A routine blood test-associated predictive model and application for tuberculosis diagnosis: a retrospective cohort study from northwest China.
Ontology highlight
ABSTRACT:
SUBMITTER: Li K
PROVIDER: S-EPMC6683917 | biostudies-literature | 2019 Jul
REPOSITORIES: biostudies-literature
Publications
A routine blood test-associated predictive model and application for tuberculosis diagnosis: a retrospective cohort study from northwest China.
Li Kui K Liu Sheng-Xi SX Yang Cai-Yong CY Jiang Zi-Cheng ZC Liu Jun J Fan Chuan-Qi CQ Li Tao T Dong Xue-Min XM Wang Jing J Ran Ren-Yu RY
The Journal of international medical research 20190603 7
Similar Datasets
Project description:IntroductionKaryotyping and chromosome microarray analysis (CMA) are the two main prenatal diagnostic techniques currently used for genetic testing. We aimed to evaluate the value of chromosomal karyotyping and CMA for different prenatal indications.MethodsA total of 2084 amniocentesis samples from pregnant women who underwent prenatal diagnosis from 16 to 22 + 6 weeks of gestation between January 2021 and December 2022 were retrospectively collected. The pregnant women were classified according to different prenatal diagnostic indications and underwent CMA and karyotype analysis. Clinical data were collected, and the results of the CMA and karyotype analysis were statistically analyzed to compare the effects of the two diagnostic techniques.ResultsThe total detection rate of abnormal chromosomes was significantly higher using CMA than karyotype analysis. The detection rate of abnormal chromosomes using CMA was significantly higher than that using karyotyping for ultrasound abnormalities, high-risk serologic screening, adverse pregnancy history, positive noninvasive prenatal test (NIPT) screening, and ultrasound abnormalities combined with adverse pregnancy history indications. Among the fetuses with inconsistent results between the two testing methods, 144 had an abnormal CMA but a normal karyotype, with the highest percentage of pregnant women with ultrasound abnormalities at 38.89% (56/144). CMA had the highest detection rate for structural abnormalities combined with soft-index abnormalities among all ultrasound abnormalities. The highest detection rate of copy number variants in the group of structural abnormalities in a single system was in the genitourinary system (3/29, 10.34%).ConclusionCMA can improve the detection rate of chromosomal abnormalities in patients with ultrasound abnormalities, high-risk serologic screening, adverse maternal history, positive NIPT screening, and ultrasound abnormalities combined with adverse maternal history and can increase the detection rate of chromosomal abnormalities in karyotypic normality by 6.91% (144/2,084), this result is higher than similar studies. However, karyotype analysis remains advantageous over CMA regarding balanced chromosomal rearrangement and detection of low-level chimeras, and the combination of the two methods is more helpful in improving the detection rate of prenatal chromosomal abnormalities.
| S-EPMC11576268 | biostudies-literature
Project description:The present study aimed to develop algorithms for early identification of patients who are at risk of being involved in abnormal immunothrombosis, enabling prompt interventions and averted progression of disease.
2021-10-06 | GSE167930 | GEO
Project description:A rapid, accurate, non-sputum-based triage test for diagnosing tuberculosis (TB) is a high-priority need. Cepheid developed a novel prototype blood test, Xpert Mycobacterium tuberculosis Host Response (Xpert-MTB-HR), which generates a TB score based on the mRNA expression of three genes. We conducted a case-control study with prospective recruitment to evaluate its accuracy in the clinic of the Wusheng County Centers for Disease Prevention and Control in China. We enrolled 149 TB patients, 248 other respiratory diseases (ORD) patients, and 193 healthy controls. In addition, whole-blood samples taken from TB patients after 2, 5, and 6 months of treatment were tested with Xpert-MTB-HR to evaluate its ability to monitor treatment response. Xpert-MTB-HR discriminated between TB and healthy controls with an area under the curve (AUC) of 0.912 (95% CI, 0.878-0.945). With the specificity of 70% envisioned for a triage test, its sensitivity was 90.1% (84.9%-94.6%). Xpert-MTB-HR discriminated between TB and ORD with an AUC of 0.798 (0.750-0.847), and at specificity of 70%, the sensitivity was only 75.8% (68.5%-82.8%). In patients determined by Ultra to have medium or high sputum bacillary loads, with specificity of 70%, the sensitivity for discriminating patients with TB from healthy controls was 100.0% (100.0-100.0) and from patients with ORD, 95.1% (89.8-100.0). The TB scores generally increased by 2 months of treatment and then remained stable. Xpert-MTB-HR met the criteria for a triage test to discriminate between TB and healthy controls, but not between TB and ORD, except when limited to patients with high sputum bacillary loads. Xpert-MTB-HR showed promise for monitoring response to treatment but needs to be further evaluated in larger prospective studies.
| S-EPMC10662368 | biostudies-literature
Project description:ObjectiveTuberculosis remains a major global health challenge, with delayed diagnosis contributing to increased transmission and disease burden. While microbiological tests are the gold standard for confirming active tuberculosis, many cases lack microbiological evidence, necessitating additional clinical and laboratory data for diagnosis. The complete blood count (CBC), an inexpensive and widely available test, could provide a valuable tool for tuberculosis diagnosis by analyzing disturbances in blood parameters. This study aimed to develop and evaluate a machine learning (ML)-based web application, TubIAgnosis, for diagnosing active tuberculosis using CBC data.MethodsWe conducted a retrospective case-control study using data from 449 tuberculosis patients and 1200 healthy controls in Oran, Algeria, from January 2016 to April 2023. Eight ML algorithms were trained on 18 CBC parameters and demographic data. Model performance was evaluated using balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC).ResultsThe best-performing model, Extreme Gradient Boosting (XGB), achieved a balanced accuracy of 83.3%, AUC of 89.4%, sensitivity of 83.3%, and specificity of 83.3% on the testing dataset. Platelet-to-lymphocyte ratio was the most influential parameter in this ML predictive model. The best performing model (XGB) was made available online as a web application called TubIAgnosis, which is available free of charge at https://yh5f0z-ghermi-mohamed.shinyapps.io/TubIAgnosis/.ConclusionsTubIAgnosis, a ML-based web application utilizing CBC data, demonstrated promising performance for diagnosing active tuberculosis. This accessible and cost-effective tool could complement existing diagnostic methods, particularly in resource-limited settings. Prospective studies are warranted to further validate and refine this approach.
| S-EPMC11367613 | biostudies-literature
Project description:ABSTRACTThe World Health Organization has identified high-priority target product profiles for new TB diagnostics which include rapid biomarker-based, non-sputum-based diagnostic testing, using an easily accessible sample. The Cepheid 3-gene Host Response Fingerstick Blood Prototype Test (MTB-HR) quantifies relative mRNA levels of a 3-gene signature (GBP5, DUSP3, and KLF2) from a whole-blood sample on the GeneXpert platform. The objective of the present study was to evaluate the performance of the MTB-HR to distinguish between active tuberculosis (ATB), latent Mycobacterium tuberculosis infection (LTBI), other pulmonary diseases, and healthy volunteers at a tertiary care centre. Among 653 participants enrolled in this study, 192 were diagnosed as having ATB, and the remaining 461 were classified as non-ATB, including 137 cases of LTBI, 224 cases of other pulmonary diseases, and 100 healthy volunteers. The corresponding AUCs of the MTB-HR in distinguishing untreated ATB from non-ATB, LTBI, other pulmonary diseases, and healthy volunteers were 0.814 (95% CI, 0.760-0.868, sensitivity 76.1%, specificity 71.6%), 0.739 (95% CI, 0.667-0.812, sensitivity 59.7%, specificity 78.1%), 0.825 (95% CI, 0.770-0.880, sensitivity 82.1%, specificity 65.6%), 0.892 (95% CI, 0.839-0.945, sensitivity 76.1%, specificity 88.0%), respectively. When only samples with TAT of less than 1 h were included, the AUC of the MTB-HR in distinguishing untreated ATB from non-ATB was largest, 0.920 (95% CI, 0.822-1.000, sensitivity 81.3%, specificity 87.7%). In conclusion, the MTB-HR assay shows potential as a rapid, blood-based screening and triage test for ATB, especially for untreated ATB, with the advantage of increased diagnostic yield since blood is more readily available.
| S-EPMC10583623 | biostudies-literature
Project description:Physicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the routine blood tests of 5333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected the operational ROC point at a sensitivity of 81.9% and a specificity of 97.9%. The cross-validated AUC was 0.97. The five most useful routine blood parameters for COVID-19 diagnosis according to the feature importance scoring of the XGBoost algorithm were: MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. t-SNE visualization showed that the blood parameters of the patients with a severe COVID-19 course are more like the parameters of a bacterial than a viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results represent a significant contribution to improvements in COVID-19 diagnosis.
| S-EPMC8144373 | biostudies-literature
Project description:BackgroundExtrapulmonary tuberculosis (EPTB) is a diagnostic challenge. An immunochemistry-based MPT64 antigen detection test (MPT64 test) has reported higher sensitivity in the diagnosis of EPTB compared with conventional methods. The objective of this study was to implement and evaluate the MPT64 test in routine diagnostics in a low-resource setting.MethodsPatients with presumptive EPTB were prospectively enrolled at Mnazi Mmoja Hospital, Zanzibar, and followed to the end of treatment. Specimens collected were subjected to routine diagnostics, GeneXpert® MTB/RIF assay and the MPT64 test. The performance of the MPT64 test was assessed using a composite reference standard, defining the patients as tuberculosis (TB) cases or non-TB cases.ResultsPatients (n = 132) were classified as confirmed TB (n = 12), probable TB (n = 34), possible TB (n = 18), non-TB (n = 62) and uncategorized (n = 6) cases. Overall, in comparison to the composite reference standard for diagnosis, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy of the MPT64 test was 69%, 95%, 94%, 75% and 82%, respectively. The MPT64 test performance was best in TB lymphadenitis cases (n = 67, sensitivity 79%, specificity 97%) and in paediatric TB (n = 41, sensitivity 100%, specificity 96%).ConclusionsWe show that the MPT64 test can be implemented in routine diagnostics in a low-resource setting and improves the diagnosis of EPTB, especially in TB lymphadenitis and in children.
| S-EPMC5942825 | biostudies-literature
Project description:BACKGROUND. Novel rapid diagnostics for active tuberculosis (TB) are required to overcome the time delays and inadequate sensitivity of current microbiological tests that are critically dependent on sampling the site of disease. Multiparametric blood transcriptomic signatures of TB have been described as potential diagnostic tests. We sought to identify the best transcript candidates as host biomarkers for active TB, extend the evaluation of their specificity by comparison with other infectious diseases, and to test their performance in both pulmonary and extrapulmonary TB. METHODS. Support vector machine learning, combined with feature selection, was applied to new and previously published blood transcriptional profiles in order to identify the minimal TB‑specific transcriptional signature shared by multiple patient cohorts including pulmonary and extrapulmonary TB, and individuals with and without HIV-1 coinfection. RESULTS. We identified and validated elevated blood basic leucine zipper transcription factor 2 (BATF2) transcript levels as a single sensitive biomarker that discriminated active pulmonary and extrapulmonary TB from healthy individuals, with receiver operating characteristic (ROC) area under the curve (AUC) scores of 0.93 to 0.99 in multiple cohorts of HIV-1-negative individuals, and 0.85 in HIV-1-infected individuals. In addition, we identified and validated a potentially novel 4-gene signature comprising CD177, haptoglobin, immunoglobin J chain, and galectin 10 that discriminated active pulmonary and extrapulmonary TB from other febrile infections, giving ROC AUCs of 0.94 to 1. CONCLUSIONS. Elevated blood BATF2 transcript levels provide a sensitive biomarker that discriminates active TB from healthy individuals, and a potentially novel 4-gene transcriptional signature differentiates between active TB and other infectious diseases in individuals presenting with fever. FUNDING. MRC, Wellcome Trust, Rosetrees Trust, British Lung Foundation, NIHR.
| S-EPMC5053151 | biostudies-literature
Project description:Pulmonary tuberculosis (PTB) is a major health issue in Northwest China. Most previous studies on the spatiotemporal patterns of PTB considered all PTB cases as a whole; they did not distinguish notified bacteriologically positive PTB (BP-PTB) and notified bacteriologically negative PTB (BN-PTB). Thus, the spatiotemporal characteristics of notified BP-PTB and BN-PTB are still unclear. A retrospective county-level spatial epidemiological study (2011-2018) was conducted in Shaanxi, Northwest China. In total, 44,894 BP-PTB cases were notified, with an average annual incidence rate of 14.80 per 100,000 persons between 2011 and 2018. Global Moran's I values for notified BP-PTB ranged from 0.19 to 0.49 (P < 0.001). Anselin's local Moran's I analysis showed that the high-high (HH) cluster for notified BP-PTB incidence was mainly located in the southernmost region. The primary spatiotemporal cluster for notified BP-PTB (LLR = 612.52, RR = 1.77, P < 0.001) occurred in the central region of the Guanzhong Plain in 2011. In total, 116,447 BN-PTB cases were notified, with an average annual incidence rate of 38.38 per 100,000 persons between 2011 and 2018. Global Moran's I values for notified BN-PTB ranged from 0.39 to 0.69 (P < 0.001). The HH clusters of notified BN-PTB were mainly located in the north between 2011 and 2014 and in the south after 2015. The primary spatiotemporal cluster for notified BN-PTB (LLR = 1084.59, RR = 1.85, P < 0.001) occurred in the mountainous areas of the southernmost region from 2014 to 2017. Spatiotemporal clustering of BP-PTB and BN-PTB was detected in the poverty-stricken mountainous areas of Shaanxi, Northwest China. Our study provides evidence for intensifying PTB control activities in these geographical clusters.
| S-EPMC9046232 | biostudies-literature
Project description:Multiple sclerosis (MS) is an autoimmune chronic disease characterized by inflammation and demyelination of the central nervous system (CNS). Despite numerous studies conducted, valid biomarkers enabling a definitive diagnosis of MS are not yet available. The aim of our study was to identify a marker from a blood sample to ease the diagnosis of MS. In this study, since there is evidence connecting the serotonin pathway to MS, we used an ELISA (Enzyme-Linked Immunosorbent Assay) to detect serum MS-specific auto-antibodies (auto-Ab) against the extracellular loop 1 (ECL-1) of the 5-hydroxytryptamine (5-HT) receptor subtype 2A (5-HT2A). We utilized an ELISA format employing poly-D-lysine as a pre-coating agent. The binding of 208 serum samples from controls, both healthy and pathological, and of 104 serum samples from relapsing-remitting MS (RRMS) patients was tested. We observed that the serum-binding activity in control cohort sera, including those with autoimmune and neurological diseases, was ten times lower compared to the RRMS patient cohort (p = 1.2 × 10-47), with a sensitivity and a specificity of 98% and 100%, respectively. These results show that in the serum of patients with MS there are auto-Ab against the serotonin receptor type 2A which can be successfully used in the diagnosis of MS due to their high sensitivity and specificity.
| S-EPMC10855725 | biostudies-literature