Identifying peripheral arterial disease in the elderly patients using machine-learning algorithms.

BACKGROUND: Peripheral artery disease (PAD) is a common syndrome in elderly people. Recently, artificial intelligence (AI) algorithms, in particular machine-learning algorithms, have been increasingly used in disease diagnosis. AIM: In this study, we designed an effective diagnostic model of PAD in the elderly patients using artificial intelligence. METHODS: The study was performed with 539 participants, all over 80 years in age, who underwent the measurements of Doppler ultrasonography and ankle-brachial pressure index (ABI). Blood samples were collected. ABI and two machine-learning algorithms (MLAs)-logistic regression and a random forest (RF) model-were established to diagnose PAD. The sensitivity and specificity of the models were analyzed. An additional RF model was designed based on the most significant features of the original RF model and a prospective study was conducted to demonstrate its external validity. RESULTS: Thirteen of the 28 features introduced to the MLAs differed significantly between PAD and non-PAD participants. The respective sensitivities and specificities of logistic regression, RF, and ABI were as follows: logistic regression (81.5%, 83.8%), RF (89.3%, 91.6%) and ABI (85.1%, 84.5%). In the prospective study, the newly designed RF model based on the most significant seven features exhibited an acceptable performance rate for the diagnosis of PAD with 100.0% sensitivity and 90.3% specificity. CONCLUSIONS: An RF model was a more effective method than the logistic regression and ABI for the diagnosis of PAD in an elderly cohort.

Biomarkers of Distinguishing Neutrophil-Predominant Tuberculous Pleural Effusion from Parapneumonic Pleural Effusion.

BACKGROUND: Tuberculous pleural effusion (TPE) is usually characterized by lymphocytic predominance and high pleural fluid adenosine deaminase (pfADA), while parapneumonic pleural effusion (PPE) is usually characterized by neutrophilic predominance. However, in some cases, neutrophils can be predominant in TPE. In such cases, the differential diagnosis between TPE and PPE is challenging and has been rarely investigated. The aim of this study was to evaluate the accuracy of pfADA, pleural fluid lactate dehydrogenase (pfLDH) and other parameters, such as age/pfADA in the differential diagnosis of neutrophil-predominant TPE (NP-TPE) and PPE. METHODS: Between January 2003 and August 2018, 19 patients with NP-TPE and 54 patients with PPE at Shanghai Jiao Tong University Affiliated Sixth People's Hospital were retrospectively reviewed. Age, blood and pleural fluid findings, and eight ratios that consisted of routine biomarkers were compared between the two groups in ≤50 and >50 years old groups. ROC curve analysis was used to evaluate diagnostic performance. RESULTS: The three parameters with the largest AUC were age/pfADA, pfADA and pfLDH in ≤ 50 years old group, and pfADA, age/pfADA and the percentage of neutrophils in pleural fluid (pfN%) in >50 years old group. For patients ≤ 50 years old, pfADA combined with pfLDH or age/pfADA combined with pfLDH could increase the specificity to 100%, while the sensitivity of the former was high (84.6% vs 76.9%). For patients >50 years old, both pfADA combined with pfN% and age/pfADA combined with pfN% could increase the specificity to 90.3% with the same sensitivity. CONCLUSIONS: Although pfADA played an important role in the discrimination of NP-TPE from PPE, combining pfADA with pfLDH for patients ≤50 years old or combining pfADA with pfN% for patients >50 years old might improve diagnostic performance.