Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis

The global burden of multimorbidity is increasing yet poorly understood, owing to insufficient methods for modelling complex systems of conditions. In particular, hepatosplenic multimorbidity has been inadequately investigated. From 17 January to 16 February 2023, we examined 3186 individuals aged 5...

Full description

Saved in:
Bibliographic Details
Main Authors: Yin-Cong Zhi, Simon Mpooya, Narcis B. Kabatereine, Betty Nabatte, Christopher K. Opio, Goylette F. Chami
Format: Article
Language:English
Published: The Royal Society 2025-07-01
Series:Royal Society Open Science
Subjects:
Online Access:https://royalsocietypublishing.org/doi/10.1098/rsos.242256
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717305216335872
author Yin-Cong Zhi
Simon Mpooya
Narcis B. Kabatereine
Betty Nabatte
Christopher K. Opio
Goylette F. Chami
author_facet Yin-Cong Zhi
Simon Mpooya
Narcis B. Kabatereine
Betty Nabatte
Christopher K. Opio
Goylette F. Chami
author_sort Yin-Cong Zhi
collection DOAJ
description The global burden of multimorbidity is increasing yet poorly understood, owing to insufficient methods for modelling complex systems of conditions. In particular, hepatosplenic multimorbidity has been inadequately investigated. From 17 January to 16 February 2023, we examined 3186 individuals aged 5–92 years from 52 villages across Uganda within the SchistoTrack Cohort. Point-of-care B-mode ultrasound was used to assess 45 hepatosplenic conditions within the context of schistosomiasis (Schistosoma mansoni). Three graph learning methods for representing hepatosplenic multimorbidity were compared. Thresholds for including graph edges were found using graph kernels and tested with graph neural networks to assess predictive utility for unobserved conditions. Clinical validity was assessed by identifying medically relevant condition inter-dependencies for portal hypertension. 54.65% (1741/3186) of individuals were multimorbid with two or more hepatosplenic conditions. Thresholds were 50.16 and 64.46% for graphical lasso and signed distance correlation, respectively, but could not be inferred for co-occurrence. Co-occurrence graphs were clinically uninformative with low predictive capacity. Graph learning algorithms with statistical assumptions, e.g. graphical lasso, enabled accurate and clinically valid multimorbidity representations. Severe conditions related to portal hypertension were predicted with high sensitivity and specificity. This work presents a generalizable framework for understanding multimorbidity to enable more accurate diagnoses of complex diseases.
format Article
id doaj-art-dba6a92695c440be944b47ffb72d0865
institution DOAJ
issn 2054-5703
language English
publishDate 2025-07-01
publisher The Royal Society
record_format Article
series Royal Society Open Science
spelling doaj-art-dba6a92695c440be944b47ffb72d08652025-08-20T03:12:42ZengThe Royal SocietyRoyal Society Open Science2054-57032025-07-0112710.1098/rsos.242256Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasisYin-Cong Zhi0Simon Mpooya1Narcis B. Kabatereine2Betty Nabatte3Christopher K. Opio4Goylette F. Chami5Big Data Institute, Nuffield Department of Population Health, Oxford, UKRepublic of Uganda Ministry of Health, Kampala, Central Region, UgandaRepublic of Uganda Ministry of Health, Kampala, Central Region, UgandaRepublic of Uganda Ministry of Health, Kampala, Central Region, UgandaThe Aga Khan University Hospital Nairobi, Nairobi, Nairobi County, KenyaBig Data Institute, Nuffield Department of Population Health, Oxford, UKThe global burden of multimorbidity is increasing yet poorly understood, owing to insufficient methods for modelling complex systems of conditions. In particular, hepatosplenic multimorbidity has been inadequately investigated. From 17 January to 16 February 2023, we examined 3186 individuals aged 5–92 years from 52 villages across Uganda within the SchistoTrack Cohort. Point-of-care B-mode ultrasound was used to assess 45 hepatosplenic conditions within the context of schistosomiasis (Schistosoma mansoni). Three graph learning methods for representing hepatosplenic multimorbidity were compared. Thresholds for including graph edges were found using graph kernels and tested with graph neural networks to assess predictive utility for unobserved conditions. Clinical validity was assessed by identifying medically relevant condition inter-dependencies for portal hypertension. 54.65% (1741/3186) of individuals were multimorbid with two or more hepatosplenic conditions. Thresholds were 50.16 and 64.46% for graphical lasso and signed distance correlation, respectively, but could not be inferred for co-occurrence. Co-occurrence graphs were clinically uninformative with low predictive capacity. Graph learning algorithms with statistical assumptions, e.g. graphical lasso, enabled accurate and clinically valid multimorbidity representations. Severe conditions related to portal hypertension were predicted with high sensitivity and specificity. This work presents a generalizable framework for understanding multimorbidity to enable more accurate diagnoses of complex diseases.https://royalsocietypublishing.org/doi/10.1098/rsos.242256complex networkschistosomiasisportal hypertensionthresholdgraph neural networkhepatosplenic
spellingShingle Yin-Cong Zhi
Simon Mpooya
Narcis B. Kabatereine
Betty Nabatte
Christopher K. Opio
Goylette F. Chami
Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis
Royal Society Open Science
complex network
schistosomiasis
portal hypertension
threshold
graph neural network
hepatosplenic
title Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis
title_full Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis
title_fullStr Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis
title_full_unstemmed Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis
title_short Clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis
title_sort clinically validated graphical approaches identify hepatosplenic multimorbidity in individuals at risk of schistosomiasis
topic complex network
schistosomiasis
portal hypertension
threshold
graph neural network
hepatosplenic
url https://royalsocietypublishing.org/doi/10.1098/rsos.242256
work_keys_str_mv AT yincongzhi clinicallyvalidatedgraphicalapproachesidentifyhepatosplenicmultimorbidityinindividualsatriskofschistosomiasis
AT simonmpooya clinicallyvalidatedgraphicalapproachesidentifyhepatosplenicmultimorbidityinindividualsatriskofschistosomiasis
AT narcisbkabatereine clinicallyvalidatedgraphicalapproachesidentifyhepatosplenicmultimorbidityinindividualsatriskofschistosomiasis
AT bettynabatte clinicallyvalidatedgraphicalapproachesidentifyhepatosplenicmultimorbidityinindividualsatriskofschistosomiasis
AT christopherkopio clinicallyvalidatedgraphicalapproachesidentifyhepatosplenicmultimorbidityinindividualsatriskofschistosomiasis
AT goylettefchami clinicallyvalidatedgraphicalapproachesidentifyhepatosplenicmultimorbidityinindividualsatriskofschistosomiasis