Jove
Visualize
お問い合わせ
JoVE
x logofacebook logolinkedin logoyoutube logo
JoVEについて
概要リーダーシップブログJoVEヘルプセンター
著者向け
出版プロセス編集委員会範囲と方針査読よくある質問投稿
図書館員向け
推薦の声購読アクセスリソース図書館諮問委員会よくある質問
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experimentsアーカイブ
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教員リソースセンター教員サイト
利用規約
プライバシーポリシー
ポリシー

関連する概念動画

Infection01:20

Infection

11.6K
When a pathogen enters the body and reproduces, it can cause an infection, damage body cells, and cause illness symptoms that eventually lead to disease. Therefore, its prevention requires breaking the chain of infection.
The chain begins with pathogens: bacteria, viruses, fungi, prions, or parasites such as protozoa helminths. These can be present on the skin as transient or resident flora, or they can be acquired from the environment. Identifying and treating the type of infection and...
11.6K
Urinary Tract Infection II: Pathophysiology01:25

Urinary Tract Infection II: Pathophysiology

521
The pathophysiology of urinary tract infections (UTIs) encompasses several progressive stages, beginning with bacterial colonization and culminating in potential systemic complications if untreated. UTIs are primarily initiated by bacteria, such as Escherichia coli, which often originate from the gastrointestinal tract and migrate to the urinary system through the periurethral area. This migration can occur via several routes, including improper hygiene practices, sexual activity, or...
521
Cystic Fibrosis: Pathogenesis01:23

Cystic Fibrosis: Pathogenesis

674
Cystic fibrosis (CF), an autosomal recessive disorder, significantly affects the function of exocrine glands. This genetically inherited disease is characterized by the production of thick and sticky mucus, which can severely affect various organs and systems in the body.
CF is primarily caused by a genetic mutation in a chromosome 7 gene coding for the cystic fibrosis transmembrane conductance regulator (CFTR) protein. The most common gene mutation leading to CF is the ΔF508 mutation,...
674
Pneumonia II: Pathophysiology01:29

Pneumonia II: Pathophysiology

2.5K
The pathophysiology of pneumonia involves the following steps:
2.5K
Stages of Infection01:26

Stages of Infection

64.7K
Stages of infection describe what happens to a susceptible host once a pathogen invades the human body. The stages of infection are incubation, prodromal, illness, stage of decline, and convalescence. The incubation stage is the period from exposure to a pathogen until symptoms start. The infected person is unaware of impending illness as the pathogens grow and multiply within the body. The duration may vary depending on the type of infection. The incubation period of measles averages ten to...
64.7K
Defense Against Bacterial Pathogens01:31

Defense Against Bacterial Pathogens

2.6K
The human immune system is a complex network of cells, tissues, and organs that work together to defend the body against bacterial infections. It consists of various immune cells, each playing a specific role in the defense mechanism.
Phagocytes
Phagocytes are the frontline soldiers of the immune system. They include neutrophils and macrophages. Neutrophils are the most abundant type of white blood cell and are quickly mobilized to the site of infection. Macrophages are larger cells that patrol...
2.6K

こちらも読む

関連記事

共著者、ジャーナル、引用グラフによってこの研究に関連する記事。

並び替え
Same author

Automated biomedical hypothesis generation with time-aware hypergraph contrastive learning.

Knowledge and information systems·2026
Same author

Cell-o1 : training LLMs to solve single-cell reasoning puzzles with reinforcement learning.

Bioinformatics (Oxford, England)·2026
Same author

β-Substitution and prodrug derivation leading to identification of fosmidomycin analogs with improved herbicidal activity.

Pest management science·2026
Same author

Genome-Wide Characterization of the <i>Expansin</i> Gene Family in Eggplant (<i>Solanum melongena</i> L.) Reveals Its Roles in Fruit Development and Heat Stress Response.

Plants (Basel, Switzerland)·2026
Same author

Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prexdiction with Multimodal Biomedical Data.

ArXiv·2026
Same author

Integrating Social Determinants of Health in a Multi-Modal Deep Clustering Survival Model for Injury-Risk in Alzheimer's and Related Dementia Patients.

Proceedings of machine learning research·2026
Same journal

Evidence for progressive neurodegeneration in iatrogenic cerebral amyloid angiopathy.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same journal

Human brain connectome profiles mediate the relationship between pathology burden and clinical phenotypes in Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same journal

Kat5 cKO mouse replicates biological domain signatures associated with Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same journal

Evaluation of CSF and plasma tau species as fluid surrogate candidates for tau PET in prodromal to moderate Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same journal

Associations of self-reported obstructive sleep apnea with cognition and dementia risk in cognitively unimpaired middle-aged adults.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same journal

Inflammation profiles in Alzheimer's disease relate to cognition and neurodegeneration.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
関連記事をすべて見る

関連する実験動画

Updated: Jan 7, 2026

Mouse Footpad Inoculation Model to Study Viral-Induced Neuroinflammatory Responses
09:07

Mouse Footpad Inoculation Model to Study Viral-Induced Neuroinflammatory Responses

Published on: June 14, 2020

11.5K

基礎科学と病態生理

Kazi Noshin1, Bojian Hou2, Mary Regina Bolan3

  • 1University of Virginia, Charlottesville, VA, USA.

Alzheimer's & dementia : the journal of the Alzheimer's Association
|December 25, 2025
PubMed
まとめ
この要約は機械生成です。

アルツハイマー病(AD)研究のために解釈可能な深層学習モデルNADCSMを開発しました。ADの進行に影響を与える重要な脳領域を特定し、神経変性疾患のバイオマーカー発見と精密医療を強化します。

キーワード:
深層学習アルツハイマー病神経変性疾患病態生理バイオマーカー精密医療生存時間解析解釈可能性脳画像神経科学

さらに関連する動画

A Precise Pathogen Delivery and Recovery System for Murine Models of Secondary Bacterial Pneumonia
13:45

A Precise Pathogen Delivery and Recovery System for Murine Models of Secondary Bacterial Pneumonia

Published on: September 21, 2019

6.0K
Using a Bacterial Pathogen to Probe for Cellular and Organismic-level Host Responses
08:38

Using a Bacterial Pathogen to Probe for Cellular and Organismic-level Host Responses

Published on: February 22, 2019

6.3K

関連する実験動画

Last Updated: Jan 7, 2026

Mouse Footpad Inoculation Model to Study Viral-Induced Neuroinflammatory Responses
09:07

Mouse Footpad Inoculation Model to Study Viral-Induced Neuroinflammatory Responses

Published on: June 14, 2020

11.5K
A Precise Pathogen Delivery and Recovery System for Murine Models of Secondary Bacterial Pneumonia
13:45

A Precise Pathogen Delivery and Recovery System for Murine Models of Secondary Bacterial Pneumonia

Published on: September 21, 2019

6.0K
Using a Bacterial Pathogen to Probe for Cellular and Organismic-level Host Responses
08:38

Using a Bacterial Pathogen to Probe for Cellular and Organismic-level Host Responses

Published on: February 22, 2019

6.3K

科学分野:

  • 神経科学
  • 計算生物学
  • 医用画像処理

背景:

  • アルツハイマー病(AD)の進行に重要な脳領域を特定することは、病態生理の理解と標的療法の開発に不可欠です。
  • 深層学習モデルはADの高度な生存時間解析を提供しますが、その性質上、臨床的な解釈可能性を欠くことがよくあります。
  • 本研究では、高い予測精度を維持しながら、AD進行に対する脳領域の寄与に関する解釈可能な洞察を提供するために設計された、ニューラル加算型深層クラスタリング生存機械(NADCSM)フレームワークを紹介します。

研究 の 目的:

  • アルツハイマー病(AD)研究のための解釈可能な深層学習モデルを開発すること。
  • ADの進行に著しく影響を与える特定の脳領域を特定すること。
  • AD生存時間解析における予測パフォーマンスと臨床的有用性のギャップを埋めること。

主な方法:

  • AV45フロルベタピルPET画像を含むアルツハイマー病神経画像イニシアチブ(ADNI)からのデータを利用しました。
  • 生存時間をワイブル分布でモデル化し、解釈可能性のためにニューラル加算型モデル(NAM)を組み込んだNADCSMフレームワークを採用しました。
  • 予測のためのコンコーダンスインデックス(C指数)および生存曲線分離とクラスタリングのためのLogRank統計量を使用してモデルパフォーマンスを評価しました。

主要な成果:

  • NADCSMは、DCSM(0.7789 ± 0.0193)に匹敵する0.7772 ± 0.0236のC指数で、競争力のある予測精度を示しました。
  • NADCSMのLogRank統計量(317.84 ± 31.89)は、生存曲線分離とクラスタリングにおける強力なパフォーマンスを示し、DCSM(317.84 ± 31.89)に匹敵しました。
  • NADCSMは、海馬傍回(左)および小脳脚(右)などの主要な脳領域を特定し、アミロイド負荷とAD進行との解釈可能な関係を明らかにしました。

結論:

  • NADCSMフレームワークは、アルツハイマー病および関連認知症(ADRD)のリスク予測に対する解釈可能なアプローチを提供します。
  • ADRD進行に対する重要な特徴を正常に抽出し、その影響を説明することで、予測モデルの透明性を高めます。
  • この解釈可能性は、精密医療の取り組みを加速し、ADRDの病態生理の理解を深めることができます。