Abstract：
BACKGROUND: Amyloid-negative amnestic mild cognitive impairment (MCI) patients have a conversion rate to dementia of approximately 10% within 2 years. This study aimed to investigate whether brain age, calculated using quantitative data obtained from brain magnetic resonance imaging (MRI) artificial intelligence (AI) software can be an important factor in predicting the conversion of dementia in amyloid-negative amnestic MCI patients.
METHODS: We conducted a retrospective cohort study of patients with amyloid-negative amnestic MCI who visited the memory clinic of Asan Medical Center. All participants underwent detailed neuropsychological testing, brain MRI, and [18F]-florbetaben (FBB) positron emission tomography (PET) scan. Conversion to dementia was determined by a neurologist based on a clinical interview with a detailed neuropsychological test or a decline in the Korean version of the Mini-Mental State Examination score of more than 4 points per year combined with impaired activities of daily living. Brain age was determined through volumetric assessment of 12 distinct brain regions using commercially available segmentation software, Neurophet AQUA.
RESULTS: During the follow-up period, 38% (35/91) of patients converted to dementia from amnestic MCI. 73% (66/91) of patients had a higher brain age than their actual chronological age. In the conversion group, all participants except three (91%, 32/35) had a brain age older than their chronological age. Conversely, the conversion rate to dementia was significantly lower in the group with a younger brain age than their actual age. The subjects were divided into eight groups based on sex, education level, and brain age. When defining the \'survival\' as the non-conversion of MCI to dementia, these groups significantly differed in survival probability with a p-value of 0.036. The low-educated female group with a higher brain age than their actual age had the lowest survival rate of all groups.
CONCLUSIONS: Our findings suggest that MRI-based brain age used in this study can contribute to predicting conversion to dementia in patients with amyloid-negative amnestic MCI.
METHODS: We conducted a retrospective cohort study of patients with amyloid-negative amnestic MCI who visited the memory clinic of Asan Medical Center. All participants underwent detailed neuropsychological testing, brain MRI, and [18F]-florbetaben (FBB) positron emission tomography (PET) scan. Conversion to dementia was determined by a neurologist based on a clinical interview with a detailed neuropsychological test or a decline in the Korean version of the Mini-Mental State Examination score of more than 4 points per year combined with impaired activities of daily living. Brain age was determined through volumetric assessment of 12 distinct brain regions using commercially available segmentation software, Neurophet AQUA.
RESULTS: During the follow-up period, 38% (35/91) of patients converted to dementia from amnestic MCI. 73% (66/91) of patients had a higher brain age than their actual chronological age. In the conversion group, all participants except three (91%, 32/35) had a brain age older than their chronological age. Conversely, the conversion rate to dementia was significantly lower in the group with a younger brain age than their actual age. The subjects were divided into eight groups based on sex, education level, and brain age. When defining the \'survival\' as the non-conversion of MCI to dementia, these groups significantly differed in survival probability with a p-value of 0.036. The low-educated female group with a higher brain age than their actual age had the lowest survival rate of all groups.
CONCLUSIONS: Our findings suggest that MRI-based brain age used in this study can contribute to predicting conversion to dementia in patients with amyloid-negative amnestic MCI.
摘要：
背景：淀粉样蛋白阴性遗忘型轻度认知障碍（MCI）患者在2年内向痴呆的转化率约为10％。这项研究旨在调查大脑年龄，使用从脑磁共振成像（MRI）人工智能（AI）软件获得的定量数据进行计算，可能是预测淀粉样蛋白阴性遗忘型MCI患者痴呆转化的重要因素。
方法：我们对在Asan医疗中心的记忆门诊就诊的淀粉样蛋白阴性遗忘型MCI患者进行了一项回顾性队列研究。所有参与者都接受了详细的神经心理学测试，脑部MRI,和[18F]-氟倍他班(FBB)正电子发射断层扫描(PET)扫描。神经科医生根据详细的神经心理学测试的临床访谈或韩国版的迷你精神状态检查评分每年下降4分以上，并伴有日常生活活动受损，确定了向痴呆症的转化。通过使用市售分割软件对12个不同的大脑区域进行体积评估来确定大脑年龄。NeurophetAQUA.
结果：在随访期间，38%(35/91)的患者从遗忘型MCI转变为痴呆。73％（66/91）的患者的大脑年龄高于其实际实际年龄。在转换组中，除三名参与者外，所有参与者(91%，32/35）的大脑年龄比实际年龄大。相反，大脑年龄较小的组的痴呆转化率显著低于其实际年龄.根据性别将受试者分为八组，教育水平,大脑年龄当将“生存”定义为MCI未转化为痴呆症时，这些组的生存概率显著不同,p值为0.036.受教育程度低的女性群体的大脑年龄高于实际年龄，在所有群体中存活率最低。
结论：我们的研究结果表明，本研究中使用的基于MRI的脑年龄有助于预测淀粉样蛋白阴性遗忘型MCI患者向痴呆的转化。
方法：我们对在Asan医疗中心的记忆门诊就诊的淀粉样蛋白阴性遗忘型MCI患者进行了一项回顾性队列研究。所有参与者都接受了详细的神经心理学测试，脑部MRI,和[18F]-氟倍他班(FBB)正电子发射断层扫描(PET)扫描。神经科医生根据详细的神经心理学测试的临床访谈或韩国版的迷你精神状态检查评分每年下降4分以上，并伴有日常生活活动受损，确定了向痴呆症的转化。通过使用市售分割软件对12个不同的大脑区域进行体积评估来确定大脑年龄。NeurophetAQUA.
结果：在随访期间，38%(35/91)的患者从遗忘型MCI转变为痴呆。73％（66/91）的患者的大脑年龄高于其实际实际年龄。在转换组中，除三名参与者外，所有参与者(91%，32/35）的大脑年龄比实际年龄大。相反，大脑年龄较小的组的痴呆转化率显著低于其实际年龄.根据性别将受试者分为八组，教育水平,大脑年龄当将“生存”定义为MCI未转化为痴呆症时，这些组的生存概率显著不同,p值为0.036.受教育程度低的女性群体的大脑年龄高于实际年龄，在所有群体中存活率最低。
结论：我们的研究结果表明，本研究中使用的基于MRI的脑年龄有助于预测淀粉样蛋白阴性遗忘型MCI患者向痴呆的转化。
