Machine learning helps to tackle long COVID

Credit: Unsplash/CC0 Public Domain

A new machine learning tool is here to help.

Developed by a team of researchers from institutions across the country, led by Justin Reese of Berkeley Lab and Peter Robinson of Jackson Lab, the software analyzes entries in electronic health records (EHRs) to find symptoms in common between people who have been diagnosed with long COVID and to define subtypes of the condition. The research, which is described in a new paper in eBioMedicine, also identifies strong correlations between different long COVID subtypes and pre-existing conditions such as diabetes and hypertension.

According to Reese, a computer research scientist in Berkeley Lab’s Biosciences Area, this research will help improve our understanding of how and why some individuals develop long COVID symptoms, and may enable more effective treatments by helping clinicians develop tailored therapies for each group. For example, the best treatment for patients experiencing nausea and abdominal pain might be quite different from a treatment for those suffering from persistent cough and other lung symptoms.

The team developed and validated their software using a database of EHR information from 6,469 patients diagnosed with long COVID after confirmed COVID-19 infections. “Basically, we found long COVID features in the EHR data for each long COVID patient, and then assessed patient-patient similarity using semantic similarity, which essentially allows ‘fuzzy matching’ between features—for example, ‘cough’ is not the same as ‘shortness of breath,’ but they are similar since they both involve lung problems,” Reese said. “We compare all symptoms for the pair of the patients in this way, and get a score of how similar the two long COVID patients are. We can then perform unsupervised machine learning on these scores to find different subtypes of long COVID.”

The researchers applied machine learning to these patient-patient similarity scores to cluster patients into groups, which were then characterized by analyzing relationships between symptoms and pre-existing diseases and other demographic features, such as age, gender, or race.

Reese and his colleagues note that the tool will be convenient for researchers because the machine learning approach at its core self-adapts for different EHR systems, allowing researchers to gather data from a wide variety of medical establishments.

This research builds on previous work to develop the Human Phenotype Ontology, an open-access database and research tool that provides a standardized vocabulary of symptoms and features found in all human diseases.

More information:
Justin T. Reese et al, Generalisable long COVID subtypes: Findings from the NIH N3C and RECOVER programmes, eBioMedicine (2022). DOI: 10.1016/j.ebiom.2022.104413

Provided by
Lawrence Berkeley National Laboratory

Citation:
Machine learning helps to tackle long COVID (2023, January 5)
retrieved 5 January 2023
from https://medicalxpress.com/news/2023-01-machine-tackle-covid.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.

lisa1 lisa2 lisa3 lisa4 lisa5 lisa6 lisa7 lisa8 lisa9 lisa10 lisa11 lisa12 lisa13 lisa14 lisa15 lisa16 lisa17 lisa18 lisa19 lisa20 lisa21 lisa22 lisa23 lisa24 lisa25 lisa26 lisa27 lisa28 lisa29 lisa30 lisa31 lisa32 lisa33 lisa34 lisa35 lisa36 lisa37 lisa38 lisa39 lisa40 lisa41 lisa42 lisa43 lisa44 lisa45 lisa46 lisa47 lisa48 lisa49 lisa50 lisa51 lisa52 lisa53 lisa54 lisa55 lisa56 lisa57 lisa58 lisa59 lisa60 lisa61 lisa62 lisa63 lisa64 lisa65 lisa66 lisa67 lisa68 lisa69 lisa70 lisa71 lisa72 lisa73 lisa74 lisa75 lisa76 lisa77 lisa78 lisa79 lisa80 lisa81 lisa82 lisa83 lisa84 lisa85 lisa86 lisa87 lisa88 lisa89 lisa90 lisa91 lisa92 lisa93 lisa94 lisa95 lisa96 lisa97 lisa98 lisa99 lisa100 lisa101 lisa102 lisa103 lisa104 lisa105 lisa106 lisa107 lisa108 lisa109 lisa110 lisa111 lisa112 lisa113 lisa114 lisa115 lisa116 lisa117 lisa118 lisa119 lisa120 lisa121 lisa122 lisa123 lisa124 lisa125 lisa126 lisa127 lisa128 lisa129 lisa130 lisa131 lisa132 lisa133 lisa134 lisa135 lisa136 lisa137 lisa138 lisa139 lisa140 lisa141 lisa142 lisa143 lisa144 lisa145 lisa146 lisa147 lisa148 lisa149 lisa150 lisa151 lisa152 lisa153 lisa154 lisa155 lisa156 lisa157 lisa158 lisa159 lisa160 lisa161 lisa162 lisa163 lisa164 lisa165 lisa166 lisa167 lisa168 lisa169 lisa170 lisa171 lisa172 lisa173 lisa174 lisa175 lisa176 lisa177 lisa178 lisa179 lisa180 lisa181 lisa182 lisa183 lisa184 lisa185 lisa186 lisa187 lisa188 lisa189 lisa190 lisa191 lisa192 lisa193 lisa194 lisa195 lisa196 lisa197 lisa198 lisa199 lisa200 lisa201 lisa202 lisa203 lisa204 lisa205 lisa206 lisa207 lisa208 lisa209 lisa210

NewToNews

Machine learning helps to tackle long COVID

Byolaksjl

By olaksjl

Related Post

Risk for acute myocardial infarction increased for patients with pneumonia

Transplant from deceased donor with brain tumor appears to be safe

Largest study to date of minipuberty identifies two new patterns of the reproductive hormone, AMH, in infant girls

Leave a Reply Cancel reply

You missed

Risk for acute myocardial infarction increased for patients with pneumonia

Transplant from deceased donor with brain tumor appears to be safe

Peanut consumption could have a beneficial impact on vascular health in young and healthy people

LinkUP intervention improves COVID-19 testing, vaccination referral rates among PWID

NewToNews