Detecting neurodegenerative disorders from web search signals

Neurodegenerative disorders, such as Parkinson’s disease (PD) and Alzheimer’s disease (AD), are important public health problems warranting early detection. We trained machine-learned classifiers on the longitudinal search logs of 31,321,773 search engine users to automatically detect neurodegenerative disorders. Several digital phenotypes with high discriminatory weights for detecting these disorders are identified. Classifier sensitivities for PD detection are 94.2/83.1/42.0/34.6% at false positive rates (FPRs) of 20/10/1/0.1%, respectively. Preliminary analysis shows similar performance for AD detection. Subject to further refinement of accuracy and reproducibility, these findings show the promise of web search digital phenotypes as adjunctive screening tools for neurodegenerative disorders.

[1]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[2]  J. Hughes,et al.  Accuracy of clinical diagnosis of idiopathic Parkinson's disease: a clinico-pathological study of 100 cases. , 1992, Journal of neurology, neurosurgery, and psychiatry.

[3]  P. Hobson,et al.  Accuracy of diagnosis in patients with presumed Parkinson's disease. , 1999, Age and ageing.

[4]  R. Elble,et al.  Diagnostic criteria for essential tremor and differential diagnosis. , 2000, Neurology.

[5]  R. Griggs.  Neurology: Ready for the new millennium , 2000 .

[6]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[7]  S. DeKosky,et al.  Looking Backward to Move Forward: Early Detection of Neurodegenerative Disorders , 2003, Science.

[8]  R. Tanzi,et al.  The genetic epidemiology of neurodegenerative disease. , 2005, The Journal of clinical investigation.

[9]  B. Sonawane,et al.  Neurodegenerative Diseases: An Overview of Environmental Risk Factors , 2005, Environmental health perspectives.

[10]  K. Chaudhuri,et al.  Non-motor symptoms of Parkinson's disease: diagnosis and management , 2006, The Lancet Neurology.

[11]  Kerry Rodden,et al.  Eye-mouse coordination patterns on web search results pages , 2008, CHI Extended Abstracts.

[12]  J. Jankovic.  Parkinson’s disease: clinical features and diagnosis , 2008, Journal of Neurology, Neurosurgery, and Psychiatry.

[13]  Jeremy Ginsberg,et al.  Detecting influenza epidemics using search engine query data , 2009, Nature.

[14]  J. Brownstein,et al.  Digital disease detection--harnessing the Web for public health surveillance. , 2009, The New England journal of medicine.

[15]  B. Yankner,et al.  Neural mechanisms of ageing and cognitive decline , 2010, Nature.

[16]  Elan D Louis,et al.  Distinguishing essential tremor from Parkinson's disease: bedside tests and laboratory evaluations , 2012, Expert review of neurotherapeutics.

[17]  E. Katunina,et al.  [Epidemiology of Parkinson's disease]. , 2013, Zhurnal nevrologii i psikhiatrii imeni S.S. Korsakova.

[18]  Brian W. Powers,et al.  The digital phenotype , 2015, Nature Biotechnology.

[19]  Ryen W. White,et al.  Screening for Pancreatic Adenocarcinoma Using Signals From Web Search Logs: Feasibility Study and Results. , 2016, Journal of oncology practice.

[20]  K. Jellinger,et al.  Accuracy of clinical diagnosis of Parkinson disease: A systematic review and meta-analysis , 2016, Neurology.

[21]  W. Adams,et al.  High-accuracy detection of early Parkinson's Disease using multiple characteristics of finger movement while typing , 2017, PloS one.

[22]  Ryen W. White,et al.  Evaluation of the Feasibility of Screening Patients for Early Signs of Lung Carcinoma in Web Search Logs , 2017, JAMA oncology.