Gait speed and survival of older surgical patient with cancer: Prediction after machine learning

Sasani, Keyvan; Catanese, Helen N.; Ghods, Alireza; Rokni, Seyed Ali; Ghasemzadeh, Hassan; Downey, Robert J.; Shahrokni, Armin

doi:10.1016/j.jgo.2018.06.012

Cited by 20 publications

(18 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For a digital patent reported CSGA, the remainder of the clinical components could be integrated into routine oncology appointments, without the need for a formal GA service. There is some evidence that even a Timed Up and Go test can be predicted using a threequestion decision tree, although this remains to be prospectively validated (39). This movement appears to have driven the reductionism of CSGA and emphasis on using short instruments easily used in outpatient settings by non-specialist staff (13).…”

Section: Information Technologymentioning

confidence: 99%

Implementation of geriatric assessment in oncology settings: A systematic realist review

McKenzie

Bullock

Greenley

et al. 2021

Journal of Geriatric Oncology

View full text Add to dashboard Cite

Older adults with cancer are more likely to have worse clinical outcomes than their younger counterparts, and shared decision-making can be difficult, due to both complexity from adverse ageing and under-representation in clinical trials. Geriatric assessment (GA) has been increasingly recognised as a predictive and prehabilitative tool for older adults with cancer. However, GA has been notoriously difficult to implement in oncological settings due to workforce, economic, logistical, and practical barriers. We aimed to review the heterogenous literature on implementation of GA in oncology settings to understand the different implementation context configurations of GA and the mechanisms they trigger to enable successful implementation. A systematic realist review was undertaken in two stages: i) systematic searches with structured data extraction combined with iterative key stakeholder consultations to develop programme theories for implementing GA in oncology settings; ii) synthesis to refine programme theories. Medline, Embase, PsycInfo, Cochrane Library,

show abstract

Section: Information Technologymentioning

confidence: 99%

Implementation of geriatric assessment in oncology settings: A systematic realist review

McKenzie

Bullock

Greenley

et al. 2021

Journal of Geriatric Oncology

View full text Add to dashboard Cite

show abstract

“… 11 A prolonged TUG has a simple 3-item algorithm that may assist in distinguishing those with slow gait speed from those who walk faster. 12 Supplemental Digital Content 1 ( http://links.lww.com/DCR/B379 ) presents an algorithm for simple office-based frailty evaluation to trigger additional referrals. Supplemental Digital Content 2 ( http://links.lww.com/DCR/B378 ) presents a summary of the common tests for frailty and the threshold for abnormal results.…”

Section: Domains Of Gamentioning

confidence: 99%

Care of the Geriatric Colorectal Surgical Patient and Framework for Creating a Geriatric Program: A Compendium From the 2019 American Society of Colon and Rectal Surgeons Annual Meeting

Saur

Montroni

Shahrokni

et al. 2020

Diseases of the Colon &Amp; Rectum

Self Cite

View full text Add to dashboard Cite

show abstract

“… The data provide a set of data acquired during the performance of the Timed-Up and Go test [1] , [2] , [3] with the sensors available in a mobile [ 4 , 5 ] and a BITalino devices [6] , including accelerometer, magnetometer, Electroencephalography and Electrocardiography sensors; The data is important for the creation of solutions for automatic validation of Timed-Up and Go test, and, as we acquired Electroencephalography and Electrocardiography data, it will allows to the creation of patterns of different diseases [7] , [8] , [9] , [10] for further developments; The acquired data may be used for the recognition of different stages and activities during the Timed-Up and Go test, as well as the identification of diseases with machine learning techniques [10] , [11] , [12] ; The data are valid for the creation of disease patterns associated with movement, cardiac and brain frequency, and other problems related to walking activity, applying different techniques to reduce the artefacts [13] , [14] , [15] . It also allows further research with the sensors available in off-the-shelf mobile devices for further creation of Mobile Health solutions [ 16 , 17 ].…”

Section: Value Of the Datamentioning

confidence: 99%

“…The acquired data may be used for the recognition of different stages and activities during the Timed-Up and Go test, as well as the identification of diseases with machine learning techniques [10] , [11] , [12] ;…”

Section: Value Of the Datamentioning

confidence: 99%

Data acquisition of timed-up and go test with older adults: accelerometer, magnetometer, electrocardiography and electroencephalography sensors’ data

et al. 2020

View full text Add to dashboard Cite

We present a dataset related to the acquisition of different sensors data during the performance of the Timed-Up and Go test with the mobile device positioned in a waistband for the acquisition of accelerometer and magnetometer data, and a BITalino device positioned in a chest band for the acquisition of Electrocardiography and Electroencephalography for further processing. The data acquired from the BITalino device is acquired simultaneously by a Bluetooth connection with the same mobile application. The data was acquired in five institutions, including Centro Comunitário das Lameiras, Lar Nossa Senhora de Fátima, Centro Comunitário das Minas da Panasqueira, Lar da Misericórdia da Santa Casa da Misericórdia do Fundão, and Lar da Aldeia de Joanes da Santa Casa da Misericórdia do Fundão from Fundão and Covilhã municipalities (Portugal). This article describes the data acquired from a several subjects from the different institutions for the acquisition of accelerometer and magnetometer data, where each person performed the Timed-Up and Go test three times, where each output from the sensors was acquired with a sampling rate of 100 Hz. Related to the data acquired by the sensors connected to the BITalino device, 31 persons performed the different experiments related to the Timed-Up and Go Test. Following the data acquired from Electroencephalography and Electrocardiography sensors, only the data acquired from 14 individuals was considered valid. The data acquired by a BITalino device has a sampling rate of 100 Hz. These data can be reused for testing machine learning methods for the evaluation of the performance of the Timed-Up and Go test with older adults.

show abstract

Gait speed and survival of older surgical patient with cancer: Prediction after machine learning

Abstract: Machine learning algorithms can accurately predict the gait speed of older patients with cancer, based on their response to questions addressing other aspects of functional status.

Cited by 20 publications

References 29 publications

Implementation of geriatric assessment in oncology settings: A systematic realist review

Implementation of geriatric assessment in oncology settings: A systematic realist review

Care of the Geriatric Colorectal Surgical Patient and Framework for Creating a Geriatric Program: A Compendium From the 2019 American Society of Colon and Rectal Surgeons Annual Meeting

Data acquisition of timed-up and go test with older adults: accelerometer, magnetometer, electrocardiography and electroencephalography sensors’ data

Contact Info

Product

Resources

About