Counterfactual diagnosis
Machine learning promises to revolutionize clinical decision making and diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms by determining the diseases \emph{causing} them. However, existing diagnostic algorithms are purely associative, identifying diseases that are st...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Richens, Jonathan G Lee, Ciaran M Johri, Saurabh |
description | Machine learning promises to revolutionize clinical decision making and
diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms
by determining the diseases \emph{causing} them. However, existing diagnostic
algorithms are purely associative, identifying diseases that are strongly
correlated with a patients symptoms and medical history. We show that this
inability to disentangle correlation from causation can result in sub-optimal
or dangerous diagnoses. To overcome this, we reformulate diagnosis as a
counterfactual inference task and derive new counterfactual diagnostic
algorithms. We show that this approach is closer to the diagnostic reasoning of
clinicians and significantly improves the accuracy and safety of the resulting
diagnoses. We compare our counterfactual algorithm to the standard Bayesian
diagnostic algorithm and a cohort of 44 doctors using a test set of clinical
vignettes. While the Bayesian algorithm achieves an accuracy comparable to the
average doctor, placing in the top 48% of doctors in our cohort, our
counterfactual algorithm places in the top 25% of doctors, achieving expert
clinical accuracy. This improvement is achieved simply by changing how we query
our model, without requiring any additional model improvements. Our results
show that counterfactual reasoning is a vital missing ingredient for applying
machine learning to medical diagnosis. |
doi_str_mv | 10.48550/arxiv.1910.06772 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1910_06772</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1910_06772</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-e61a67fd81d2d938609440636f8934d9d0f8849d7156d0911bf87bf7d37d2a2a3</originalsourceid><addsrcrecordid>eNotzrkOgkAUheFpLAzaa6UvAM7GLKUhbomJDT25eBlDgmAGMPr2Ilr9ySlOPkKWjEbSxDHdgH-Vz4jZYaBKaz4li6Tp667wDq5dD9UaS7jVTVu2MzJxULXF_N-ApPtdmhzD8-VwSrbnEJTmYaHYUIeGIUcrjKJWSqqEcsYKiRapM0Za1CxWSC1juTM6dxqFRg4cREBWv9uRlj18eQf_zr7EbCSKD4byNKU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Counterfactual diagnosis</title><source>arXiv.org</source><creator>Richens, Jonathan G ; Lee, Ciaran M ; Johri, Saurabh</creator><creatorcontrib>Richens, Jonathan G ; Lee, Ciaran M ; Johri, Saurabh</creatorcontrib><description>Machine learning promises to revolutionize clinical decision making and
diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms
by determining the diseases \emph{causing} them. However, existing diagnostic
algorithms are purely associative, identifying diseases that are strongly
correlated with a patients symptoms and medical history. We show that this
inability to disentangle correlation from causation can result in sub-optimal
or dangerous diagnoses. To overcome this, we reformulate diagnosis as a
counterfactual inference task and derive new counterfactual diagnostic
algorithms. We show that this approach is closer to the diagnostic reasoning of
clinicians and significantly improves the accuracy and safety of the resulting
diagnoses. We compare our counterfactual algorithm to the standard Bayesian
diagnostic algorithm and a cohort of 44 doctors using a test set of clinical
vignettes. While the Bayesian algorithm achieves an accuracy comparable to the
average doctor, placing in the top 48% of doctors in our cohort, our
counterfactual algorithm places in the top 25% of doctors, achieving expert
clinical accuracy. This improvement is achieved simply by changing how we query
our model, without requiring any additional model improvements. Our results
show that counterfactual reasoning is a vital missing ingredient for applying
machine learning to medical diagnosis.</description><identifier>DOI: 10.48550/arxiv.1910.06772</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2019-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1910.06772$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1910.06772$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Richens, Jonathan G</creatorcontrib><creatorcontrib>Lee, Ciaran M</creatorcontrib><creatorcontrib>Johri, Saurabh</creatorcontrib><title>Counterfactual diagnosis</title><description>Machine learning promises to revolutionize clinical decision making and
diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms
by determining the diseases \emph{causing} them. However, existing diagnostic
algorithms are purely associative, identifying diseases that are strongly
correlated with a patients symptoms and medical history. We show that this
inability to disentangle correlation from causation can result in sub-optimal
or dangerous diagnoses. To overcome this, we reformulate diagnosis as a
counterfactual inference task and derive new counterfactual diagnostic
algorithms. We show that this approach is closer to the diagnostic reasoning of
clinicians and significantly improves the accuracy and safety of the resulting
diagnoses. We compare our counterfactual algorithm to the standard Bayesian
diagnostic algorithm and a cohort of 44 doctors using a test set of clinical
vignettes. While the Bayesian algorithm achieves an accuracy comparable to the
average doctor, placing in the top 48% of doctors in our cohort, our
counterfactual algorithm places in the top 25% of doctors, achieving expert
clinical accuracy. This improvement is achieved simply by changing how we query
our model, without requiring any additional model improvements. Our results
show that counterfactual reasoning is a vital missing ingredient for applying
machine learning to medical diagnosis.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrkOgkAUheFpLAzaa6UvAM7GLKUhbomJDT25eBlDgmAGMPr2Ilr9ySlOPkKWjEbSxDHdgH-Vz4jZYaBKaz4li6Tp667wDq5dD9UaS7jVTVu2MzJxULXF_N-ApPtdmhzD8-VwSrbnEJTmYaHYUIeGIUcrjKJWSqqEcsYKiRapM0Za1CxWSC1juTM6dxqFRg4cREBWv9uRlj18eQf_zr7EbCSKD4byNKU</recordid><startdate>20191015</startdate><enddate>20191015</enddate><creator>Richens, Jonathan G</creator><creator>Lee, Ciaran M</creator><creator>Johri, Saurabh</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20191015</creationdate><title>Counterfactual diagnosis</title><author>Richens, Jonathan G ; Lee, Ciaran M ; Johri, Saurabh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-e61a67fd81d2d938609440636f8934d9d0f8849d7156d0911bf87bf7d37d2a2a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Richens, Jonathan G</creatorcontrib><creatorcontrib>Lee, Ciaran M</creatorcontrib><creatorcontrib>Johri, Saurabh</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Richens, Jonathan G</au><au>Lee, Ciaran M</au><au>Johri, Saurabh</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Counterfactual diagnosis</atitle><date>2019-10-15</date><risdate>2019</risdate><abstract>Machine learning promises to revolutionize clinical decision making and
diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms
by determining the diseases \emph{causing} them. However, existing diagnostic
algorithms are purely associative, identifying diseases that are strongly
correlated with a patients symptoms and medical history. We show that this
inability to disentangle correlation from causation can result in sub-optimal
or dangerous diagnoses. To overcome this, we reformulate diagnosis as a
counterfactual inference task and derive new counterfactual diagnostic
algorithms. We show that this approach is closer to the diagnostic reasoning of
clinicians and significantly improves the accuracy and safety of the resulting
diagnoses. We compare our counterfactual algorithm to the standard Bayesian
diagnostic algorithm and a cohort of 44 doctors using a test set of clinical
vignettes. While the Bayesian algorithm achieves an accuracy comparable to the
average doctor, placing in the top 48% of doctors in our cohort, our
counterfactual algorithm places in the top 25% of doctors, achieving expert
clinical accuracy. This improvement is achieved simply by changing how we query
our model, without requiring any additional model improvements. Our results
show that counterfactual reasoning is a vital missing ingredient for applying
machine learning to medical diagnosis.</abstract><doi>10.48550/arxiv.1910.06772</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.1910.06772 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_1910_06772 |
source | arXiv.org |
subjects | Computer Science - Artificial Intelligence Computer Science - Learning Statistics - Machine Learning |
title | Counterfactual diagnosis |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T23%3A35%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Counterfactual%20diagnosis&rft.au=Richens,%20Jonathan%20G&rft.date=2019-10-15&rft_id=info:doi/10.48550/arxiv.1910.06772&rft_dat=%3Carxiv_GOX%3E1910_06772%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |