Neurobiological heterogeneity in schizophrenia is poorly understood and confounds current analyses. We investigated neuroanatomical subtypes in a multi-institutional multi-ethnic cohort, using novel semi-supervised machine learning methods designed to discover patterns associated with disease rather than normal anatomical variation. Structural MRI and clinical measures in established schizophrenia (n = 307) and healthy controls (n = 364) were analysed across three sites of PHENOM (Psychosis Heterogeneity Evaluated via Dimensional Neuroimaging) consortium. Regional volumetric measures of grey matter, white matter, and CSF were used to identify distinct and reproducible neuroanatomical subtypes of schizophrenia. Two distinct neuroanatomical subtypes were found. Subtype 1 showed widespread lower grey matter volumes, most prominent in thalamus, nucleus accumbens, medial temporal, medial prefrontal/frontal and insular cortices. Subtype 2 showed increased volume in the basal ganglia and internal capsule, and otherwise normal brain volumes. Grey matter volume correlated negatively with illness duration in Subtype 1 (r = -0.201, P = 0.016) but not in Subtype 2 (r = -0.045, P = 0.652), potentially indicating different underlying neuropathological processes. The subtypes did not differ in age (t = -1.603, d.f. = 305, P = 0.109), sex (chi-square = 0.013, d.f. = 1, P = 0.910), illness duration (t = -0.167, d.f. = 277, P = 0.868), antipsychotic dose (t = -0.439, d.f. = 210, P = 0.521), age of illness onset (t = -1.355, d.f. = 277, P = 0.177), positive symptoms (t = 0.249, d.f. = 289, P = 0.803), negative symptoms (t = 0.151, d.f. = 289, P = 0.879), or antipsychotic type (chi-square = 6.670, df = 3, P = 0.083). Subtype 1 had lower educational attainment than Subtype 2 (chi-square = 6.389, d.f. = 2, P = 0.041). In conclusion, we discovered two distinct and highly reproducible neuroanatomical subtypes. Subtype 1 displayed widespread volume reduction correlating with illness duration, and worse premorbid functioning. Subtype 2 had normal and stable anatomy, except for larger basal ganglia and internal capsule, not explained by antipsychotic dose. These subtypes challenge the notion that brain volume loss is a general feature of schizophrenia and suggest differential aetiologies. They can facilitate strategies for clinical trial enrichment and stratification, and precision diagnostics.

中文翻译：

---

使用机器学习揭示了两种不同的精神分裂症神经解剖亚型。

精神分裂症的神经生物学异质性知之甚少，并且混淆了当前的分析。我们使用旨在发现与疾病相关的模式而非正常解剖变异的新型半监督机器学习方法，研究了多机构多种族队列中的神经解剖亚型。在 PHENOM（通过维度神经影像评估的精神病异质性）联盟的三个站点中分析了已建立的精神分裂症（n = 307）和健康对照（n = 364）的结构 MRI 和临床测量。灰质、白质和脑脊液的区域体积测量用于识别精神分裂症的不同和可重复的神经解剖亚型。发现了两种不同的神经解剖亚型。亚型 1 表现出广泛的低灰质体积，在丘脑中最为突出，伏核、内侧颞叶、内侧前额叶/额叶和岛叶皮质。亚型 2 显示基底神经节和内囊体积增加，其他脑容量正常。灰质体积与亚型 1 (r = -0.201, P = 0.016) 的病程呈负相关，但在亚型 2 (r = -0.045, P = 0.652) 中不存在，这可能表明不同的潜在神经病理过程。亚型在年龄（t = -1.603，df = 305，P = 0.109）、性别（卡方 = 0.013，df = 1，P = 0.910）、病程（t = -0.167，df = 277）方面没有差异, P = 0.868), 抗精神病药剂量 (t = -0.439, df = 210, P = 0.521), 发病年龄 (t = -1.355, df = 277, P = 0.177), 阳性症状 (t = 0.249, df = 289，P = 0.803）、阴性症状（t = 0.151，df = 289，P = 0.879）或抗精神病药物类型（卡方 = 6.670，df = 3，P = 0.083）。亚型 1 的受教育程度低于亚型 2（卡方 = 6.389，df = 2，P = 0.041）。总之，我们发现了两种不同且高度可重复的神经解剖亚型。亚型 1 显示出与疾病持续时间相关的广泛体积减少和更差的病前功能。亚型 2 具有正常和稳定的解剖结构，除了较大的基底神经节和内囊，不能用抗精神病药剂量来解释。这些亚型挑战了脑容量减少是精神分裂症的一个普遍特征的观点，并提出了不同的病因。它们可以促进临床试验丰富和分层以及精确诊断的策略。我们发现了两种不同且高度可重复的神经解剖亚型。亚型 1 显示出与疾病持续时间相关的广泛体积减少和更差的病前功能。亚型 2 具有正常和稳定的解剖结构，除了较大的基底神经节和内囊，不能用抗精神病药剂量来解释。这些亚型挑战了脑容量减少是精神分裂症的一个普遍特征的观点，并提出了不同的病因。它们可以促进临床试验丰富和分层以及精确诊断的策略。我们发现了两种不同且高度可重复的神经解剖亚型。亚型 1 显示出与疾病持续时间相关的广泛体积减少和更差的病前功能。亚型 2 具有正常和稳定的解剖结构，除了较大的基底神经节和内囊，不能用抗精神病药剂量来解释。这些亚型挑战了脑容量减少是精神分裂症的一个普遍特征的观点，并提出了不同的病因。它们可以促进临床试验丰富和分层以及精确诊断的策略。不能用抗精神病药剂量来解释。这些亚型挑战了脑容量减少是精神分裂症的一个普遍特征的观点，并提出了不同的病因。它们可以促进临床试验丰富和分层以及精确诊断的策略。不能用抗精神病药剂量来解释。这些亚型挑战了脑容量减少是精神分裂症的一个普遍特征的观点，并提出了不同的病因。它们可以促进临床试验丰富和分层以及精确诊断的策略。