Pneumonia is declared a global emergency public health crisis in children less than five age and the geriatric population. Recent advancements in deep learning models could be utilized effectively for the timely and early diagnosis of pneumonia in immune-compromised patients to avoid complications. This systematic review and meta-analysis utilized PRISMA guidelines for the selection of ten articles included in this study. The literature search was done through electronic databases including PubMed, Scopus, and Google Scholar from 1st January 2016 till 1 July 2023. Overall studies included a total of 126,610 images and 1706 patients in this meta-analysis. At a 95% confidence interval, for pooled sensitivity was 0.90 (0.85–0.94) and I2 statistics 90.20 (88.56 – 91.92). The pooled specificity for deep learning models' diagnostic accuracy was 0.89 (0.86–––0.92) and I2 statistics 92.72 (91.50 – 94.83). I2 statistics showed low heterogeneity across studies highlighting consistent and reliable estimates, and instilling confidence in these findings for researchers and healthcare practitioners. The study highlighted the recent deep learning models single or in combination with high accuracy, sensitivity, and specificity to ensure reliable use for bacterial pneumonia identification and differentiate from other viral, fungal pneumonia in children and adults through chest x-rays and radiographs.

肺炎被宣布为五岁以下儿童和老年人口的全球紧急公共卫生危机。深度学习模型的最新进展可以有效地用于及时、早期诊断免疫功能低下患者的肺炎，以避免并发症。这项系统回顾和荟萃分析利用 PRISMA 指南来选择本研究中包含的 10 篇文章。文献检索是通过电子数据库进行的，包括2016年1月1日至2023年7月1日期间的PubMed、Scopus和Google Scholar。在这项荟萃分析中，总体研究共包括126,610张图像和1706名患者。在 95% 置信区间，汇总敏感性为 0.90 (0.85–0.94)，I2 统计值为 90.20 (88.56 – 91.92)。深度学习模型诊断准确性的汇总特异性为 0.89 (0.86–––0.92)，I2 统计值为 92.72 (91.50 – 94.83)。I2 统计数据显示，各项研究之间的异质性较低，突出了一致且可靠的估计，并为研究人员和医疗保健从业者灌输了对这些发现的信心。该研究强调了最近的深度学习模型单独或组合具有高精度、敏感性和特异性，以确保可靠地用于细菌性肺炎识别，并通过胸部 X 光和 X 线照片区分儿童和成人的其他病毒性、真菌性肺炎。