Rare disease diagnosis: A review of web search, social media and large-scale data-mining approaches

Dan Tito Svenstrup, Henrik L Jørgensen, Ole Winther

Research output: Contribution to journalJournal articleResearchpeer-review

280 Downloads (Pure)

Abstract

Physicians and the general public are increasingly using web-based tools to find answers to medical questions. The field of rare diseases is especially challenging and important as shown by the long delay and many mistakes associated with diagnoses. In this paper we review recent initiatives on the use of web search, social media and data mining in data repositories for medical diagnosis. We compare the retrieval accuracy on 56 rare disease cases with known diagnosis for the web search tools google.com, pubmed.gov, omim.org and our own search tool findzebra.com. We give a detailed description of IBM's Watson system and make a rough comparison between findzebra.com and Watson on subsets of the Doctor's dilemma dataset. The recall@10 and recall@20 (fraction of cases where the correct result appears in top 10 and top 20) for the 56 cases are found to be be 29%, 16%, 27% and 59% and 32%, 18%, 34% and 64%, respectively. Thus, FindZebra has a significantly (p <0.01) higher recall than the other 3 search engines. When tested under the same conditions, Watson and FindZebra showed similar recall@10 accuracy. However, the tests were performed on different subsets of Doctors dilemma questions. Advances in technology and access to high quality data have opened new possibilities for aiding the diagnostic process. Specialized search engines, data mining tools and social media are some of the areas that hold promise.
Original languageEnglish
Article numbere1083145
JournalRare Diseases (Online)
Volume3
Issue number1
Number of pages7
ISSN2167-5511
DOIs
Publication statusPublished - 2015

Keywords

  • clinical diagnosis decision support systems
  • data mining
  • information retrieval
  • machine learning
  • rare diseases
  • search engines

Cite this

@article{3bb7e78de8b94c5e8583a5274bed616d,
title = "Rare disease diagnosis: A review of web search, social media and large-scale data-mining approaches",
abstract = "Physicians and the general public are increasingly using web-based tools to find answers to medical questions. The field of rare diseases is especially challenging and important as shown by the long delay and many mistakes associated with diagnoses. In this paper we review recent initiatives on the use of web search, social media and data mining in data repositories for medical diagnosis. We compare the retrieval accuracy on 56 rare disease cases with known diagnosis for the web search tools google.com, pubmed.gov, omim.org and our own search tool findzebra.com. We give a detailed description of IBM's Watson system and make a rough comparison between findzebra.com and Watson on subsets of the Doctor's dilemma dataset. The recall@10 and recall@20 (fraction of cases where the correct result appears in top 10 and top 20) for the 56 cases are found to be be 29{\%}, 16{\%}, 27{\%} and 59{\%} and 32{\%}, 18{\%}, 34{\%} and 64{\%}, respectively. Thus, FindZebra has a significantly (p <0.01) higher recall than the other 3 search engines. When tested under the same conditions, Watson and FindZebra showed similar recall@10 accuracy. However, the tests were performed on different subsets of Doctors dilemma questions. Advances in technology and access to high quality data have opened new possibilities for aiding the diagnostic process. Specialized search engines, data mining tools and social media are some of the areas that hold promise.",
keywords = "clinical diagnosis decision support systems, data mining, information retrieval, machine learning, rare diseases, search engines",
author = "Svenstrup, {Dan Tito} and J{\o}rgensen, {Henrik L} and Ole Winther",
year = "2015",
doi = "10.1080/21675511.2015.1083145",
language = "English",
volume = "3",
journal = "Rare Diseases (Online)",
issn = "2167-5511",
publisher = "Taylor & Francis Inc.",
number = "1",

}

Rare disease diagnosis: A review of web search, social media and large-scale data-mining approaches. / Svenstrup, Dan Tito; Jørgensen, Henrik L; Winther, Ole.

In: Rare Diseases (Online), Vol. 3, No. 1, e1083145, 2015.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Rare disease diagnosis: A review of web search, social media and large-scale data-mining approaches

AU - Svenstrup, Dan Tito

AU - Jørgensen, Henrik L

AU - Winther, Ole

PY - 2015

Y1 - 2015

N2 - Physicians and the general public are increasingly using web-based tools to find answers to medical questions. The field of rare diseases is especially challenging and important as shown by the long delay and many mistakes associated with diagnoses. In this paper we review recent initiatives on the use of web search, social media and data mining in data repositories for medical diagnosis. We compare the retrieval accuracy on 56 rare disease cases with known diagnosis for the web search tools google.com, pubmed.gov, omim.org and our own search tool findzebra.com. We give a detailed description of IBM's Watson system and make a rough comparison between findzebra.com and Watson on subsets of the Doctor's dilemma dataset. The recall@10 and recall@20 (fraction of cases where the correct result appears in top 10 and top 20) for the 56 cases are found to be be 29%, 16%, 27% and 59% and 32%, 18%, 34% and 64%, respectively. Thus, FindZebra has a significantly (p <0.01) higher recall than the other 3 search engines. When tested under the same conditions, Watson and FindZebra showed similar recall@10 accuracy. However, the tests were performed on different subsets of Doctors dilemma questions. Advances in technology and access to high quality data have opened new possibilities for aiding the diagnostic process. Specialized search engines, data mining tools and social media are some of the areas that hold promise.

AB - Physicians and the general public are increasingly using web-based tools to find answers to medical questions. The field of rare diseases is especially challenging and important as shown by the long delay and many mistakes associated with diagnoses. In this paper we review recent initiatives on the use of web search, social media and data mining in data repositories for medical diagnosis. We compare the retrieval accuracy on 56 rare disease cases with known diagnosis for the web search tools google.com, pubmed.gov, omim.org and our own search tool findzebra.com. We give a detailed description of IBM's Watson system and make a rough comparison between findzebra.com and Watson on subsets of the Doctor's dilemma dataset. The recall@10 and recall@20 (fraction of cases where the correct result appears in top 10 and top 20) for the 56 cases are found to be be 29%, 16%, 27% and 59% and 32%, 18%, 34% and 64%, respectively. Thus, FindZebra has a significantly (p <0.01) higher recall than the other 3 search engines. When tested under the same conditions, Watson and FindZebra showed similar recall@10 accuracy. However, the tests were performed on different subsets of Doctors dilemma questions. Advances in technology and access to high quality data have opened new possibilities for aiding the diagnostic process. Specialized search engines, data mining tools and social media are some of the areas that hold promise.

KW - clinical diagnosis decision support systems

KW - data mining

KW - information retrieval

KW - machine learning

KW - rare diseases

KW - search engines

U2 - 10.1080/21675511.2015.1083145

DO - 10.1080/21675511.2015.1083145

M3 - Journal article

VL - 3

JO - Rare Diseases (Online)

JF - Rare Diseases (Online)

SN - 2167-5511

IS - 1

M1 - e1083145

ER -