Milner Tracy, Brown Matthew R G, Jones Chelsea, Leung Ada W S, Brémault-Phillips Suzette
Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, AB, Canada.
Department of Computing Science, University of Alberta, Edmonton, AB, Canada.
Front Digit Health. 2024 Mar 6;6:1265846. doi: 10.3389/fdgth.2024.1265846. eCollection 2024.
Mild Cognitive Impairment (MCI) poses a challenge for a growing population worldwide. Early identification of risk for and diagnosis of MCI is critical to providing the right interventions at the right time. The paucity of reliable, valid, and scalable methods for predicting, diagnosing, and monitoring MCI with traditional biomarkers is noteworthy. Digital biomarkers hold new promise in understanding MCI. Identifying digital biomarkers specifically for MCI, however, is complex. The biomarker profile for MCI is expected to be multidimensional with multiple phenotypes based on different etiologies. Advanced methodological approaches, such as high-dimensional statistics and deep machine learning, will be needed to build these multidimensional digital biomarker profiles for MCI. Comparing patients to these MCI phenotypes in clinical practice can assist clinicians in better determining etiologies, some of which may be reversible, and developing more precise care plans. Key considerations in developing reliable multidimensional digital biomarker profiles specific to an MCI population are also explored.
轻度认知障碍（MCI）给全球日益增长的人口带来了挑战。早期识别MCI的风险和诊断对于在正确的时间提供正确的干预措施至关重要。值得注意的是，使用传统生物标志物预测、诊断和监测MCI的可靠、有效且可扩展的方法匮乏。数字生物标志物在理解MCI方面有新的前景。然而，识别专门针对MCI的数字生物标志物很复杂。基于不同病因，MCI的生物标志物特征预计是具有多种表型的多维特征。需要先进的方法，如高维统计和深度机器学习，来构建这些针对MCI的多维数字生物标志物特征。在临床实践中将患者与这些MCI表型进行比较，可以帮助临床医生更好地确定病因（其中一些可能是可逆的），并制定更精确的护理计划。还探讨了开发针对MCI人群的可靠多维数字生物标志物特征的关键考虑因素。
