prior knowledge of accelerometry data. The results are very promising especially when we consider that our method predicts cut-points without prior knowledge of accelerometry data, unlike the state-of-the-art. More data is required to expand the scope of the experiments presented in this paper." @default.
- W3161343107 created "2021-05-24" @default.
- W3161343107 creator A5000316628 @default.
- W3161343107 creator A5005374951 @default.
- W3161343107 creator A5010094949 @default.
- W3161343107 creator A5015468991 @default.
- W3161343107 creator A5060320466 @default.
- W3161343107 creator A5091371031 @default.
- W3161343107 date "2021-09-01" @default.
- W3161343107 modified "2023-10-01" @default.
- W3161343107 title "Personalised Accelerometer Cut-point Prediction for Older Adults’ Movement Behaviours using a Machine Learning approach" @default.
- W3161343107 cites W1641346875 @default.
- W3161343107 cites W1964903133 @default.
- W3161343107 cites W1965820488 @default.
- W3161343107 cites W1970820481 @default.
- W3161343107 cites W1990263623 @default.
- W3161343107 cites W2000784007 @default.
- W3161343107 cites W2006745520 @default.
- W3161343107 cites W2010163891 @default.
- W3161343107 cites W2011781303 @default.
- W3161343107 cites W2016045939 @default.
- W3161343107 cites W2023453107 @default.
- W3161343107 cites W2024501987 @default.
- W3161343107 cites W2026670008 @default.
- W3161343107 cites W2028152539 @default.
- W3161343107 cites W2028190916 @default.
- W3161343107 cites W2036623705 @default.
- W3161343107 cites W2050998072 @default.
- W3161343107 cites W2051919578 @default.
- W3161343107 cites W2062835801 @default.
- W3161343107 cites W2070493638 @default.
- W3161343107 cites W2072517764 @default.
- W3161343107 cites W2074276081 @default.
- W3161343107 cites W2074490765 @default.
- W3161343107 cites W2079462520 @default.
- W3161343107 cites W2079801649 @default.
- W3161343107 cites W2084103512 @default.
- W3161343107 cites W2085642767 @default.
- W3161343107 cites W2088111259 @default.
- W3161343107 cites W2089180972 @default.
- W3161343107 cites W2089506576 @default.
- W3161343107 cites W2095079167 @default.
- W3161343107 cites W2103522423 @default.
- W3161343107 cites W2108707936 @default.
- W3161343107 cites W2117352205 @default.
- W3161343107 cites W2122131892 @default.
- W3161343107 cites W2138934389 @default.
- W3161343107 cites W2141118708 @default.
- W3161343107 cites W2144686228 @default.
- W3161343107 cites W2256578114 @default.
- W3161343107 cites W2276660292 @default.
- W3161343107 cites W2314386516 @default.
- W3161343107 cites W2316339537 @default.
- W3161343107 cites W2323933728 @default.
- W3161343107 cites W2329483624 @default.
- W3161343107 cites W2381952344 @default.
- W3161343107 cites W2515677080 @default.
- W3161343107 cites W2560466788 @default.
- W3161343107 cites W2560654398 @default.
- W3161343107 cites W2584016859 @default.
- W3161343107 cites W2605334806 @default.
- W3161343107 cites W2768563038 @default.
- W3161343107 cites W2781068560 @default.
- W3161343107 cites W2783446128 @default.
- W3161343107 cites W2896546521 @default.
- W3161343107 cites W2905159640 @default.
- W3161343107 cites W4231595660 @default.
- W3161343107 doi "https://doi.org/10.1016/j.cmpb.2021.106165" @default.
- W3161343107 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34118492" @default.
- W3161343107 hasPublicationYear "2021" @default.
- W3161343107 type Work @default.
- W3161343107 sameAs 3161343107 @default.
- W3161343107 citedByCount "4" @default.
- W3161343107 countsByYear W31613431072021 @default.
- W3161343107 countsByYear W31613431072022 @default.
- W3161343107 countsByYear W31613431072023 @default.
- W3161343107 crossrefType "journal-article" @default.
- W3161343107 hasAuthorship W3161343107A5000316628 @default.
- W3161343107 hasAuthorship W3161343107A5005374951 @default.
- W3161343107 hasAuthorship W3161343107A5010094949 @default.
- W3161343107 hasAuthorship W3161343107A5015468991 @default.
- W3161343107 hasAuthorship W3161343107A5060320466 @default.
- W3161343107 hasAuthorship W3161343107A5091371031 @default.
- W3161343107 hasBestOaLocation W31613431072 @default.
- W3161343107 hasConcept C105795698 @default.
- W3161343107 hasConcept C107038049 @default.
- W3161343107 hasConcept C107457646 @default.
- W3161343107 hasConcept C111919701 @default.
- W3161343107 hasConcept C119857082 @default.
- W3161343107 hasConcept C138885662 @default.
- W3161343107 hasConcept C154945302 @default.
- W3161343107 hasConcept C2524010 @default.
- W3161343107 hasConcept C2780226923 @default.
- W3161343107 hasConcept C2781415353 @default.
- W3161343107 hasConcept C28719098 @default.
- W3161343107 hasConcept C33923547 @default.
- W3161343107 hasConcept C41008148 @default.
- W3161343107 hasConcept C44154836 @default.