Back

Explainable machine learning identifies candidate shared neuroanatomical features in Alzheimer's and Parkinson's via importance inversion transfer

Caligiore, D.; Torsello, S.

2026-04-14 neuroscience
10.64898/2026.04.10.717735 bioRxiv
Show abstract

Despite significant neurobiological and pathological overlaps, Alzheimers (AD) and Parkinsons (PD)--the primary threats to healthy aging--are still managed as distinct clinical entities. Standard machine learning exacerbates this fragmentation by prioritizing divergent markers over shared traits, obscuring the invariant foundations of neurodegeneration. This study introduces an explainable framework leveraging Importance Inversion Transfer (IIT) to identify candidate neuroanatomical features that show relative stability across both disorders. By prioritizing structural anchors invariant across the neurodegenerative spectrum, IIT isolates candidate shared structural features. Analysis of multi-regional brain volumes identifies eight shared anchors, confirmed via an inductive validation protocol with high diagnostic robustness (AUC = 0.894). Findings reveal a morphological continuum between healthy aging and neurodegeneration, suggesting the presence of partially shared structural substrates. These results are consistent with--though do not demonstrate--a potential common early-phase vulnerability across neurodegenerative conditions, as conceptualized by the Neurodegenerative Elderly Syndrome (NES) framework, establishing a possible paradigm for early, system-level diagnosis.

Matching journals

The top 11 journals account for 50% of the predicted probability mass.

1
Advanced Science
249 papers in training set
Top 1%
10.1%
2
Communications Biology
886 papers in training set
Top 0.6%
4.9%
3
Alzheimer's & Dementia
143 papers in training set
Top 1%
4.9%
4
Human Brain Mapping
295 papers in training set
Top 1%
4.3%
5
npj Aging
15 papers in training set
Top 0.2%
4.3%
6
Nature Communications
4913 papers in training set
Top 35%
4.3%
7
Scientific Reports
3102 papers in training set
Top 31%
4.0%
8
Translational Psychiatry
219 papers in training set
Top 2%
3.6%
9
Frontiers in Aging Neuroscience
67 papers in training set
Top 1%
3.6%
10
NeuroImage
813 papers in training set
Top 3%
3.6%
11
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 20%
3.6%
50% of probability mass above
12
Aging Cell
144 papers in training set
Top 1%
3.6%
13
Neurobiology of Aging
95 papers in training set
Top 0.9%
3.1%
14
GeroScience
97 papers in training set
Top 0.6%
3.1%
15
eLife
5422 papers in training set
Top 34%
2.4%
16
Alzheimer's Research & Therapy
52 papers in training set
Top 1.0%
2.1%
17
PLOS ONE
4510 papers in training set
Top 48%
2.1%
18
Brain Communications
147 papers in training set
Top 1%
1.8%
19
Cell Reports
1338 papers in training set
Top 24%
1.7%
20
NeuroImage: Clinical
132 papers in training set
Top 2%
1.7%
21
Communications Psychology
20 papers in training set
Top 0.1%
1.7%
22
PLOS Computational Biology
1633 papers in training set
Top 17%
1.7%
23
Brain
154 papers in training set
Top 3%
1.2%
24
Nature Medicine
117 papers in training set
Top 3%
1.2%
25
Imaging Neuroscience
242 papers in training set
Top 3%
1.2%
26
PLOS Biology
408 papers in training set
Top 16%
0.9%
27
eBioMedicine
130 papers in training set
Top 3%
0.9%
28
Neuropathology and Applied Neurobiology
14 papers in training set
Top 0.5%
0.9%
29
Science Advances
1098 papers in training set
Top 28%
0.8%
30
Aging
69 papers in training set
Top 3%
0.8%