Uniform manifold approximation and projection (UMAP) is a technique for dimension reduction and visualization of high-dimensional (HD) data. Here, we apply UMAP to represent in two dimensions, data from members of the Wake Forest School of Medicine Alzheimer’s Disease Research Center (WFUSM-ADRC) clinical cohort. We examined baseline data from 542 WFUSM-ADRC participants with mean age 70.1 years (range 54-95 years), including 66% women and 18% Black self-reported participants. A total of 195 participants were adjudicated with mild cognitive impairment(MCI), 67 with dementia and 280 were normal controls(NC) at baseline. Participants were further classified according to the stability of their cognitive status during 6.7 years of follow-up with respect to baseline. We created a vector of 36 variables including cognitive tests, blood-based biomarkers, MRI measures and age for each participant using baseline data. Based on UMAP, a 2D view of the data was created. Next, we fitted a nonlinear support vector machine with a Gaussian-kernel and generated the boundary decision using data from participants classified at baseline as NC and dementia who kept the same status during their follow-up. Data from individuals with MCI who remained stable, converted to dementia, or reverted to NC was provided to the classifier. The distance of each sample to the boundary was estimated. We evaluated this distance as a multimodal measure of AD dementia risk using a Wilcoxon test. The classifier discriminated NC from dementia cases with an area under the curve of 96.3. The blue area in Figure 1 surrounded by the classifier’s boundary decision, we refer to as the “high-risk zone”. Overall individuals with MCI falling inside the risk zone at baseline had significantly worse values of cognitive parameters (Verbal Fluency, AVLT, Digit Span, MoCA, Trails A &B), blood (GFAP, ptau181, NFL) and imaging biomarkers (AD Pattern Similarity scores, hippocampal and a temporal-metaROI volume),(p < 0.001) than those individuals with MCI outside the high-risk zone. Positive distances indicate the samples to be inside the zone. Differences in distances between the three MCIs groups were significant (p < 0.001). UMAP 2D projections have explanatory value to evaluate dementia risk in MCI.

Rationale and Objectives: Tools are needed for frailty screening of older adults. Opportunistic analysis of body composition could play a role. We aim to determine whether computed tomography (CT) -derived measurements of muscle and adipose tissue are associated with frailty. Materials and Methods: Outpatients aged >= 55 years consecutively imaged with contrast -enhanced abdominopelvic CT over a 3month interval were included. Frailty was determined from the electronic health record using a previously validated electronic frailty index (eFI). CT images at the level of the L3 vertebra were automatically segmented to derive muscle metrics (skeletal muscle area [SMA], skeletal muscle density [SMD], intermuscular adipose tissue [IMAT]) and adipose tissue metrics (visceral adipose tissue [VAT], subcutaneous adipose tissue [SAT]). Distributions of demographic and CT -derived variables were compared between sexes. Sexspecific associations of muscle and adipose tissue metrics with eFI were characterized by linear regressions adjusted for age, race, ethnicity, duration between imaging and eFI measurements, and imaging parameters. Results: The cohort comprised 886 patients (449 women, 437 men, mean age 67.9 years), of whom 382 (43%) met the criteria for prefrailty (ie, 0.10 < eFI <= 0.21) and 138 (16%) for frailty (eFI > 0.21). In men, 1 standard deviation changes in SMD (beta = -0.01, 95% confidence interval [CI], -0.02 to -0.001, P = .02) and VAT area (beta = 0.008, 95% CI, 0.0005-0.02, P = .04), but not SMA, IMAT, or SAT, were associated with higher frailty. In women, none of the CT -derived muscle or adipose tissue metrics were associated with frailty. Conclusion: We observed a positive association between frailty and CT -derived biomarkers of myosteatosis and visceral adiposity in a sex -dependent manner.

Machine learning models are increasingly being used to estimate “brain age” from neuroimaging data. The gap between chronological age and the estimated brain age gap (BAG) is potentially a measure of accelerated and resilient brain aging. Brain age calculated in this fashion has been shown to be associated with mortality, measures of physical function, health, and disease. Here, we estimate the BAG using a voxel-based elastic net regression approach, and then, we investigate its associations with mortality, cognitive status, and measures of health and disease in participants from Atherosclerosis Risk in Communities (ARIC) study who had a brain MRI at visit 5 of the study. Finally, we used the SOMAscan assay containing 4877 proteins to examine the proteomic associations with the MRI-defined BAG. Among N = 1849 participants (age, 76.4 (SD 5.6)), we found that increased values of BAG were strongly associated with increased mortality and increased severity of the cognitive status. Strong associations with mortality persisted when the analyses were performed in cognitively normal participants. In addition, it was strongly associated with BMI, diabetes, measures of physical function, hypertension, prevalent heart disease, and stroke. Finally, we found 33 proteins associated with BAG after a correction for multiple comparisons. The top proteins with positive associations to brain age were growth/differentiation factor 15 (GDF-15), Sushi, von Willebrand factor type A, EGF, and pentraxin domain-containing protein 1 (SEVP 1), matrilysin (MMP7), ADAMTS-like protein 2 (ADAMTS), and heat shock 70 kDa protein 1B (HSPA1B) while EGF-receptor (EGFR), mast/stem-cell-growth-factor-receptor (KIT), coagulation-factor-VII, and cGMP-dependent-protein-kinase-1 (PRKG1) were negatively associated to brain age. Several of these proteins were previously associated with dementia in ARIC. These results suggest that circulating proteins implicated in biological aging, cellular senescence, angiogenesis, and coagulation are associated with a neuroimaging measure of brain aging.

INTRODUCTION:The course of depressive symptoms and dementia risk is unclear, as are potential structural neuropathological common causes. METHODS:Utilizing joint latent class mixture models, we identified longitudinal trajectories of annually assessed depressive symptoms and dementia risk over 21 years in 957 older women (baseline age 72.7 years old) from the Women's Health Initiative Memory Study. In a subsample of 569 women who underwent structural magnetic resonance imaging, we examined whether estimates of cerebrovascular disease and Alzheimer's disease (AD)-related neurodegeneration were associated with identified trajectories. RESULTS:Five trajectories of depressive symptoms and dementia risk were identified. Compared to women with minimal symptoms, women who reported mild and stable and emerging depressive symptoms were at the highest risk of developing dementia and had more cerebrovascular disease and AD-related neurodegeneration. DISCUSSION:There are heterogeneous profiles of depressive symptoms and dementia risk. Common neuropathological factors may contribute to both depression and dementia. Highlights The progression of depressive symptoms and concurrent dementia risk is heterogeneous. Emerging depressive symptoms may be a prodromal symptom of dementia. Cerebrovascular disease and AD are potentially shared neuropathological factors.

Abstract Machine learning models are increasingly being used to estimate ‘brain age’ from neuroimaging data. The gap between chronological age and the estimated brain age (BAG) is potentially a measure of accelerated/resilient brain aging, and we estimated BAG based on an elastic net regression approach. Here, we report associations between this brain age measure and plasma protein levels (measured using an aptamer-based proteomic platform) in the Atherosclerosis Risk in Communities (ARIC) Study to determine whether BAG was associated with proteins linked to biologic aging. We used brain MRI scans from 1507 ARIC visit 5 participants: 938 were Cognitively Normal (CN), 495 had mild cognitive impairment (MCI) and 74 had dementia. The proteomic dataset contains 4877 plasma proteins in these same individuals. We fitted univariate linear regression models adjusting for age, race, smoking, education, sex, diabetes, hypertension and intra-cranial volume. A Bonferroni correction was applied to account for multiple testing to maintain an analysis-wise α=0.05. In total 31 proteins were significantly associated with BAG. Among these SEVP1, GDF-15, pleiotrophin, MMP7, Natriuretic-peptides and Hsp70 were found to be associated with accelerated BAG, whereas EGF-receptor, mast/stem-cell-growth-factor-receptor (KIT), Coagulation-factor-VII and cGMP-dependent-protein-kinase-1 were associated to resilient BAG. The analysis based only on CN participants produced 3 significant proteins: retinoblastoma-2 and SEVP1, which were associated with accelerated BAG and Coagulation-factor-VII, which was associated to resilient BAG. These results suggest circulating proteins implicated in biological aging, cellular senescence, angiogenesis and coagulation are associated with a neuroimaging measure of accelerated brain aging.

Machine learning and artificial intelligence methods have been applied to brain images to estimate measures of brain aging. However, only rarely have these measures been examined in the context of biologic age. Here, we investigated associations of an MRI-based measure of dementia risk the Alzheimer’s disease pattern similarity (AD-PS) scores with measures of longevity and biological age. Participants were those from visit 5 of the Atherosclerosis Risk in Community Study with cognitive status adjudication and MRI available. The AD-PS score was estimated based on previously reported machine learning methods. We evaluated associations of the AD-PS score with all-cause mortality. Participants were stratified by AD-PS tertiles and the analyses were adjusted for age, race, sex, hypertension and smoking. AD-PS score was examined in association with 32 proteins reported to be associated with age. In these analyses, we used Bonferroni correction (α = 0.05,p<0.0016). Finally, associations with a deficit accumulation index(DAI) based on 38 health items was investigated. In both cases, linear regression models were adjusted for age, race and sex. Sensitivity analyses using only cognitively normal (CN) individuals were performed. Mortality – A total of 356 participants died within 8 years of follow-up. The AD-PS score was significantly associated(p<0.001) with time to all-cause mortality. Participants in the lowest tertile had lower all-cause mortality rate compared to those in the highest tertile (HR: 0.43;95% CI:0.31,0.60). The association remained significant when restricting the sample to only CN subjects (HR for lowest tertile:0.53; 95% CI:0.35,0.81, p = 0.0028). Age related proteins - The AD-PS scores were significantly associated (p<0.05, uncorrected) with 10 of the 32 proteins. Growth/differentiation factor 15(GDF-15) and pleiotrophin remained significant after correction for multiple-testing. Analysis of CN participants showed a subset of the same proteins to be significant (p<0.05,uncorrected) but only the GDF-15 remained significant after correction for multiple-testing. DAI - A linear regression model showed a significant association between DAI and AD-PS scores overall (coeff = 0.52; 95% CI:0.37-0.67) and in the CN subset (coeff = 0.3,95% CI:0.13-0.48). While the AD-PS scores were created as a measure of dementia risk, our analyses suggest that they could also be capturing brain aging.

There is an increasing interest in using machine learning and artificial intelligence to estimate chronological age using neuroimaging data. The gap between chronological age and estimated brain age (brain age gap, BAG) is used as a measure of accelerated/resilient brain aging. Previously, BAG has been associated with cognitive status. However, whether the BAG varies across sex and cognitive status have been less explored. The present study examines these associations and validates a voxel-based machine learning approach based on the elastic net regression (ENR) for BAG calculation. Using data from the Atherosclerosis Risk in Communities Study (ARIC) study, the Wake Forest School of Medicine Alzheimer’s Disease Research Center (WFSM-ADRC) clinical cohort and Alzheimer’s Disease Neuroimaging Initiative (ADNI), we examined associations of BAG across cognitive status and sex. We used structural MRI scans from 1853 ARIC participants (ages 67-90, 60% females), 508 from the WFSM-ADRC (55-95 yo., 66% females) and 584 ADNI cognitively normal (CN) participants (55-90 yo., 57% females). All images were aligned into a common template and the derived gray matter (GM) probability maps from ADNI MRIs were used as input to train the machine learning algorithm. Once the model was fitted the ARIC and WFSM-ADRC GM probability maps were provided as input to the algorithm to estimate the BAG values. Finally, an age bias correction was applied. Linear regression methods were used to investigate differences between groups. Age, race, education, sex, and cognitive status were included in the model. We found in both ARIC and WFSM-ADRC participants that differences in BAG values between CN-MCI and MCI-Dementia participants were highly significant. In addition, when we examined differences in BAG values across sex per cognitive status, we found again in both cohorts that differences were only significant for CN individuals. See Table 1 for details. Our analyses show that our approach to estimate chronological age using high-dimensional ENR, produces BAG values which are strongly associated with cognitive status. The increased severity of cognitive impairment is related to accelerated brain aging. Differences in BAG between men and women were significant for CN individuals only.

MRI is a widely used modality to evaluate dementia risk. Here, we extend previous work by estimating the Alzheimer’s disease pattern similarity (AD-PS) scores for participants of a community-dwelling older adult cohort to evaluate neuroanatomic risk of AD using MRI. Baseline MRI data were available from 522 participants from the Wake Forest Alzheimer’s Disease Research Center’s (ADRC) Clinical Core with mean age 70.2, 81.2% White and 17.6% African American. Of those, 253 were cognitively impaired (dementia and mild cognitive impairment (MCI)) and 138 underwent [11C]PiB PET (MCI = 48 and dementia = 19). Global PiB SUVR was averaged from a cortical region of interest sensitive to early AD. Participants were classified as amyloid positivity using a previously defined threshold (≥1.21 SUVR). AD-PS scores were estimated based on GM probability maps according to previously reported machine learning methodology[1]. High-dimensional classifiers were trained using ADNI MRI data. To generate the AD-PS scores, MRI data from the ADRC cohort was provided as input to the classifiers. We investigated associations that AD-PS scores [range 0-1] had with amyloid positivity and cognitive impairment. All analyses were adjusted for age, sex, race and education. AD-PS scores discrimination of participants with dementia versus normal cognition (CN) was compared to hippocampal volume and cortical thickness in temporal regions based meta-ROI which are sensitive to AD. AD-PS scores were strongly associated with cognitive impairment: OR = 4.1, CI: 95% [2.9-5.9], p<0.0001. In addition, they were associated with amyloid positivity with OR = 2.8,CI: 95% [1.7-4.7], p<0.001, N = 138. These amyloid positivity results did not hold in analyses limited to CN participants only(N = 71). Performance when discriminating patients with dementia from CN individuals was highest for AD-PS score (AUC = 92.2, CI: 95% [86.9-97.5]), followed by hippocampal volume (AUC = 86.5, CI: 95% [81.1-91.2]) and cortical thickness in temporal regions based meta-ROI (AUC = 81.5 CI: 95% [74.4-88.6], See-Figure). This work highlights further the generalization performance of our machine learning algorithm. AD-PS scores, a measure of dementia neuroanatomic risk, strongly discriminated individuals with dementia from CN individuals in the Wake Forest ADRC. References [1] Casanova et. al., Alzheimer’s & Dementia, 2021, PMID:34310039.

Objective The objective was to develop a disability-based metric for quantifying disability rates as a result of motor vehicle crash (MVC) spine injuries and compare functional outcomes between pediatric and adult subgroups. Methods Disability rate was quantified using Functional Independence Measure (FIM) scores within the National Trauma Data Bank-Research Data System for the top 95% most frequent Abbreviated Injury Scale (AIS) 3 spine injuries (14 unique injuries). Pediatric (7-18 years), young adult (19-45 years), middle-aged adult (46-65 years), and older adult (66+ years) MVC occupants with FIM scores available and at least one of the 14 spine injuries were included. FIM scores of 1 or 2 at time of discharge were used to define disability and correspond to full functional or modified dependence in self-feeding, locomotion, and/or verbal expression. Disability rate was evaluated on a per injury basis for each AIS 3 spine injury and calculated as the proportion of cases associated with disability (i.e. FIM of 1 or 2) out of the total cases of that particular injury. Disability rates were calculated with and without the exclusion of cases with severe co-injuries (AIS 4+) to minimize bias from additional non-spinal injuries that could have contributed to disability. Associations between adjusted disability rates and existing mortality rates were investigated. Results Locomotion impairment alone was the most frequent disability type for the top 14 AIS 3 spine injuries (7 cervical, 4 thoracic, and 3 lumbar) across all age groups and spine regions. Adjusted and unadjusted disability rates ranged from 0-69%. Adjusted disability rates increased with age: 14.8 +/- 10% (mean +/- SD) in pediatrics to 16.2 +/- 6.6% (young adults), 29.2 +/- 10.9% (middle-aged adults), and 45.0 +/- 12.2% (older adults). Among all adult populations, adjusted mortality and disability rates were positively correlated (R-2>0.24), with disability rates consistently greater than corresponding mortality rates. Conclusions Older adults had significantly greater disability rates associated with MVC spine injuries across all spinal regions. MVC disability rates for pediatrics were considerably lower. Overall, rates of mortality were significantly lower than rates of disability. The adjusted disability rates developed can supplement existing injury metrics by accounting for age- and location-specific functional implications of MVC spine injuries.

Machine learning methods have been applied to estimate measures of brain aging from neuroimages. However, only rarely have these measures been examined in the context of biologic age. Here, we investigated associations of an MRI-based measure of dementia risk, the Alzheimer's disease pattern similarity (AD-PS) scores, with measures used to calculate biological age. Participants were those from visit 5 of the Atherosclerosis Risk in Communities Study with cognitive status adjudication, proteomic data, and AD-PS scores available. The AD-PS score estimation is based on previously reported machine learning methods. We evaluated associations of the AD-PS score with all-cause mortality. Sensitivity analyses using only cognitively normal (CN) individuals were performed treating CNS-related causes of death as competing risk. AD-PS score was examined in association with 32 proteins measured, using a Somalogic platform, previously reported to be associated with age. Finally, associations with a deficit accumulation index (DAI) based on a count of 38 health conditions were investigated. All analyses were adjusted for age, race, sex, education, smoking, hypertension, and diabetes. The AD-PS score was significantly associated with all-cause mortality and with levels of 9 of the 32 proteins. Growth/differentiation factor 15 (GDF-15) and pleiotrophin remained significant after accounting for multiple-testing and when restricting the analysis to CN participants. A linear regression model showed a significant association between DAI and AD-PS scores overall. While the AD-PS scores were created as a measure of dementia risk, our analyses suggest that they could also be capturing brain aging.

Abstract There is an increasing interest in using machine learning and artificial intelligence to estimate chronological age using neuroimaging data. The gap between chronological age and estimated brain age (brain age gap, BAG) is used as a measure of accelerated/resilient brain aging. Accelerated brain aging has been associated with increased mortality risk. However, these reports are based on cohorts mostly composed by white individuals. Here we capitalized on the racially diverse nature of the Atherosclerosis Risk in Communities Study (ARIC) cohort to investigate associations of brain across race. We used brain MRI scans from 1172 cognitively normal ARIC participants that were collected at ARIC Visit 5. Of those 772 were White and 366 were African Americans. We used Cox regression models to investigate BAG values associations with mortality. There were 163 deaths (dw = 124 and daa = 39) over 8 years of follow-up. Participants were stratified by tertiles according to BAG values. We found that, compared to those individuals with BAG scores in the highest tertile (>=1.15), those who scored in the lowest tertile (<= -1.3 years) to be associated with significantly lower mortality among the White (HR=0.41, 95% CI, [0.26–0.66], p < 0.001) and Black (HR=0.43, 95% CI, [0.20–0.92], p = 0.03) participants after adjusting for age, race-center, sex, education, diabetes, smoking and hypertension. Our analyses show that our approach to estimate chronological age using high-dimensional elastic net regression, produces BAG values which are associated with mortality not only in White individuals but also in African Americans.

BACKGROUND:Advanced automatic crash notification (AACN) can improve triage decision-making by using vehicle telemetry to alert first responders of a motor vehicle crash and estimate an occupant's likelihood of injury. The objective was to develop an AACN algorithm to predict the risk that a pediatric occupant is seriously injured and requires treatment at a Level I or II trauma center.METHODS:Based on 3 injury facets (severity; time sensitivity; predictability), a list of Target Injuries associated with a child's need for Level I/II trauma center treatment was determined. Multivariable logistic regression of motor vehicle crash occupants was performed creating the pediatric-specific AACN algorithm to predict risk of sustaining a Target Injury. Algorithm inputs included: delta-v, rollover quarter-turns, belt status, multiple impacts, airbag deployment, and age. The algorithm was optimized to achieve under-triage ≤5% and over-triage ≤50%. Societal benefits were assessed by comparing correctly triaged motor vehicle crash occupants using the AACN algorithm against real-world decisions.RESULTS:The pediatric AACN algorithm achieved 25% to 49% over-triage across crash modes, and under-triage rates of 2% for far-side, 3% for frontal and near-side, 8% for rear, and 14% for rollover crashes. Applied to real-world motor vehicle crashes, improvements of 59% in under-triage and 45% in over-triage are estimated: more appropriate triage of 32,320 pediatric occupants annually.CONCLUSIONS:This AACN algorithm accounts for pediatric developmental stage and will aid emergency personnel in correctly triaging pediatric occupants after a motor vehicle crash. Once incorporated into the trauma triage network, it will increase triage efficiency and improve patient outcomes.

Objective To examine whether late-life exposure to PM2.5 (particulate matter with aerodynamic diameters <2.5 µm) contributes to progressive brain atrophy predictive of Alzheimer disease (AD) using a community-dwelling cohort of women (age 70–89 years) with up to 2 brain MRI scans (MRI-1, 2005–2006; MRI-2, 2010–2011). Methods AD pattern similarity (AD-PS) scores, developed by supervised machine learning and validated with MRI data from the Alzheimer’s Disease Neuroimaging Initiative, were used to capture high-dimensional gray matter atrophy in brain areas vulnerable to AD (e.g., amygdala, hippocampus, parahippocampal gyrus, thalamus, inferior temporal lobe areas, and midbrain). Using participants' addresses and air monitoring data, we implemented a spatiotemporal model to estimate 3-year average exposure to PM2.5 preceding MRI-1. General linear models were used to examine the association between PM2.5 and AD-PS scores (baseline and 5-year standardized change), accounting for potential confounders and white matter lesion volumes. Results For 1,365 women 77.9 ± 3.7 years of age in 2005 to 2006, there was no association between PM2.5 and baseline AD-PS score in cross-sectional analyses (β = −0.004; 95% confidence interval [CI] −0.019 to 0.011). Longitudinally, each interquartile range increase of PM2.5 (2.82 µg/m3) was associated with increased AD-PS scores during the follow-up, equivalent to a 24% (hazard ratio 1.24, 95% CI 1.14–1.34) increase in AD risk over 5 years (n = 712, age 77.4 ± 3.5 years). This association remained after adjustment for sociodemographics, intracranial volume, lifestyle, clinical characteristics, and white matter lesions and was present with levels below US regulatory standards (<12 µg/m3). Conclusions Late-life exposure to PM2.5 is associated with increased neuroanatomic risk of AD, which may not be explained by available indicators of cerebrovascular damage.

INTRODUCTION:A data-driven index of dementia risk based on magnetic resonance imaging (MRI), the Alzheimer's Disease Pattern Similarity (AD-PS) score, was estimated for participants in the Atherosclerosis Risk in Communities (ARIC) study.METHODS:AD-PS scores were generated for 839 cognitively non-impaired individuals with a mean follow-up of 4.86 years. The scores and a hypothesis-driven volumetric measure based on several brain regions susceptible to AD were compared as predictors of incident cognitive impairment in different settings.RESULTS:Logistic regression analyses suggest the data-driven AD-PS scores to be more predictive of incident cognitive impairment than its counterpart. Both biomarkers were more predictive of incident cognitive impairment in participants who were White, female, and apolipoprotein E gene (APOE) ε4 carriers. Random forest analyses including predictors from different domains ranked the AD-PS scores as the most relevant MRI predictor of cognitive impairment.CONCLUSIONS:Overall, the AD-PS scores were the stronger MRI-derived predictors of incident cognitive impairment in cognitively non-impaired individuals.

Background Muscle metrics derived from computed tomography (CT) are associated with adverse health events in older persons, but obtaining these metrics using current methods is not practical for large datasets. We developed a fully automated method for muscle measurement on CT images. This study aimed to determine the relationship between muscle measurements on CT with survival in a large multicenter trial of older adults. Method The relationship between baseline paraspinous skeletal muscle area (SMA) and skeletal muscle density (SMD) and survival over 6 years was determined in 6,803 men and 4,558 women (baseline age: 60–69 years) in the National Lung Screening Trial (NLST). The automated machine learning pipeline selected appropriate CT series, chose a single image at T12, and segmented left paraspinous muscle, recording cross-sectional area and density. Associations between SMA and SMD with all-cause mortality were determined using sex-stratified Cox proportional hazards models, adjusted for age, race, height, weight, pack-years of smoking, and presence of diabetes, chronic lung disease, cardiovascular disease, and cancer at enrollment. Results After a mean 6.44 ± 1.06 years of follow-up, 635 (9.33%) men and 265 (5.81%) women died. In men, higher SMA and SMD were associated with a lower risk of all-cause mortality, in fully adjusted models. A one-unit standard deviation increase was associated with a hazard ratio (HR) = 0.85 (95% confidence interval [CI] = 0.79, 0.91; p < .001) for SMA and HR = 0.91 (95% CI = 0.84, 0.98; p = .012) for SMD. In women, the associations did not reach significance. Conclusion Higher paraspinous SMA and SMD, automatically derived from CT exams, were associated with better survival in a large multicenter cohort of community-dwelling older men.

The Comprehensive, Computable NanoString Diagnostic gene panel (C2Dx) is a promising solution to address the need for a molecular pathological research and diagnostic tool for precision oncology utilizing small volume tumor specimens. We translate subtyping-related gene expression patterns of Non-Small Cell Lung Cancer (NSCLC) derived from public transcriptomic data which establish a highly robust and accurate subtyping system. The C2Dx demonstrates supreme performance on the NanoString platform using microgram-level FNA samples and has excellent portability to frozen tissues and RNA-Seq transcriptomic data. This workflow shows great potential for research and the clinical practice of cancer molecular diagnosis.

Patient input into treatment decisions is potentially useful for choices between options, especially for tradeoffs between risk and benefit in the setting of clinical equipoise, such as use of paclitaxel-coated devices. Clinicians lack efficient methods of eliciting patient preferences or applying this information to treatment selection, however. We quantified preferences and values of patients with peripheral artery disease and characterized group-wise preferences using latent class methods. Patients diagnosed with symptomatic peripheral artery disease (either chronic limb-threatening ischemia [CLTI] or claudication) were recruited from three sites and completed a survey-based discrete choice experiment. Theoretical treatments were evaluated on the basis of five treatment attributes (type of treatment, chance of technical success, symptomatic improvement, durability, and risk). Discrete choice machine learning determined part-worth utilities for each attribute summarized as shares of overall importance. Latent class methods were used to identify group-wise values phenotypes. Attributes accounting for a >30% share of overall preference were considered dominant. There were 120 patients who participated (63 with CLTI, 57 with claudication). Group-wise preference weights suggested that durability was more important to patients with CLTI vs those with claudication (Fig 1). Latent class analysis identified three values phenotype clusters within each subgroup (Fig 2). Durability was most important among the largest cluster of CLTI participants (A = 34.2% of overall importance; n = 40) but none of the clusters with claudication. Both subgroups had a cluster for whom technical success was most important (B = 32.7% share; n = 19 for CLTI; and D = 40.1% share; n = 20 for claudication) as well as a small group for whom treatment type was the only important variable (C = 100% share; n = 7 for CLTI; and F = 97.0% share; n = 2 for claudication). Risk accounted for <20% of overall importance within all clusters (range, 0.4%-18.3% among participants with CLTI and 0%-19.6% among those with claudication). Patient preferences are heterogeneous on the basis of disease severity. Durability appears more important to patients with CLTI than to those with claudication. These findings may reflect familiarity with patency loss among patients with CLTI or a durability “blind spot” among patients with claudication. Tradeoffs between technical success and degree of symptomatic improvement are also important. Some patients strongly prefer a specific treatment (or to avoid a specific treatment) regardless of other factors. These phenotypes can be used to identify concordant treatment strategies, communication strategies, and educational resources.Fig 2Preference clusters among patients with symptomatic peripheral artery disease. Latent class analysis identified 3 preference clusters within patients with chronic limb-threatening ischemia (left) and claudication (right). Vertical bars demonstrate relative within-cluster importance by attribute. Icons () indicate participant counts for each cluster.View Large Image Figure ViewerDownload Hi-res image Download (PPT)