Radio daignosis

The study find that the TB patients to diagnose and treat the disease appropriately; therefore including lab tests, microbiology tests, culture tests, frontal chest X-ray (CXR) and/or computed tomography (CT) scans; can be augment with M.tb genomic information; because  patient microbiome data, and host genomic markers related to drug metabolism and immune system condition.

Host genomic markers

Analysis of the above-mentioned data in the context of treatment history and outcomes can be used to optimize drug regimens and diagnostics; both at the beginning and end of treatment. However, collecting enough sufficiently-detailed TB patient cases for statistical analysis is difficult; especially from rare DR-TB cases.

During 2012, the NIAID TB Portals Program (TBPP)  initiated the creation of a novel data repository containing socioeconomic, geographic, clinical, laboratory, radiological; and pathogen genomic information from deidentified patient cases. This TBPP initiative brings disparate; therefore local, clinical records of DR-TB cases from countries burdened with TB to the attention of the global research community in the form of an open-access online resource.

Immune system condition

Clinical and microbiological information is augmented by the results of M.tb pathogen full genome sequencing and both expert- and computer-derived descriptors of clinical images (CXR and CT). TBPP follows the recommendations of the NIH Big Data to Knowledge (BD2K) initiative to enable biomedical research as a digital research enterprise and adheres to the NIH FAIR principles.

The TB Portals Program is included in the US National Action Plan for Combatting MDR-TB; the NIH Strategic Plan for Data Science; and the NIAID Strategic Plan for TB Research. By supporting a data ecosystem that accelerates discovery as part of the translational medicine; NIAID helps countries with a heavy burden of DR-TB to coordinate their efforts and share unique patient-centric data to shape future research with practical implementations.

Most complete information

As of November 2018, TBPP has collected 2,428 total cases from nine country sites (Azerbaijan, Belarus, Moldova, Georgia, Romania, China, India, Kazakhstan, and South Africa), 1,611 (66%) of which are multidrug or extensively-drug resistant and 1,185 (49%), 863 (36%), and 952 (39%) of which contain X-ray, computed tomography (CT) scan, and genomic data,
respectively. checked for quality issues, and released for publication with the help of a data capture module,
which accumulates a growing list of clinical, socioeconomic, image, and genomic data.

The TB Portals contain patient-centric data, which means that we do not augment our records with externally downloaded information; every piece of information in the record is related to a specific patient’s diagnostics, treatment, monitoring, and outcome. From the beginning, TBPP was selective, specifically choosing patient cases with the most complete information from multiple domains. There are currently 170 data descriptors, making the resource unique in
enabling wide-ranging data mining and hypothesis testing