Gaser 2013.

Study characteristics
Patient sampling	Primary objectives: explore the potential of applying the BrainAGE approach in early detection of abnormal brain changes in order to predict the conversion from MCI to AD within a time span of 3 years Study population: data obtained from the ADNI database including all MCI for whom baseline MRI data 1.5 T, at least moderately confident diagnoses, hippocampus volumes calculated by Freesurfer Version 4.3 and test scores in certain cognitive scales were available Selection criteria: inclusion and exclusion criteria according to the ADNI protocol (ADNI 2010; Petersen 2010). All participants were aged 55–90 and had no evidence of cerebrovascular disease (Modified Hachinski Ischaemia Score ≤ 4), depression (GDS < 6), no significant neurological disease, no visual or hearing impairment, stable medications, good general health, 6 grades of education or equivalent, a study partner, English or Spanish language fluency, and no medical contraindications to MRI Study design: prospective longitudinal study (ADNI study)
Patient characteristics and setting	Clinical presentations: MCI defined according to the ADNI protocol and these criteria: memory complaint verified by study partner; abnormal memory function based on education‐adjusted cut‐off on the Logical Memory II subscale (delayed paragraph recall) from the WMS‐R; MMSE score of 24–30 (inclusive); CDR score of 0.5; and cognitive and functional impairment not severe enough to meet criteria for AD or dementia Age mean (SD): MCI who progressed early to AD: 74 ± 7; MCI who progressed late to AD: 75 ± 7; stable MCI: 76 ± 6 Gender (% men): MCI who progressed early to AD: 57%; MCI who progressed late to AD: 64%; stable MCI: 79% Education years mean (SD): MCI who progressed early to AD: 15.4 ± 2.9; MCI who progressed late to AD: 16.0 ± 2.9; stable MCI: 16.5 ± 2.6 ApoE4 carriers (%): not reported Neuropsychological tests: employed; MMSE mean (SD): MCI who progressed early to AD: 26.5 ± 1.9; MCI who progressed late to AD: 26.8 ± 1.6; stable MCI: 27.7 ± 1.8 Clinical stroke excluded: not specified Co‐morbidities: not reported Number enrolled: 195 Number available for analysis: 195 Setting: ADNI database (multicentre study) Country: USA and Canada Period: data downloaded in May 2010 Language: English
Index tests	Index test: MRI automated method for estimation of left and right hippocampal volumes Manufacturer: GE Healthcare, Philips Medical System, Siemens Medical Solution (Jack 2008b) Tesla strength: 1.5 Tesla Assessment methods: automated method using FreeSurfer version 4.3 (data obtained from the ADNI database). For the exact procedures of data collection and up‐to‐date information, see adni.loni.usc.edu/. Description of positive cases definition by index test as reported: not specified Examiners: not specified Interobserver variability: not specified
Target condition and reference standard(s)	Target condition: AD Prevalence of AD in the sample: 133/195 (68%) of the enrolled participants at 3‐year follow‐up; 58/195 (30%) at 1‐year follow‐up Stable MCI or converted to other dementia: 62 (32%) stable MCI at 3‐year follow‐up Reference standard: AD diagnosis was made according to NINCDS‐ADRDA criteria
Flow and timing	Withdrawals and losses to follow‐up: none reported Uninterpretable MRI results have not been reported
Comparative
Key conclusions by the authors	With accuracy rates of up to 81%, BrainAGE outperformed all cognitive scales and cerebrospinal fluid biomarkers in predicting conversion of MCI to AD within 3 years of follow‐up. Furthermore, the post‐test probability was increased to 90% when using baseline BrainAGE scores to predict conversion to AD
Conflict of interests	Study authors declared no competing interests
Notes	Source of funding: BMBF grant 01EV0709, data collection and sharing was funded by ADNI 2 x 2 table: data from the published article
Methodological quality
Item	Authors' judgement	Risk of bias	Applicability concerns
DOMAIN 1: Patient Selection
Was a consecutive or random sample of patients enrolled?	No
Was a case‐control design avoided?	Yes
Did the study avoid inappropriate exclusions?	No
		High	Low
DOMAIN 2: Index Test All tests
Were the index test results interpreted without knowledge of the results of the reference standard?	Unclear
Did the study provide a clear pre‐specified definition of what was considered to be a "positive" result of the index test?	No
Was the index test performed by a single operator or interpreted by consensus in a joint session?	Unclear
		High	Low
DOMAIN 3: Reference Standard
Is the reference standards likely to correctly classify the target condition?	Yes
Were the reference standard results interpreted without knowledge of the results of the index tests?	Yes
		Low	Low
DOMAIN 4: Flow and Timing
Was there an appropriate interval between index test and reference standard?	Yes
Did all patients receive the same reference standard?	Yes
Were all patients included in the analysis?	Yes
		Low