In a recent preprint study posted to Preprints with The Lancet*, a team of researchers evaluated the usage of prediction models together with clinical information, metatranscriptomics, and lower respiratory tract microbiome.
Their results suggest that machine learning models may change into a rapid diagnosis tool, circumventing morbidity and mortality related to conventional microbiological testing.
Study: Integrating Respiratory Microbiome and Host Immune Response Using Machine Learning for Diagnosis of the Lower Respiratory Tract Infections. Image Credit: MZinchenko/Shutterstock.com
*Essential notice: SSRN publishes preliminary scientific reports that will not be peer-reviewed and, due to this fact, mustn’t be considered conclusive, guide clinical practice/health-related behavior, or treated as established information.
LRTI diagnosis
Lower respiratory tract infections (LRTIs) are accountable for over 3 million deaths per 12 months, making them certainly one of the leading infectious causes of human mortality globally. The high morbidity and mortality of LRTIs have historically been attributed to standard respiratory infection diagnosis. Traditional diagnosis lacks sensitivity, cannot discover 60-70% of causative agents, and takes 24-48 hours or more for infection characterization.
LRTIs are known to exhibit extreme variety and variability of their symptomatic presentation, lots of which overlap with non-infectious conditions like asthma, chronic obstructive pulmonary disease (COPD), or cystic fibrosis. Clinicians hence prefer to delay their diagnosis of a patient or risk disease misdiagnosis, each of which may very well be life-threatening.
Recent studies challenge the classical view of LRTI pathogenesis – traditional knowledge assumes that the lungs are initially sterile. It takes a critical volume of pathogenic microbes invading the lungs to overwhelm the immune response, leading to rapid infection.
A growing body of research using microbial genomes proposes that LRTIs originate as a consequence of a mixture of low microbial species diversity, high overall biomass, and host inflammation response.
Alternations in respiratory tract microbiomes have also been observed in non-infectious diseases like asthma, flagging microbiome studies as critical in LRTI identification and characterization. An emerging field, metagenomic next-generation sequencing (mNGS) is being tested as a viable, rapid, and sensitive alternative to traditional diagnosis tools.
mNGS requires microlitre volumes of patient samples and will yield accurate diagnoses in minutes to hours versus the times that conventional diagnostic tools currently take.
In regards to the study
In the current preprint study, researchers attempted to collate and mix respiratory microbiome and host transcriptional profiling with clinical data. They then trained a machine-learning model and tested its diagnostic speed and accuracy when fed with the collated data.
Researchers began by enrolling patients suspected to have LRTIs from the Peking University People’s Hospital, Beijing, between May 2020 and January 2021. After screening for radiography, clinical presentation, and demographic characters in keeping with the US Centers for Disease Control/National Healthcare Safety Network (CDC/NHSN), 136 participants were chosen for the study.
All participants received traditional microbiological and serological testing for LRTI diagnosis. Researchers moreover collected bronchoalveolar lavage fluid (BALF) for characterization and model training. BALF was sequenced for each DNA and RNA. RNA reads were screened against the human transcriptome and against the SILVA rRNA database to make sure that the remaining reads belonged to the lung microbiome.
Host transcriptome and microbiome were correlated and standardized by comparing transcripts per million (TMP) expression in hosts to the relative concentration of microbial flora. This data was then used to coach machine learning models.
Researchers vetted 11 identifying variables from clinical indicators, microbial flora abundance, and host TMP upregulation. Random forest models were utilized, using 91 participants’ data for algorithm training and 45 for testing.
Study findings
Of the 136 patients enrolled within the study, 81 were found to have LRTIs and formed the LRTI cohort, while the remainder 55 were placed within the non-LRTI cohort. LRTI-positive individuals were found to have a significantly higher quantity of prior antibiotic use in comparison with their non-LRTI counterparts.
Notably, laboratory findings, including white blood cell (WBC) count and inflammation indicators, didn’t differ between the 2 groups. This highlights the low characterization power of conventional diagnostic tools.
Patients were LRTIs were found to have significantly reduced BALF microbiota diversity in comparison with non-LRTI samples. The relative abundance of microbiota was also different between the groups, with BALF of LRTI samples depicting the high abundance of pathogenic Klebsiella pneumoniae, Stenotrophomonas maltophilia, Pseudomonas aeruginosa, and Streptococcus pneumoniae.
In contrast, BALF of the non-LRTI group showed the best abundance of Halomonas pacifica, a symbiont ordinarily present in healthy lungs and respiratory tracts. The pathogenic microbes within the LRTI samples were either absent or present in trace quantities within the non-LRTI group.
Transcriptome analyses revealed 674 differentially expressed genes (DEGs). Of those, BALF of the LRTI cohort revealed that 613 DEGs were up-regulated, while the remaining 61 were down-regulated in comparison with the non-LRTI cohort. Screening against the Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed that LRTI up-regulated DEGs were related to pathogen infection pathways.
Correlations between microbiota diversity and host transcriptomes suggest that 31 host genes (and their relative expression levels) are associated and vary depending on the ratio of normal LRT flora to pathogenic microbes.
Training the Random forest model using this data allowed for predictions of LRTIs using 70 features (11 clinical, 39 lung microbiome, 20 host response). The diagnostic accuracy of the model was found to be 88.2%, and results were obtainable in a number of hours, each significant improvements over traditional diagnostic approaches.
The elemental limitations of this study are that mNGS is currently extremely expensive and requires high technical requirements. Moreover, while these machine learning models might function diagnostic indicators of LRTI, they by no means characterize or explain the pathways or biological functions of the microbiota-host transcriptome interactions observed.
Conclusions
This pre-print study represents a novel approach to lower respiratory tract infection diagnosis. Traditionally, LRTI diagnoses can take multiple days and depict low sensitivity to over 60% of infectious agents. These features lead to disease misidentifications and intervention delays, significantly contributing to morbidity and mortality.
On this study, researchers characterised microbial abundance in LRTI and non-LRTI cohorts, which they clubbed with host transcriptome and response data. These data were used to coach machine learning models, which were subsequently capable of accurately diagnose 88.2% of patients with LRTI in a fraction of the time conventional techniques take.
This research, if validated during peer review, and developed to cut back its inherent high cost, could help clinicians rapidly and accurately diagnose LRTI in the longer term, thereby reducing the high mortality related to the disease.
*Essential notice: SSRN publishes preliminary scientific reports that will not be peer-reviewed and, due to this fact, mustn’t be considered conclusive, guide clinical practice/health-related behavior, or treated as established information.
Journal reference:
- Preliminary scientific report.
Chen H, Qi T, Guo S, et al. (2023). Integrating Respiratory Microbiome and Host Immune Response Using Machine Learning for Diagnosis of the Lower Respiratory Tract Infections. Preprints with The Lancet. doi: 10.2139/ssrn.4505343 https://ssrn.com/abstract=4505343