Advances on diagnosis of Helicobacter pylori infections

Data-driven rapid detection of Helicobacter pylori infection through machine learning with limited laboratory parameters in Chinese primary clinics

Background

Helicobacter pylori (H. pylori) is a significant global health concern, posing a high risk for gastric cancer. Conventional diagnostic and screening approaches are inaccessible, invasive, inaccurate, time-consuming, and expensive in primary clinics.

Objective

This study aims to apply machine learning (ML) models to detect H. pylori infection using limited laboratory parameters from routine blood tests and to investigate the association of these biomarkers with clinical outcomes in primary clinics.

Methods

A retrospective analysis with three ML and five ensemble models was conducted on 1409 adults from Hubei Provincial Hospital of Traditional Chinese Medicine. evaluating twenty-three blood test parameters and using theC 14 urea breath test as the gold standard for diagnosing H. pylori infection.

Results

In our comparative study employing three different feature selection strategies, Random Forest (RF) model exhibited superior performance over other ML and ensemble models. Multiple evaluation metrics underscored the optimal performance of the RF model (ROC = 0.951, sensitivity = 0.882, specificity = 0.906, F1 = 0.906, accuracy = 0.894, PPV = 0.908, NPV = 0.880) without feature selection. Key biomarkers identified through importance ranking and shapley additive Explanations (SHAP) analysis using the RF model without feature selection include White Blood Cell Count (WBC), Mean Platelet Volume (MPV), Hemoglobin (Hb), Red Blood Cell Count (RBC), Platelet Crit (PCT), and Platelet Count (PLC). These biomarkers were found to be significantly associated with the presence of H. pylori infection, reflecting the immune response and inflammation levels.

Conclusion

Abnormalities in key biomarkers could prompt clinical workers to consider H. pylori infection. The RF model effectively identifies H. pylori infection using routine blood tests, offering potential for clinical application in primary clinics. This ML approach can enhance diagnosis and screening, reducing medical burdens and reliance on invasive diagnostics.

Chitosan-modified molybdenum selenide mediated efficient killing of Helicobacter pylori and treatment of gastric cancer

Helicobacter pylori (H. pylori) is one of the major causes of gastrointestinal diseases, including gastric cancer. However, the acidic environment of the stomach and H. pylori resistance severely impair the antimicrobial efficacy of oral drugs. Here, a biocompatible chitosan-modified molybdenum selenide (MoSe2@CS) was designed for the simultaneous photothermal treatment of H. pylori infection and gastric cancer. MoSe2@CS showed a photothermal conversion efficiency was as high as 45.7 %. In the H. pylori-infected mice model, MoSe2@CS displayed a high bacteriostasis ratio of 99.9 % upon near-infrared irradiation. The antimicrobial functionality was also proved by transcriptomic sequencing study, which showed that MoSe2@CS combined with NIR laser irradiation modulated the gene expression of a variety of H. pylori bioprocesses, including cell proliferation and inflammation-related pathways. Further gut flora analysis results indicated that MoSe2@CS mediated PTT of H. pylori did not affect the homeostasis of gut flora, which highlights its advantages over traditional antibiotic therapy. In addition, MoSe2@CS exhibited a good photothermal ablation effect and significantly inhibited gastric tumor growth in vitro and in vivo. The comprehensive application of MoSe2@CS in the PTT of H. pylori infection and gastric cancer provides a new avenue for the clinical treatment of H. pylori infection and related diseases.

Prospective Evaluation of a New Liquid-Type Rapid Urease Test Kit for Diagnosis of Helicobacter pylori

BACKGROUND/AIMS

Rapid and accurate diagnostic tools are essential for the timely recognition of Helicobacter pylori (H. pylori) in clinical practice. The rapid urease test (RUT) is a comparatively accurate and time-saving method recommended as a first-line diagnostic test. The primary objective of conducting the RUT is to obtain rapid results, thus enabling the initiation of an eradication therapy based on clarithromycin resistance testing. This study aimed to assess the reaction time and accuracy of a new liquid-type RUT.

METHOD

In this prospective study, consecutive dyspeptic or check-up patients referred to our clinic for endoscopy were assessed to evaluate the rapidity and accuracy of a novel liquid-type RUT (Helicotest®, WON Medical, Bucheon, Republic of Korea) compared with another commercial RUT kit (HP kit, Chong Kun Dang, Seoul, Republic of Korea) and a real-time quantitative PCR-based assay (Seeplex® H.pylori-ClaR Detection, Seegene, Republic of Korea). RUTs were analyzed at 10 min, 30 min, 60 min, and 120 min.

RESULTS

Among the 177 enrolled patients, 38.6% were infected with H. pylori. The positivity rates of the liquid-type RUT were 26.1, 35.8, 39.2%, and 41.5% at 10, 30, 60, and 120 min, respectively. When compared with the HP kit test, the time needed to confirm positivity was significantly reduced by 28.6 min (95% CI, 16.60-39.73, p < 0.0001). Helicotest® had a greater accuracy (96.02 ± 1.47), sensitivity (98.53 ± 1.46) and NPV (99.03 ± 0.97) compared to the HP kit.

CONCLUSIONS

Compared to the commonly used RUT, the new liquid-type RUT presented faster and reliable results. Such findings could improve H. pylori treatment outcomes, particularly in outpatient clinical settings.

Photoacoustic Spectroscopy-Based Breath Analysis for SIBO

Breath hydrogen (H2) and methane (CH4) monitoring play an important role in the diagnosis of gastrointestinal disorders, such as lactose intolerance and small intestinal bacterial overgrowth (SIBO). In this paper, the photoacoustic spectroscopy method is used for H2 gas and CH4 gas detection. We present a novel approach for H2 gas concentration measurement, which is the linear relationship between the resonant frequency of breath carbon dioxide (CO2) and the H2 concentration in a resonant photoacoustic cell. Experimental results show that the minimum detectable limits of H2, CH4, and CO2 are calculated to be 8.86, 0.56, and 145.14 ppm, respectively, which can meet the requirements of breath diagnosis.

Hyponatremia and Cancer: From Bedside to Benchside

Hyponatremia is the most common electrolyte disorder encountered in hospitalized patients. This applies also to cancer patients. Multiple causes can lead to hyponatremia, but most frequently this electrolyte disorder is due to the syndrome of inappropriate antidiuresis. In cancer patients, this syndrome is mostly secondary to ectopic secretion of arginine vasopressin by tumoral cells. In addition, several chemotherapeutic drugs induce the release of arginine vasopressin by the hypothalamus. There is evidence that hyponatremia is associated to a more negative outcome in several pathologies, including cancer. Many studies have demonstrated that in different cancer types, both progression-free survival and overall survival are negatively affected by hyponatremia, whereas the correction of serum [Na⁺] has a positive effect on patient outcome. In vitro studies have shown that cells grown in low [Na⁺] have a greater proliferation rate and motility, due to a dysregulation in intracellular signalling pathways. Noteworthy, vasopressin receptors antagonists, which were approved more than a decade ago for the treatment of euvolemic and hypervolemic hyponatremia, have shown unexpected antiproliferative effects. Because of this property, vaptans were also approved for the treatment of polycystic kidney disease. In vitro evidence indicated that this family of drugs effectively counteracts proliferation and invasivity of cancer cells, thus possibly opening a new scenario among the pharmacological strategies to treat cancer.