Neurostructural subgroup in 4291 individuals with schizophrenia identified using the subtype and stage inference algorithm.
Yu-Chao JiangCheng LuoJijun WangLena PalaniyappanXiao ChangShi-Tong XiangJie ZhangMingjun DuanHuan HuangChristian GaserKiyotaka NemotoKenichiro MiuraRyota HashimotoLars Tjelta WestlyeGenevieve RichardSara Fernandez-CabelloNadine ParkerOle Andreas AndreassenTilo KircherIgor NenadićFrederike SteinFlorian Thomas-OdenthalLea TeutenbergPaula UsemannUdo DannlowskiTim HahnDominik GrotegerdSusanne MeinertRebekka LencerYingying TangTian Hong ZhangChunbo LiWei-Hua YueYuyanan ZhangXin YuEnpeng ZhouChing-Po LinShih-Jen TsaiAmanda L RodrigueDavid GlahnGodfrey PearlsonJohn E BlangeroAndriana KarukEdith Pomarol-ClotetRaymond SalvadorPaola Fuentes-ClaramonteMaría Ángeles Garcia-LeónGianfranco SpallettaGianfranco SpallettaDaniela VecchioNerisa BanajJingliang ChengZhening LiuJie YangAli Saffet GonulOzgul UsluBirce Begum BurhanogluAslihan Uyar-DemirKelly Rootes-MurdyVince D CalhounKang SimMelissa Jane GreenYann QuidéYoung Chul ChungWoo-Sung KimScott R SponheimCaroline DemroIan S RamsayFelice IasevoliAndrea De BartolomeisAnnarita BaroneMariateresa CiccarelliArturo BrunettiSirio CocozzaGiuseppe PontilloMario TranfaMin Tae M ParkMatthias KirschnerFoivos GeorgiadisStefan KaiserTamsyn E Van RheenenSusan L RossellMatthew E HughesWilliam WoodsSean P CarruthersPhilip SumnerElysha RinginFilip SpanielAntonin SkochDavid TomecekPhilipp HomanStephanie HomanWolfgang OmlorGiacomo CecereDana D NguyenAdrian PredaSophia I ThomopoulosNeda JahanshadLong-Biao CuiDezhong YaoPaul M ThompsonJessica A TurnerTheo G M van ErpWei Chengnull nullJianfeng Fengnull nullPublished in: Nature communications (2024)
Machine learning can be used to define subtypes of psychiatric conditions based on shared biological foundations of mental disorders. Here we analyzed cross-sectional brain images from 4,222 individuals with schizophrenia and 7038 healthy subjects pooled across 41 international cohorts from the ENIGMA, non-ENIGMA cohorts and public datasets. Using the Subtype and Stage Inference (SuStaIn) algorithm, we identify two distinct neurostructural subgroups by mapping the spatial and temporal 'trajectory' of gray matter change in schizophrenia. Subgroup 1 was characterized by an early cortical-predominant loss with enlarged striatum, whereas subgroup 2 displayed an early subcortical-predominant loss in the hippocampus, striatum and other subcortical regions. We confirmed the reproducibility of the two neurostructural subtypes across various sample sites, including Europe, North America and East Asia. This imaging-based taxonomy holds the potential to identify individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.
Keyphrases
- machine learning
- bipolar disorder
- deep learning
- white matter
- cross sectional
- high resolution
- phase iii
- mental health
- single cell
- artificial intelligence
- healthcare
- big data
- emergency department
- cerebral ischemia
- optical coherence tomography
- multiple sclerosis
- risk assessment
- brain injury
- human health
- functional connectivity
- adverse drug
- subarachnoid hemorrhage