Garaszczuk Izabela K, Romanos-Ibanez Maria, Consejo Alejandra
Wroclaw University of Science and Technology, Wroclaw, Poland.
Aragon Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain.
Ophthalmic Physiol Opt. 2024 Jun;44(4):727-736. doi: 10.1111/opo.13302. Epub 2024 Mar 25.
This study addressed the utilisation of machine learning techniques to estimate tear osmolarity, a clinically significant yet challenging parameter to measure accurately. Elevated tear osmolarity has been observed in contact lens wearers and is associated with contact lens-induced dry eye, a common cause of discomfort leading to discontinuation of lens wear.
The study explored machine learning, regression and classification techniques to predict tear osmolarity using routine clinical parameters. The data set consisted of 175 participants, primarily healthy subjects eligible for soft contact lens wear. Various clinical assessments were performed, including symptom assessment with the Ocular Surface Disease Index and 5-Item Dry Eye Questionnaire (DEQ-5), tear meniscus height (TMH), tear osmolarity, non-invasive keratometric tear film break-up time (NIKBUT), ocular redness, corneal and conjunctival fluorescein staining and Meibomian glands loss.
The results revealed that simple linear regression was insufficient for accurate osmolarity prediction. Instead, more advanced regression models achieved a moderate level of predictive power, explaining approximately 32% of the osmolarity variability. Notably, key predictors for osmolarity included NIKBUT, TMH, ocular redness, Meibomian gland coverage and the DEQ-5 questionnaire. In classification tasks, distinguishing between low (<299 mOsmol/L), medium (300-307 mOsmol/L) and high osmolarity (>308 mOsmol/L) levels yielded an accuracy of approximately 80%. Key parameters for classification were similar to those in regression models, emphasising the importance of NIKBUT, TMH, ocular redness, Meibomian glands coverage and the DEQ-5 questionnaire.
This study highlights the potential benefits of integrating machine learning into contact lens research and practice. It suggests the clinical utility of assessing Meibomian glands and NIKBUT in contact lens fitting and follow-up visits. Machine learning models can optimise contact lens prescriptions and aid in early detection of conditions like dry eye, ultimately enhancing ocular health and the contact lens wearing experience.
本研究探讨了利用机器学习技术来估计泪液渗透压，这是一个在临床上具有重要意义但准确测量颇具挑战性的参数。在隐形眼镜佩戴者中观察到泪液渗透压升高，且其与隐形眼镜诱发的干眼有关，干眼是导致不适并致使停止佩戴隐形眼镜的常见原因。
本研究探索了机器学习、回归和分类技术，以使用常规临床参数预测泪液渗透压。数据集由175名参与者组成，主要是符合软性隐形眼镜佩戴条件的健康受试者。进行了各种临床评估，包括使用眼表疾病指数和5项干眼问卷（DEQ - 5）进行症状评估、泪液弯月面高度（TMH）、泪液渗透压、非侵入性角膜曲率计测量的泪膜破裂时间（NIKBUT）、眼红、角膜和结膜荧光素染色以及睑板腺缺失情况。
结果显示，简单线性回归不足以准确预测渗透压。相反，更先进的回归模型实现了中等水平的预测能力，解释了约32%的渗透压变异性。值得注意的是，渗透压的关键预测因素包括NIKBUT、TMH、眼红、睑板腺覆盖率和DEQ - 5问卷。在分类任务中，区分低（<299毫摩尔/升）、中（300 - 307毫摩尔/升）和高渗透压（>308毫摩尔/升）水平的准确率约为80%。分类的关键参数与回归模型中的参数相似，强调了NIKBUT、TMH、眼红、睑板腺覆盖率和DEQ - 5问卷的重要性。
本研究突出了将机器学习整合到隐形眼镜研究和实践中的潜在益处。它表明在隐形眼镜验配和随访中评估睑板腺和NIKBUT的临床实用性。机器学习模型可以优化隐形眼镜处方，并有助于早期发现干眼等病症，最终改善眼部健康和隐形眼镜佩戴体验。
