Metrics to guide development of machine learning algorithms for malaria diagnosis

Automated malaria diagnosis is a difficult but high-value target for machine learning (ML), and effective algorithms could save many thousands of children's lives. However, current ML efforts largely neglect crucial use case constraints and are thus not clinically useful. Two factors in particu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Delahunt, Charles B, Gachuhi, Noni, Horning, Matthew P
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 Delahunt, Charles B
Gachuhi, Noni
Horning, Matthew P
description Automated malaria diagnosis is a difficult but high-value target for machine learning (ML), and effective algorithms could save many thousands of children's lives. However, current ML efforts largely neglect crucial use case constraints and are thus not clinically useful. Two factors in particular are crucial to developing algorithms translatable to clinical field settings: (i) Clear understanding of the clinical needs that ML solutions must accommodate; and (ii) task-relevant metrics for guiding and evaluating ML models. Neglect of these factors has seriously hampered past ML work on malaria, because the resulting algorithms do not align with clinical needs. In this paper we address these two issues in the context of automated malaria diagnosis via microscopy on Giemsa-stained blood films. First, we describe why domain expertise is crucial to effectively apply ML to malaria, and list technical documents and other resources that provide this domain knowledge. Second, we detail performance metrics tailored to the clinical requirements of malaria diagnosis, to guide development of ML models and evaluate model performance through the lens of clinical needs (versus a generic ML lens). We highlight the importance of a patient-level perspective, interpatient variability, false positive rates, limit of detection, and different types of error. We also discuss reasons why ROC curves, AUC, and F1, as commonly used in ML work, are poorly suited to this context. These findings also apply to other diseases involving parasite loads, including neglected tropical diseases (NTDs) such as schistosomiasis.
doi_str_mv 10.48550/arxiv.2209.06947
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2209_06947</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2209_06947</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-c9c621b78258125019b0976a034cb2c2ae04f69d7d6052f525cee3d8cc90659f3</originalsourceid><addsrcrecordid>eNotz81KxDAUhuFsXMjoBbgyN9B6mjZJs5TBPxgRYfblNDnpBNJkSOugd6-Orr7FCx88jN00UHe9lHCH5TOcaiHA1KBMpy_Z-yutJdiFr5lPH8ERd3SimI8zpZVnz2e0h5CIR8KSQpo4ximXsB7mhftcfnrEEpC7gFPKS1iu2IXHuND1_27Y_vFhv32udm9PL9v7XYVK68oaq0Qz6l7IvhESGjOC0Qqh7eworECCzivjtFMghZdCWqLW9dYaUNL4dsNu_27PpuFYwozla_i1DWdb-w3c10od</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Metrics to guide development of machine learning algorithms for malaria diagnosis</title><source>arXiv.org</source><creator>Delahunt, Charles B ; Gachuhi, Noni ; Horning, Matthew P</creator><creatorcontrib>Delahunt, Charles B ; Gachuhi, Noni ; Horning, Matthew P</creatorcontrib><description>Automated malaria diagnosis is a difficult but high-value target for machine learning (ML), and effective algorithms could save many thousands of children's lives. However, current ML efforts largely neglect crucial use case constraints and are thus not clinically useful. Two factors in particular are crucial to developing algorithms translatable to clinical field settings: (i) Clear understanding of the clinical needs that ML solutions must accommodate; and (ii) task-relevant metrics for guiding and evaluating ML models. Neglect of these factors has seriously hampered past ML work on malaria, because the resulting algorithms do not align with clinical needs. In this paper we address these two issues in the context of automated malaria diagnosis via microscopy on Giemsa-stained blood films. First, we describe why domain expertise is crucial to effectively apply ML to malaria, and list technical documents and other resources that provide this domain knowledge. Second, we detail performance metrics tailored to the clinical requirements of malaria diagnosis, to guide development of ML models and evaluate model performance through the lens of clinical needs (versus a generic ML lens). We highlight the importance of a patient-level perspective, interpatient variability, false positive rates, limit of detection, and different types of error. We also discuss reasons why ROC curves, AUC, and F1, as commonly used in ML work, are poorly suited to this context. These findings also apply to other diseases involving parasite loads, including neglected tropical diseases (NTDs) such as schistosomiasis.</description><identifier>DOI: 10.48550/arxiv.2209.06947</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2022-09</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/2209.06947$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2209.06947$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Delahunt, Charles B</creatorcontrib><creatorcontrib>Gachuhi, Noni</creatorcontrib><creatorcontrib>Horning, Matthew P</creatorcontrib><title>Metrics to guide development of machine learning algorithms for malaria diagnosis</title><description>Automated malaria diagnosis is a difficult but high-value target for machine learning (ML), and effective algorithms could save many thousands of children's lives. However, current ML efforts largely neglect crucial use case constraints and are thus not clinically useful. Two factors in particular are crucial to developing algorithms translatable to clinical field settings: (i) Clear understanding of the clinical needs that ML solutions must accommodate; and (ii) task-relevant metrics for guiding and evaluating ML models. Neglect of these factors has seriously hampered past ML work on malaria, because the resulting algorithms do not align with clinical needs. In this paper we address these two issues in the context of automated malaria diagnosis via microscopy on Giemsa-stained blood films. First, we describe why domain expertise is crucial to effectively apply ML to malaria, and list technical documents and other resources that provide this domain knowledge. Second, we detail performance metrics tailored to the clinical requirements of malaria diagnosis, to guide development of ML models and evaluate model performance through the lens of clinical needs (versus a generic ML lens). We highlight the importance of a patient-level perspective, interpatient variability, false positive rates, limit of detection, and different types of error. We also discuss reasons why ROC curves, AUC, and F1, as commonly used in ML work, are poorly suited to this context. These findings also apply to other diseases involving parasite loads, including neglected tropical diseases (NTDs) such as schistosomiasis.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81KxDAUhuFsXMjoBbgyN9B6mjZJs5TBPxgRYfblNDnpBNJkSOugd6-Orr7FCx88jN00UHe9lHCH5TOcaiHA1KBMpy_Z-yutJdiFr5lPH8ERd3SimI8zpZVnz2e0h5CIR8KSQpo4ximXsB7mhftcfnrEEpC7gFPKS1iu2IXHuND1_27Y_vFhv32udm9PL9v7XYVK68oaq0Qz6l7IvhESGjOC0Qqh7eworECCzivjtFMghZdCWqLW9dYaUNL4dsNu_27PpuFYwozla_i1DWdb-w3c10od</recordid><startdate>20220914</startdate><enddate>20220914</enddate><creator>Delahunt, Charles B</creator><creator>Gachuhi, Noni</creator><creator>Horning, Matthew P</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220914</creationdate><title>Metrics to guide development of machine learning algorithms for malaria diagnosis</title><author>Delahunt, Charles B ; Gachuhi, Noni ; Horning, Matthew P</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-c9c621b78258125019b0976a034cb2c2ae04f69d7d6052f525cee3d8cc90659f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Delahunt, Charles B</creatorcontrib><creatorcontrib>Gachuhi, Noni</creatorcontrib><creatorcontrib>Horning, Matthew P</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Delahunt, Charles B</au><au>Gachuhi, Noni</au><au>Horning, Matthew P</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Metrics to guide development of machine learning algorithms for malaria diagnosis</atitle><date>2022-09-14</date><risdate>2022</risdate><abstract>Automated malaria diagnosis is a difficult but high-value target for machine learning (ML), and effective algorithms could save many thousands of children's lives. However, current ML efforts largely neglect crucial use case constraints and are thus not clinically useful. Two factors in particular are crucial to developing algorithms translatable to clinical field settings: (i) Clear understanding of the clinical needs that ML solutions must accommodate; and (ii) task-relevant metrics for guiding and evaluating ML models. Neglect of these factors has seriously hampered past ML work on malaria, because the resulting algorithms do not align with clinical needs. In this paper we address these two issues in the context of automated malaria diagnosis via microscopy on Giemsa-stained blood films. First, we describe why domain expertise is crucial to effectively apply ML to malaria, and list technical documents and other resources that provide this domain knowledge. Second, we detail performance metrics tailored to the clinical requirements of malaria diagnosis, to guide development of ML models and evaluate model performance through the lens of clinical needs (versus a generic ML lens). We highlight the importance of a patient-level perspective, interpatient variability, false positive rates, limit of detection, and different types of error. We also discuss reasons why ROC curves, AUC, and F1, as commonly used in ML work, are poorly suited to this context. These findings also apply to other diseases involving parasite loads, including neglected tropical diseases (NTDs) such as schistosomiasis.</abstract><doi>10.48550/arxiv.2209.06947</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2209.06947
ispartof
issn
language eng
recordid cdi_arxiv_primary_2209_06947
source arXiv.org
subjects Computer Science - Learning
title Metrics to guide development of machine learning algorithms for malaria diagnosis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T20%3A55%3A38IST&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=Metrics%20to%20guide%20development%20of%20machine%20learning%20algorithms%20for%20malaria%20diagnosis&rft.au=Delahunt,%20Charles%20B&rft.date=2022-09-14&rft_id=info:doi/10.48550/arxiv.2209.06947&rft_dat=%3Carxiv_GOX%3E2209_06947%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