Process capability indices: A tool for quality excellence in medical industry

Tóm tắt

Process capability indices (PCIs) are numerical measures used to assess the ability of a process to meet specified requirements. Customers play a pivotal role in the success of any business, and non-compliance with customer or regulatory specifications can lead to significant process losses particularly in critical sectors like the medical industry. Moreover, with the advent of Industrial Revolution 4.0, characterized by the integration of cyber-physical systems, Internet of Things (IoT), and data-driven decision-making, manufacturing and quality control processes have become increasingly complex and data-intensive. In this context, accurately assessing process performance becomes even more critical, especially in highly regulated sectors such as healthcare and medical device manufacturing. Process capability refers to the performance of a process operating under normal, in-control conditions, and its indices are designed to measure the inherent variability of a process and reflect its performance. However, when the underlying process distribution is non-normal as is frequently observed in medical manufacturing and clinical measurement processes traditional methods for calculating PCIs may yield misleading results. This paper focuses on constructing PCIs for non-normal distributions, particularly those that are asymmetric or heavy-tailed. To address this, we propose modified indices viz. quantile-based process capability indices, which offer robust alternatives for evaluating process performance under non-normality. Using both real and simulated datasets, we calculate and assess the performance of these indices for non-normal populations.