Tag Archives: Massachusetts General Hospital

Researchers at Boston-based Massachusetts General Hospital, Ann Arbor-based University of Michigan and Cambridge-based Massachusetts Institute of Technology Are Developing Institution-Specific Models That Predict Patient’s Risk Of Acquiring C.diff. Infections

Researchers at Boston-based Massachusetts General Hospital, Ann Arbor-based University of Michigan and Cambridge-based Massachusetts Institute of Technology are developing hospital-specific machine learning models that predict patients’ risk of Clostridium difficile infections much sooner than current diagnostic methods allow, according to a study published in Infection Control & Epidemiology.

“Despite substantial efforts to prevent C. diff infection and to institute early treatment upon diagnosis, rates of infection continue to increase,” co-senior study author Erica Shenoy, MD, PhD, said in a press release. “We need better tools to identify the highest risk patients so that we can target both prevention and treatment interventions to reduce further transmission and improve patient outcomes.”

The study authors noted most previous approaches to C. diff  infection risk were limited in usefulness since they were not hospital-specific and were developed as “one-size-fits-all” models that only included a few risk factors.

Therefore, to predict a patient’s C. diff risk throughout the course of their hospital stay, the researchers took a “big data” approach that analyzed the entire EHR. This method allows for institution-specific models that could be tailored to different patient populations, different EHR systems and factors specific to each facility. 

“When data are simply pooled into a one-size-fits-all model, institutional differences in patient populations, hospital layouts, testing and treatment protocols, or even in the way staff interact with the EHR can lead to differences in the underlying data distributions and ultimately to poor performance of such a model,” said co-senior study author Jenna Wiens, PhD. “To mitigate these issues, we take a hospital-specific approach, training a model tailored to each institution.”

With this machine learning-based model, the researchers looked at de-identified data, which included individual patient demographics and medical history, details on admissions and daily hospitalization, and the likelihood of C. diff exposure. The data was gathered from the EHRs of roughly 257,000 patients admitted to either MGH or to Michigan Medicine over two-year and six-year periods, respectively.

The models proved to be highly successful at predicting patients who would ultimately be diagnosed with C. diff. In half of these infected patients, accurate predictions could have been made at least five days before collecting diagnostic samples, which would allow hospitals to focus on antimicrobial interventions on the highest-risk patients.

The study’s risk prediction score could guide early screening for C. diff if validated in subsequent studies. For patients who receive an earlier diagnosis, treatment initiation could curb illness severity, and patients with confirmed C. diff could be isolated to prevent transmission to other patients.

The algorithm code is freely available here for hospital leaders to review and adapt for their institutions. However, Dr. Shenoy notes facilities looking to apply similar algorithms to their own institutions must assemble the appropriate local subject-matter experts and validate the performance of the models in their institutions.

To read article in its entirety please click on the following link to be redirected:

https://www.beckershospitalreview.com/quality/how-machine-learning-models-are-rapidly-predicting-c-diff-infections.html

Researchers Utilize Deep Metagenomic Sequencing to Profile FMT ‘s Retracting the Gut Microbiome Features That Coincided With Successful Fecal Transplant Engraftment

A team led by investigators at the Broad Institute have started untangling the bacterial strains that influence successful fecal microbiota transplantation (FMT) engraftment in individuals treated for recurrent Clostridium difficile infection.

As they reported in Cell Host & Microbe today, researchers from the Broad Institute, Massachusetts Institute of Technology, Massachusetts General Hospital, and elsewhere used deep metagenomic sequencing to profile FMT in four FMT donors and 19 recipients with C. difficile infections, retracing the gut microbiome features that coincided with successful fecal transplant engraftment.

The initial gut microbial communities in both the donors and the recipients seemed to influence this process, the team noted, particularly bacterial abundance and strain phylogeny. The final gut microbe composition differed between donors and post-FMT recipients, though, with specific strains that originated in the host either taking hold or falling by the wayside in recipients in an “all-or-nothing” manner.

“This paper provides a context for understanding how to make these live biological therapeutics as an alternative to transferring raw fecal matter,” co-senior author Eric Alm, co-director of MIT’s Center for Microbiome Informatics and Therapeutics, said in a statement.

“We describe a model focused on three elements, including bacterial engraftment, growth, and mechanism of action, that need to be considered when developing these live therapies targeting the gut microorganisms, or microbiome,” added Alm, who is also affiliated with the Broad Institute and Finch Therapeutics.

Along with its use for treating recurrent C. difficile infection, the team noted that FMT has been proposed in other conditions such as inflammatory bowel disease and metabolic syndrome. Even so, there is a ways to go in understanding the factors influencing bacterial engraftment and effectiveness in the recipient gut — information needed to move the approach from a shotgun approach using fecal donor material to microbe-based treatments based on purified collections of specific bacteria.

“Although the success of FMT requires donor bacteria to engraft in the patient’s gut, the forces governing engraftment in humans are unknown,” the authors wrote.

To follow this process, the researchers used the Illumina GAIIx instrument to do deep metagenomic sequencing on seven stool samples from four healthy donors and 67 samples collected over time from 19 individuals treated for C. difficile infection with FMT.

With the help of statistical modeling and a new computational method dubbed Strain Finder, the team looked at the bacterial species that successfully engrafted in FMT recipients and followed strain genotypes over time. It also mapped the metagenomes to Human Microbiome Project reference genomes to take a look at bacterial taxa abundance.

Prior to treatment, for example, FMT recipients had lower-than-usual gut microbiome diversity. And while gut microbial community patterns shifted in recipients after FMT, the resulting gut microbiomes continued to differ from the original donor microbiomes, the researchers reported.

Even so, their analytical methods made it possible predict post-FMR metagenomic operational taxa unit abundance and incidence.

With nearly 1,100 bacterial strains in the 79 samples considered, the team traced transmission of certain strains from FMT donors to recipients, noting that bacterial strains tended to engraft in an “all-or-nothing” manner, “whereby no strains or complete sets of strains colonize the patients.”

“We find that engraftment can be predicted largely from the abundance and phylogeny of bacteria in the donor and the pre-FMT patient,” Alm and co-authors wrote. “Furthermore, donor strains within a species engraft in an all-or-nothing manner and previously undetected strains frequently colonize patients receiving FMT.”

Such patterns were supported by the researchers’ follow-up analyses on 16S ribosomal RNA sequence data for stool samples from 10 more FMT donors and 18 recipients, as well as an analysis of metagenomic sequence data for samples from five individuals treated with FMT for metabolic syndrome.

“Together,” they authors said, “these findings suggest that the principles of engraftment we discovered for recurrent C. difficile infection may generalize to other disease indications, including metabolic syndrome.”

 

To read article in its entirety please click on the following link to be redirected:

https://www.genomeweb.com/sequencing/donor-recipient-strain-analyses-offer-fecal-transplant-engraftment-clues