Leveraging Collaborative Filtering to Accelerate Rare Disease Diagnosis

Feichen Shen, Sijia Liu, Yanshan Wang, Liwei Wang, Naveed Afzal, Hongfang D Liu

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In the USA, rare diseases are defined as those affecting fewer than 200,000 patients at any given time. Patients with rare diseases are frequently misdiagnosed or undiagnosed which may due to the lack of knowledge and experience of care providers. We hypothesize that patients' phenotypic information available in electronic medical records (EMR) can be leveraged to accelerate disease diagnosis based on the intuition that providers need to document associated phenotypic information to support the diagnosis decision, especially for rare diseases. In this study, we proposed a collaborative filtering system enriched with natural language processing and semantic techniques to assist rare disease diagnosis based on phenotypic characterization. Specifically, we leveraged four similarity measurements with two neighborhood algorithms on 2010-2015 Mayo Clinic unstructured large patient cohort and evaluated different approaches. Preliminary results demonstrated that the use of collaborative filtering with phenotypic information is able to stratify patients with relatively similar rare diseases.

Original languageEnglish (US)
Pages (from-to)1554-1563
Number of pages10
JournalAMIA ... Annual Symposium proceedings. AMIA Symposium
Volume2017
StatePublished - Jan 1 2017

Fingerprint

Rare Diseases
Natural Language Processing
Intuition
Electronic Health Records
Diagnostic Errors
Semantics

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Leveraging Collaborative Filtering to Accelerate Rare Disease Diagnosis. / Shen, Feichen; Liu, Sijia; Wang, Yanshan; Wang, Liwei; Afzal, Naveed; Liu, Hongfang D.

In: AMIA ... Annual Symposium proceedings. AMIA Symposium, Vol. 2017, 01.01.2017, p. 1554-1563.

Research output: Contribution to journalArticle

Shen, Feichen ; Liu, Sijia ; Wang, Yanshan ; Wang, Liwei ; Afzal, Naveed ; Liu, Hongfang D. / Leveraging Collaborative Filtering to Accelerate Rare Disease Diagnosis. In: AMIA ... Annual Symposium proceedings. AMIA Symposium. 2017 ; Vol. 2017. pp. 1554-1563.
@article{1e0e4a62974d4844886cd70d26f9ad70,
title = "Leveraging Collaborative Filtering to Accelerate Rare Disease Diagnosis",
abstract = "In the USA, rare diseases are defined as those affecting fewer than 200,000 patients at any given time. Patients with rare diseases are frequently misdiagnosed or undiagnosed which may due to the lack of knowledge and experience of care providers. We hypothesize that patients' phenotypic information available in electronic medical records (EMR) can be leveraged to accelerate disease diagnosis based on the intuition that providers need to document associated phenotypic information to support the diagnosis decision, especially for rare diseases. In this study, we proposed a collaborative filtering system enriched with natural language processing and semantic techniques to assist rare disease diagnosis based on phenotypic characterization. Specifically, we leveraged four similarity measurements with two neighborhood algorithms on 2010-2015 Mayo Clinic unstructured large patient cohort and evaluated different approaches. Preliminary results demonstrated that the use of collaborative filtering with phenotypic information is able to stratify patients with relatively similar rare diseases.",
author = "Feichen Shen and Sijia Liu and Yanshan Wang and Liwei Wang and Naveed Afzal and Liu, {Hongfang D}",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
volume = "2017",
pages = "1554--1563",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Leveraging Collaborative Filtering to Accelerate Rare Disease Diagnosis

AU - Shen, Feichen

AU - Liu, Sijia

AU - Wang, Yanshan

AU - Wang, Liwei

AU - Afzal, Naveed

AU - Liu, Hongfang D

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In the USA, rare diseases are defined as those affecting fewer than 200,000 patients at any given time. Patients with rare diseases are frequently misdiagnosed or undiagnosed which may due to the lack of knowledge and experience of care providers. We hypothesize that patients' phenotypic information available in electronic medical records (EMR) can be leveraged to accelerate disease diagnosis based on the intuition that providers need to document associated phenotypic information to support the diagnosis decision, especially for rare diseases. In this study, we proposed a collaborative filtering system enriched with natural language processing and semantic techniques to assist rare disease diagnosis based on phenotypic characterization. Specifically, we leveraged four similarity measurements with two neighborhood algorithms on 2010-2015 Mayo Clinic unstructured large patient cohort and evaluated different approaches. Preliminary results demonstrated that the use of collaborative filtering with phenotypic information is able to stratify patients with relatively similar rare diseases.

AB - In the USA, rare diseases are defined as those affecting fewer than 200,000 patients at any given time. Patients with rare diseases are frequently misdiagnosed or undiagnosed which may due to the lack of knowledge and experience of care providers. We hypothesize that patients' phenotypic information available in electronic medical records (EMR) can be leveraged to accelerate disease diagnosis based on the intuition that providers need to document associated phenotypic information to support the diagnosis decision, especially for rare diseases. In this study, we proposed a collaborative filtering system enriched with natural language processing and semantic techniques to assist rare disease diagnosis based on phenotypic characterization. Specifically, we leveraged four similarity measurements with two neighborhood algorithms on 2010-2015 Mayo Clinic unstructured large patient cohort and evaluated different approaches. Preliminary results demonstrated that the use of collaborative filtering with phenotypic information is able to stratify patients with relatively similar rare diseases.

UR - http://www.scopus.com/inward/record.url?scp=85055256180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055256180&partnerID=8YFLogxK

M3 - Article

C2 - 29854225

AN - SCOPUS:85055256180

VL - 2017

SP - 1554

EP - 1563

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -