Clinical, Biomarker, and Research Tests Among US Government Personnel and Their Family Members Involved in Anomalous Health Incidents.

Importance: Since 2015, US government and related personnel have reported dizziness, pain, visual problems, and cognitive dysfunction after experiencing intrusive sounds and head pressure. The US government has labeled these anomalous health incidents (AHIs). Objective: To assess whether participants with AHIs differ significantly from US government control participants with respect to clinical, research, and biomarker assessments. Design, Setting, and Participants: Exploratory study conducted between June 2018 and July 2022 at the National Institutes of Health Clinical Center, involving 86 US government staff and family members with AHIs from Cuba, Austria, China, and other locations as well as 30 US government control participants. Exposures: AHIs. Main Outcomes and Measures: Participants were assessed with extensive clinical, auditory, vestibular, balance, visual, neuropsychological, and blood biomarkers (glial fibrillary acidic protein and neurofilament light) testing. The patients were analyzed based on the risk characteristics of the AHI identifying concerning cases as well as geographic location. Results: Eighty-six participants with AHIs (42 women and 44 men; mean [SD] age, 42.1 [9.1] years) and 30 vocationally matched government control participants (11 women and 19 men; mean [SD] age, 43.8 [10.1] years) were included in the analyses. Participants with AHIs were evaluated a median of 76 days (IQR, 30-537) from the most recent incident. In general, there were no significant differences between participants with AHIs and control participants in most tests of auditory, vestibular, cognitive, or visual function as well as levels of the blood biomarkers. Participants with AHIs had significantly increased fatigue, depression, posttraumatic stress, imbalance, and neurobehavioral symptoms compared with the control participants. There were no differences in these findings based on the risk characteristics of the incident or geographic location of the AHIs. Twenty-four patients (28%) with AHI presented with functional neurological disorders. Conclusions and Relevance: In this exploratory study, there were no significant differences between individuals reporting AHIs and matched control participants with respect to most clinical, research, and biomarker measures, except for objective and self-reported measures of imbalance and symptoms of fatigue, posttraumatic stress, and depression. This study did not replicate the findings of previous studies, although differences in the populations included and the timing of assessments limit direct comparisons.

Neuroimaging Findings in US Government Personnel and Their Family Members Involved in Anomalous Health Incidents.

Importance: US government personnel stationed internationally have reported anomalous health incidents (AHIs), with some individuals experiencing persistent debilitating symptoms. Objective: To assess the potential presence of magnetic resonance imaging (MRI)-detectable brain lesions in participants with AHIs, with respect to a well-matched control group. Design, Setting, and Participants: This exploratory study was conducted at the National Institutes of Health (NIH) Clinical Center and the NIH MRI Research Facility between June 2018 and November 2022. Eighty-one participants with AHIs and 48 age- and sex-matched control participants, 29 of whom had similar employment as the AHI group, were assessed with clinical, volumetric, and functional MRI. A high-quality diffusion MRI scan and a second volumetric scan were also acquired during a different session. The structural MRI acquisition protocol was optimized to achieve high reproducibility. Forty-nine participants with AHIs had at least 1 additional imaging session approximately 6 to 12 months from the first visit. Exposure: AHIs. Main Outcomes and Measures: Group-level quantitative metrics obtained from multiple modalities: (1) volumetric measurement, voxel-wise and region of interest (ROI)-wise; (2) diffusion MRI-derived metrics, voxel-wise and ROI-wise; and (3) ROI-wise within-network resting-state functional connectivity using functional MRI. Exploratory data analyses used both standard, nonparametric tests and bayesian multilevel modeling. Results: Among the 81 participants with AHIs, the mean (SD) age was 42 (9) years and 49% were female; among the 48 control participants, the mean (SD) age was 43 (11) years and 42% were female. Imaging scans were performed as early as 14 days after experiencing AHIs with a median delay period of 80 (IQR, 36-544) days. After adjustment for multiple comparisons, no significant differences between participants with AHIs and control participants were found for any MRI modality. At an unadjusted threshold (P < .05), compared with control participants, participants with AHIs had lower intranetwork connectivity in the salience networks, a larger corpus callosum, and diffusion MRI differences in the corpus callosum, superior longitudinal fasciculus, cingulum, inferior cerebellar peduncle, and amygdala. The structural MRI measurements were highly reproducible (median coefficient of variation <1% across all global volumetric ROIs and <1.5% for all white matter ROIs for diffusion metrics). Even individuals with large differences from control participants exhibited stable longitudinal results (typically, <±1% across visits), suggesting the absence of evolving lesions. The relationships between the imaging and clinical variables were weak (median Spearman ρ = 0.10). The study did not replicate the results of a previously published investigation of AHIs. Conclusions and Relevance: In this exploratory neuroimaging study, there were no significant differences in imaging measures of brain structure or function between individuals reporting AHIs and matched control participants after adjustment for multiple comparisons.

DeepLensNet: Deep Learning Automated Diagnosis and Quantitative Classification of Cataract Type and Severity.

PURPOSE: To develop deep learning models to perform automated diagnosis and quantitative classification of age-related cataract from anterior segment photographs. DESIGN: DeepLensNet was trained by applying deep learning models to the Age-Related Eye Disease Study (AREDS) dataset. PARTICIPANTS: A total of 18 999 photographs (6333 triplets) from longitudinal follow-up of 1137 eyes (576 AREDS participants). METHODS: Deep learning models were trained to detect and quantify nuclear sclerosis (NS; scale 0.9-7.1) from 45-degree slit-lamp photographs and cortical lens opacity (CLO; scale 0%-100%) and posterior subcapsular cataract (PSC; scale 0%-100%) from retroillumination photographs. DeepLensNet performance was compared with that of 14 ophthalmologists and 24 medical students. MAIN OUTCOME MEASURES: Mean squared error (MSE). RESULTS: On the full test set, mean MSE for DeepLensNet was 0.23 (standard deviation [SD], 0.01) for NS, 13.1 (SD, 1.6) for CLO, and 16.6 (SD, 2.4) for PSC. On a subset of the test set (substantially enriched for positive cases of CLO and PSC), for NS, mean MSE for DeepLensNet was 0.23 (SD, 0.02), compared with 0.98 (SD, 0.24; P = 0.000001) for the ophthalmologists and 1.24 (SD, 0.34; P = 0.000005) for the medical students. For CLO, mean MSE was 53.5 (SD, 14.8), compared with 134.9 (SD, 89.9; P = 0.003) for the ophthalmologists and 433.6 (SD, 962.1; P = 0.0007) for the medical students. For PSC, mean MSE was 171.9 (SD, 38.9), compared with 176.8 (SD, 98.0; P = 0.67) for the ophthalmologists and 398.2 (SD, 645.4; P = 0.18) for the medical students. In external validation on the Singapore Malay Eye Study (sampled to reflect the cataract severity distribution in AREDS), the MSE for DeepSeeNet was 1.27 for NS and 25.5 for PSC. CONCLUSIONS: DeepLensNet performed automated and quantitative classification of cataract severity for all 3 types of age-related cataract. For the 2 most common types (NS and CLO), the accuracy was significantly superior to that of ophthalmologists; for the least common type (PSC), it was similar. DeepLensNet may have wide potential applications in both clinical and research domains. In the future, such approaches may increase the accessibility of cataract assessment globally. The code and models are available at https://github.com/ncbi/deeplensnet.

Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration.

OBJECTIVE: Reticular pseudodrusen (RPD), a key feature of age-related macular degeneration (AMD), are poorly detected by human experts on standard color fundus photography (CFP) and typically require advanced imaging modalities such as fundus autofluorescence (FAF). The objective was to develop and evaluate the performance of a novel multimodal, multitask, multiattention (M3) deep learning framework on RPD detection. MATERIALS AND METHODS: A deep learning framework (M3) was developed to detect RPD presence accurately using CFP alone, FAF alone, or both, employing >8000 CFP-FAF image pairs obtained prospectively (Age-Related Eye Disease Study 2). The M3 framework includes multimodal (detection from single or multiple image modalities), multitask (training different tasks simultaneously to improve generalizability), and multiattention (improving ensembled feature representation) operation. Performance on RPD detection was compared with state-of-the-art deep learning models and 13 ophthalmologists; performance on detection of 2 other AMD features (geographic atrophy and pigmentary abnormalities) was also evaluated. RESULTS: For RPD detection, M3 achieved an area under the receiver-operating characteristic curve (AUROC) of 0.832, 0.931, and 0.933 for CFP alone, FAF alone, and both, respectively. M3 performance on CFP was very substantially superior to human retinal specialists (median F1 score = 0.644 vs 0.350). External validation (the Rotterdam Study) demonstrated high accuracy on CFP alone (AUROC, 0.965). The M3 framework also accurately detected geographic atrophy and pigmentary abnormalities (AUROC, 0.909 and 0.912, respectively), demonstrating its generalizability. CONCLUSIONS: This study demonstrates the successful development, robust evaluation, and external validation of a novel deep learning framework that enables accessible, accurate, and automated AMD diagnosis and prognosis.