Machine learning applications in healthcare clinical practice and research

Machine learning(ML)is a type of artificial intelligence that assists computers in the acquisition of knowledge through data analysis,thus creating machines that can complete tasks otherwise requiring human intelligence.Among its various applications,it has proven groundbreaking in healthcare as well,both in clinical practice and research.In this editorial,we succinctly introduce ML applications and present a study,featured in the latest issue of the World Journal of Clinical Cases.The authors of this study conducted an analysis using both multiple linear regression(MLR)and ML methods to investigate the significant factors that may impact the estimated glomerular filtration rate in healthy women with and without non-alcoholic fatty liver disease(NAFLD).Their results implicated age as the most important determining factor in both groups,followed by lactic dehydrogenase,uric acid,forced expiratory volume in one second,and albumin.In addition,for the NAFLD-group,the 5th and 6th most important impact factors were thyroid-stimulating hormone and systolic blood pressure,as compared to plasma calcium and body fat for the NAFLD+group.However,the study's distinctive contribution lies in its adoption of ML methodologies,showcasing their superiority over traditional statistical approaches(herein MLR),thereby highlighting the potential of ML to represent an invaluable advanced adjunct tool in clinical practice and research.

Interdepartmental miscommunication regarding radiology:Addressing chronic challenges and exploring solutions

Effective communication and collaboration among healthcare professionals are crucial for delivering high-quality patient care.Interdepartmental miscommunication poses a significant challenge to healthcare systems,potentially undermining the quality of healthcare services provided.In the same manner,communication barriers between referring physicians and radiologists can specifically affect radiology services and patient outcomes.This article attempts to put the spotlight on the ever-present chronic challenges of this issue and prompt readers to recognize the relevant potential pitfalls in their daily clinical practice.Practical solutions are explored and proposed,which should be tailored to the specific needs and issues that each individual institution may face.

Successful endovascular treatment of transplant intrarenal artery stenosis in renal transplant recipients: Two case reports

Transplant renal artery stenosis(TRAS) is a relatively rare complication after renal transplantation. The site of the surgical anastomosis is most commonly involved, but sites both proximal and distal to the anastomosis may occur, as well. Angioplasty is the gold standard for the treatment of the stenosis, especially for intrarenal lesions. We report two cases of intrarenal TRAS and successful management with angioplasty without stent placement. Both patients were male, 44 and 55 years old respectively, and they presented with elevated blood pressure or serum creatinine within three months after transplantation. Subsequently, they have undergone angioplasty balloon dilatation with normalization of blood pressure and serum creatinine returning to baseline level. Percutaneous transluminal balloon renal angioplasty is a safe and effective method for the treatment of the intrarenal TRAS.

The Role of Multislice Computed Angiography of the Bronchial Arteries before Arterial Embolization in Patients with Hemoptysis

Purpose: To evaluate the role of multislice computed angiography of the bronchial arteries and nonbronchial systemic arteries in patients with hemoptysis when performed before arterial embolization procedure. Materials and Methods: Twenty-eight patients with hemoptysis underwent multislice CT angiography of the bronchial arteries with dual-source 64 × 2 detector row scanner before embolization. The transverse CT images as well as the multiplanar reconstructions, the maximum intensity projections and the three-dimensional CT images were used for the depiction of bronchial arteries (the total number of the bronchial arteries, the abnormal bronchial arteries, their origin at the aorta and the diameter of the ostium). The presence of nonbronchial systemic arteries regarded as causing hemoptysis was also evaluated. Digital angiography and selective arteriograms of abnormal bronchial and nonbronchial systemic arteries were performed based on the findings of multislice computed tomography (MDCT). Results: Seventy-eight (40 right and 38 left) bronchial arteries were detected at computed angiography (CTA). Forty of the seventy-eight bronchial arteries that were detected at CTA, were considered abnormal. On selective angiography 38 of these bronchial arteries were regarded as causing hemoptysis. Two of these arteries could not be selectively catheterized and therefore could not be evaluated. All 38 bronchial arteries regarded as causing hemoptysis at selective angiography were detected prospectively at CTA as abnormal. Four bronchial arteries that were found to be responsible for hemoptysis had diameter <2 mm. Twelve nonbronchial systemic arteries were considered to be abnormal on CTA scans. Ten of these twelve nonbronchial systemic arteries were regarded on selective angiography as causing hemoptysis. Two of these arteries were found normal on angiography. All 10 nonbronchial arteries regarded as causing hemoptysis were detected at CTA scans. All bronchial and nonbronchial arteries causing hemoptysis were successfully embolized. Conclusion: MDCT angiography allows detailed identification of abnormal bronchial and nonbronchial systemic arteries using a variety of reformatted images, providing a precise road map for the interventional radiologist.