Prediction of brain amyloidosis: a multi‐site machine learning analysis

نویسندگان

چکیده

Background Position emission tomography (PET) imaging and cerebrospinal fluid (CSF) analysis are the gold standards for evaluating brain amyloidosis in vivo, but their utility is limited by invasive procedures, high costs of PET, accessibility to PET facilities. Prior research has used machine learning assess based on non-invasive easily accessible information such as cognitive test scores genetic data, past accounts have typically a single cohort train models, which may undermine generalizability. Importantly, most studies imputed symptomatic participants without models cognitively unimpaired (CU) individuals. Accordingly, we aimed develop algorithms that estimate risks validate them CU from an external cohort. Method Data Alzheimer’s Disease Neuroimaging Initiative (ADNI) (n = 987) Charles F. Joanne Knight Alzheimer Research Center (Knight ADRC) 688) were used. The examined predictors demographic factors, body mass index (BMI), apolipoprotein E (APOE) genotype, performance tests (Table 1). Random forest trained with nested cross-validation (CV) ADNI before testing ADRC reliable assessment outer CV loop enabled unbiased measurement prediction performance, inner hyperparameter optimization. Result model achieved area under receiver operating characteristic curve (AUC) 0.81 [0.79, 0.84] 2), its generalized well participants. When only considered, was overall lower than full cohort, expect given they less over pathology. nonetheless able achieve AUC 0.78 [0.75, 0.81] Conclusion Machine can predict moderate degree accuracy asymptomatic individuals generalize cohorts. Our be screen likely Aβ PET-positive, thus reducing preclinical AD trial recruitment cost avoiding unnecessary scans.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Prediction of stroke thrombolysis outcome using CT brain machine learning

A critical decision-step in the emergency treatment of ischemic stroke is whether or not to administer thrombolysis - a treatment that can result in good recovery, or deterioration due to symptomatic intracranial haemorrhage (SICH). Certain imaging features based upon early computerized tomography (CT), in combination with clinical variables, have been found to predict SICH, albeit with modest ...

متن کامل

Prediction of brain maturity in infants using machine-learning algorithms

Recent resting-state functional MRI investigations have demonstrated that much of the large-scale functional network architecture supporting motor, sensory and cognitive functions in older pediatric and adult populations is present in term- and prematurely-born infants. Application of new analytical approaches can help translate the improved understanding of early functional connectivity provid...

متن کامل

Stock Price Prediction using Machine Learning and Swarm Intelligence

Background and Objectives: Stock price prediction has become one of the interesting and also challenging topics for researchers in the past few years. Due to the non-linear nature of the time-series data of the stock prices, mathematical modeling approaches usually fail to yield acceptable results. Therefore, machine learning methods can be a promising solution to this problem. Methods: In this...

متن کامل

Comparative Analysis of Machine Learning Algorithms with Optimization Purposes

The field of optimization and machine learning are increasingly interplayed and optimization in different problems leads to the use of machine learning approaches‎. ‎Machine learning algorithms work in reasonable computational time for specific classes of problems and have important role in extracting knowledge from large amount of data‎. ‎In this paper‎, ‎a methodology has been employed to opt...

متن کامل

individual qualities and integrative motivation and their prediction of non-linguistic outcomes of learning english in intermediate iranian students: a psychological perspective

abstract this study investigated the predictability of variables from a motivational framework as well as individuals qualities to predict three non-linguistic outcomes of language learning. gardners socio-educational model with its measures has been used in the current study. individual qualities presented in this study include (1) age, (2) gender, and (3) language learning experience. the...

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Alzheimers & Dementia

سال: 2023

ISSN: ['1552-5260', '1552-5279']

DOI: https://doi.org/10.1002/alz.067459