Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review

Alzheimer s & Dementia, Год журнала: 2023, Номер 19(12), С. 5885 - 5904

Опубликована: Авг. 10, 2023

Abstract Introduction Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis prognosis of dementia. Methods We systematically reviewed studies reporting AI in and/or cognitive neurodegenerative diseases. Results A total 255 were identified. Most relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers most commonly used method (48%) discriminative models performed best differentiating disease from controls. The accuracy algorithms varied with patient cohort, imaging modalities, stratifiers used. Few validation an independent cohort. Discussion literature has several methodological limitations including lack sufficient algorithm development descriptions standard definitions. make recommendations to improve model addressing key clinical questions, providing description methods validating findings datasets. Collaborative approaches between experts medicine will help achieve promising potential tools practice. Highlights There been a rapid expansion use machine learning (71%) (ADNI) dataset no other individual more than five times recent rise complex (e.g., neural networks) that better classification AD vs healthy controls address considerations, also field broadly standardize outcome measures, gaps literature, monitor sources bias

Язык: Английский

---

AI-Driven Innovations in Alzheimer's Disease: Integrating Early Diagnosis, Personalized Treatment, and Prognostic Modelling

Ageing Research Reviews, Год журнала: 2024, Номер unknown, С. 102497 - 102497

Опубликована: Сен. 1, 2024

Язык: Английский

---

Artificial intelligence and open science in discovery of disease-modifying medicines for Alzheimer’s disease

Cell Reports Medicine, Год журнала: 2024, Номер 5(2), С. 101379 - 101379

Опубликована: Фев. 1, 2024

The high failure rate of clinical trials in Alzheimer's disease (AD) and AD-related dementia (ADRD) is due to a lack understanding the pathophysiology disease, this deficit may be addressed by applying artificial intelligence (AI) "big data" rapidly effectively expand therapeutic development efforts. Recent accelerations computing power availability big data, including electronic health records multi-omics profiles, have converged provide opportunities for scientific discovery treatment development. Here, we review potential utility AI approaches data disease-modifying medicines AD/ADRD. We illustrate how tools can applied AD/ADRD drug pipeline through collaborative efforts among neurologists, gerontologists, geneticists, pharmacologists, medicinal chemists, computational scientists. open science expedite therapeutics other neurodegenerative diseases.

Язык: Английский

---

Artificial intelligence for dementia—Applied models and digital health

Alzheimer s & Dementia, Год журнала: 2023, Номер 19(12), С. 5872 - 5884

Опубликована: Июль 26, 2023

Abstract INTRODUCTION The use of applied modeling in dementia risk prediction, diagnosis, and prognostics will have substantial public health benefits, particularly as “deep phenotyping” cohorts with multi‐omics data become available. METHODS This narrative review synthesizes understanding models digital technologies, terms diagnostic discrimination, prognosis, progression. Machine learning approaches show evidence improved predictive power compared to standard clinical scores predicting dementia, the potential decompose large numbers variables into relatively few critical predictors. RESULTS focuses on key areas emerging promise including: emphasis easier, more transparent sharing cohort access; integration high‐throughput biomarker electronic record modeling; progressing beyond primary prediction secondary outcomes, for example, treatment response physical health. DISCUSSION Such benefit also from improvements remote measurement, whether cognitive (e.g., online), or naturalistic watch‐based accelerometry).

Язык: Английский

---

Artificial intelligence for dementia research methods optimization

Alzheimer s & Dementia, Год журнала: 2023, Номер 19(12), С. 5934 - 5951

Опубликована: Авг. 28, 2023

Abstract Artificial intelligence (AI) and machine learning (ML) approaches are increasingly being used in dementia research. However, several methodological challenges exist that may limit the insights we can obtain from high‐dimensional data our ability to translate these findings into improved patient outcomes. To improve reproducibility replicability, researchers should make their well‐documented code modeling pipelines openly available. Data also be shared where appropriate. enhance acceptability of models AI‐enabled systems users, prioritize interpretable methods provide how decisions generated. Models developed using multiple, diverse datasets robustness, generalizability, reduce potentially harmful bias. clarity reproducibility, adhere reporting guidelines co‐produced with multiple stakeholders. If overcome, AI ML hold enormous promise for changing landscape research care. Highlights Machine diagnosis, prevention, management dementia. Inadequate procedures affects reproduction/replication results. built on unrepresentative do not generalize new datasets. Obligatory metrics certain model structures use cases have been defined. Interpretability trust predictions barriers clinical translation.

Язык: Английский

---

Artificial intelligence for dementia prevention

Alzheimer s & Dementia, Год журнала: 2023, Номер 19(12), С. 5952 - 5969

Опубликована: Окт. 14, 2023

Abstract INTRODUCTION A wide range of modifiable risk factors for dementia have been identified. Considerable debate remains about these factors, possible interactions between them or with genetic risk, and causality, how they can help in clinical trial recruitment drug development. Artificial intelligence (AI) machine learning (ML) may refine understanding. METHODS ML approaches are being developed prevention. We discuss exemplar uses evaluate the current applications limitations prevention field. RESULTS Risk‐profiling tools identify high‐risk populations trials; however, their performance needs improvement. New risk‐profiling trial‐recruitment underpinned by models be effective reducing costs improving future trials. inform drug‐repurposing efforts prioritization disease‐modifying therapeutics. DISCUSSION is not yet widely used but has considerable potential to enhance precision Highlights practice. Causal insights needed understand over lifespan. AI will personalize risk‐management could target specific patient groups that benefit most

Язык: Английский

---

Artificial intelligence for neurodegenerative experimental models

Alzheimer s & Dementia, Год журнала: 2023, Номер 19(12), С. 5970 - 5987

Опубликована: Сен. 28, 2023

Experimental models are essential tools in neurodegenerative disease research. However, the translation of insights and drugs discovered model systems has proven immensely challenging, marred by high failure rates human clinical trials.

Язык: Английский

---

Multimodal dementia identification using lifestyle and brain lesions, a machine learning approach

AIP Advances, Год журнала: 2024, Номер 14(6)

Опубликована: Июнь 1, 2024

Dementia diagnosis often relies on expensive and invasive neuroimaging techniques that limit access to early screening. This study proposes an innovative approach for facilitating dementia screening by estimating diffusion tensor imaging (DTI) measures using accessible lifestyle brain factors. Conventional DTI analysis, though effective, is hindered high costs limited accessibility. To address this challenge, fuzzy subtractive clustering identified 14 influential variables from the Lifestyle Brain Health Atrophy Lesion Index frameworks, encompassing demographics, medical conditions, factors, structural markers. A multilayer perceptron (MLP) neural network was developed these selected predict fractional anisotropy (FA), a metric reflecting white matter integrity cognitive function. The MLP model achieved promising results, with mean squared error of 0.000 878 test set FA prediction, demonstrating its potential accurate estimation without costly techniques. values in dataset ranged 0 1, higher indicating greater integrity. Thus, suggests model’s predictions were highly compared observed values. multifactorial aligns current understanding dementia’s complex etiology influenced various biological, environmental, By integrating readily available data into predictive model, method enables widespread, cost-effective risk assessment. proposed tool could facilitate timely interventions, preventive strategies, efficient resource allocation public health programs, ultimately improving patient outcomes caregiver burden.

Язык: Английский

---

Mapping Knowledge Landscapes and Emerging Trends in AI for Dementia Biomarkers: Bibliometric and Visualization Analysis

Journal of Medical Internet Research, Год журнала: 2024, Номер 26, С. e57830 - e57830

Опубликована: Авг. 8, 2024

Background With the rise of artificial intelligence (AI) in field dementia biomarker research, exploring its current developmental trends and research focuses has become increasingly important. This study, using literature data mining, analyzes assesses key contributions development scale AI research. Objective The aim this study was to comprehensively evaluate state, hot topics, future globally. Methods thoroughly analyzed application biomarkers across various dimensions, such as publication volume, authors, institutions, journals, countries, based on Web Science Core Collection. In addition, scales, trends, potential connections between were extracted deeply through multiple expert panels. Results To date, includes 1070 publications 362 involving 74 countries 1793 major with a total 6455 researchers. Notably, 69.41% (994/1432) researchers ceased their studies before 2019. most prevalent algorithms used are support vector machines, random forests, neural networks. Current frequently imaging biomarkers, cerebrospinal fluid genetic blood biomarkers. Recent advances have highlighted significant discoveries related imaging, genetics, blood, growth digital ophthalmic Conclusions is currently phase stable development, receiving widespread attention from numerous worldwide. Despite this, clusters collaborative yet be established, there pressing need enhance interdisciplinary collaboration. Algorithm shown prominence, especially machines networks studies. Looking forward, newly discovered expected undergo further validation, new types, will garner increased interest attention.

Язык: Английский

---

Smart Solutions for Detecting, Predicting, Monitoring, and Managing Dementia in the Elderly: A Survey

IEEE Access, Год журнала: 2024, Номер 12, С. 100026 - 100056

Опубликована: Янв. 1, 2024

Dementia, a syndrome which is characterized by decline in cognitive abilities such as memory, thinking, behavior, and the ability to perform daily living activities, prevalent people aged 60 above. However, detecting it early enough can possibly slow its continuous degeneration lessen toll on families caregivers alike. Due mortality within 10 years of onset well enormous socioeconomic burden, there have been active efforts researchers find smart innovative solutions for detection, prediction, monitoring, management. These are driven recent advancements Internet Things (IoT), wearable technologies, machine learning algorithms. The modeled around modifiable risk factors dementia. In this study, we conducted survey developed or implemented assist clinicians managing health these affected individuals. We then looked at issues limitations solutions, argued that integrated comprising non-wearable technologies multiple dementia necessary should be direction future studies.

Язык: Английский

---