Tuberculosis control, and the where and why of artificial intelligence

Riddhi Doshi, Dennis Falzon, Bruce V. Thomas, Zelalem Temesgen, Lal Sadasivan, Giovanni Battista Migliori, Mario Raviglione

Research output: Contribution to journalReview article

Abstract

Countries aiming to reduce their tuberculosis (TB) burden by 2035 to the levels envisaged by the World Health Organization End TB Strategy need to innovate, with approaches such as digital health (electronic and mobile health) in support of patient care, surveillance, programme management, training and communication. Alongside the large-scale roll-out required for such interventions to make a significant impact, products must stay abreast of advancing technology over time. The integration of artificial intelligence into new software promises to make processes more effective and efficient, endowing them with a potential hitherto unimaginable. Users can benefit from artificial intelligence-enabled pattern recognition software for tasks ranging from reading radiographs to adverse event monitoring, sifting through vast datasets to personalise a patient’s care plan or to customise training materials. Many experts forecast the imminent transformation of the delivery of healthcare services. We discuss how artificial intelligence and machine learning could revolutionise the management of TB.

Original languageEnglish
Article number00056-2017
JournalERS Monograph
Volume3
Issue number2
DOIs
Publication statusPublished - Apr 1 2017

Fingerprint

Artificial Intelligence
Tuberculosis
Patient Care
Software
Telemedicine
Reading
Communication
Technology
Delivery of Health Care
Education
Health

ASJC Scopus subject areas

  • Pulmonary and Respiratory Medicine

Cite this

Doshi, R., Falzon, D., Thomas, B. V., Temesgen, Z., Sadasivan, L., Migliori, G. B., & Raviglione, M. (2017). Tuberculosis control, and the where and why of artificial intelligence. ERS Monograph, 3(2), [00056-2017]. https://doi.org/10.1183/23120541.00056-2017

Tuberculosis control, and the where and why of artificial intelligence. / Doshi, Riddhi; Falzon, Dennis; Thomas, Bruce V.; Temesgen, Zelalem; Sadasivan, Lal; Migliori, Giovanni Battista; Raviglione, Mario.

In: ERS Monograph, Vol. 3, No. 2, 00056-2017, 01.04.2017.

Research output: Contribution to journalReview article

Doshi, R, Falzon, D, Thomas, BV, Temesgen, Z, Sadasivan, L, Migliori, GB & Raviglione, M 2017, 'Tuberculosis control, and the where and why of artificial intelligence', ERS Monograph, vol. 3, no. 2, 00056-2017. https://doi.org/10.1183/23120541.00056-2017
Doshi R, Falzon D, Thomas BV, Temesgen Z, Sadasivan L, Migliori GB et al. Tuberculosis control, and the where and why of artificial intelligence. ERS Monograph. 2017 Apr 1;3(2). 00056-2017. https://doi.org/10.1183/23120541.00056-2017
Doshi, Riddhi ; Falzon, Dennis ; Thomas, Bruce V. ; Temesgen, Zelalem ; Sadasivan, Lal ; Migliori, Giovanni Battista ; Raviglione, Mario. / Tuberculosis control, and the where and why of artificial intelligence. In: ERS Monograph. 2017 ; Vol. 3, No. 2.
@article{445ddc92bd484b9a85aed91dd3c31fd6,
title = "Tuberculosis control, and the where and why of artificial intelligence",
abstract = "Countries aiming to reduce their tuberculosis (TB) burden by 2035 to the levels envisaged by the World Health Organization End TB Strategy need to innovate, with approaches such as digital health (electronic and mobile health) in support of patient care, surveillance, programme management, training and communication. Alongside the large-scale roll-out required for such interventions to make a significant impact, products must stay abreast of advancing technology over time. The integration of artificial intelligence into new software promises to make processes more effective and efficient, endowing them with a potential hitherto unimaginable. Users can benefit from artificial intelligence-enabled pattern recognition software for tasks ranging from reading radiographs to adverse event monitoring, sifting through vast datasets to personalise a patient’s care plan or to customise training materials. Many experts forecast the imminent transformation of the delivery of healthcare services. We discuss how artificial intelligence and machine learning could revolutionise the management of TB.",
author = "Riddhi Doshi and Dennis Falzon and Thomas, {Bruce V.} and Zelalem Temesgen and Lal Sadasivan and Migliori, {Giovanni Battista} and Mario Raviglione",
year = "2017",
month = "4",
day = "1",
doi = "10.1183/23120541.00056-2017",
language = "English",
volume = "3",
journal = "ERS Monograph",
issn = "2312-508X",
publisher = "European Respiratory Society",
number = "2",

}

TY - JOUR

T1 - Tuberculosis control, and the where and why of artificial intelligence

AU - Doshi, Riddhi

AU - Falzon, Dennis

AU - Thomas, Bruce V.

AU - Temesgen, Zelalem

AU - Sadasivan, Lal

AU - Migliori, Giovanni Battista

AU - Raviglione, Mario

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Countries aiming to reduce their tuberculosis (TB) burden by 2035 to the levels envisaged by the World Health Organization End TB Strategy need to innovate, with approaches such as digital health (electronic and mobile health) in support of patient care, surveillance, programme management, training and communication. Alongside the large-scale roll-out required for such interventions to make a significant impact, products must stay abreast of advancing technology over time. The integration of artificial intelligence into new software promises to make processes more effective and efficient, endowing them with a potential hitherto unimaginable. Users can benefit from artificial intelligence-enabled pattern recognition software for tasks ranging from reading radiographs to adverse event monitoring, sifting through vast datasets to personalise a patient’s care plan or to customise training materials. Many experts forecast the imminent transformation of the delivery of healthcare services. We discuss how artificial intelligence and machine learning could revolutionise the management of TB.

AB - Countries aiming to reduce their tuberculosis (TB) burden by 2035 to the levels envisaged by the World Health Organization End TB Strategy need to innovate, with approaches such as digital health (electronic and mobile health) in support of patient care, surveillance, programme management, training and communication. Alongside the large-scale roll-out required for such interventions to make a significant impact, products must stay abreast of advancing technology over time. The integration of artificial intelligence into new software promises to make processes more effective and efficient, endowing them with a potential hitherto unimaginable. Users can benefit from artificial intelligence-enabled pattern recognition software for tasks ranging from reading radiographs to adverse event monitoring, sifting through vast datasets to personalise a patient’s care plan or to customise training materials. Many experts forecast the imminent transformation of the delivery of healthcare services. We discuss how artificial intelligence and machine learning could revolutionise the management of TB.

UR - http://www.scopus.com/inward/record.url?scp=85025119429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85025119429&partnerID=8YFLogxK

U2 - 10.1183/23120541.00056-2017

DO - 10.1183/23120541.00056-2017

M3 - Review article

VL - 3

JO - ERS Monograph

JF - ERS Monograph

SN - 2312-508X

IS - 2

M1 - 00056-2017

ER -