skip to main content


Title: Comparing machine and deep learning‐based algorithms for prediction of clinical improvement in psychosis with functional magnetic resonance imaging
Abstract

Previous work using logistic regression suggests that cognitive control‐related frontoparietal activation in early psychosis can predict symptomatic improvement after 1 year of coordinated specialty care with 66% accuracy. Here, we evaluated the ability of six machine learning (ML) algorithms and deep learning (DL) to predict “Improver” status (>20% improvement on Brief Psychiatric Rating Scale [BPRS] total score at 1‐year follow‐up vs. baseline) and continuous change in BPRS score using the same functional magnetic resonance imaging‐based features (frontoparietal activations during the AX‐continuous performance task) in the same sample (individuals with either schizophrenia (n =65, 49M/16F, mean age 20.8 years) or Type I bipolar disorder (n= 17, 9M/8F, mean age 21.6 years)). 138 healthy controls were included as a reference group. “Shallow” ML methods included Naive Bayes, support vector machine, K Star, AdaBoost, J48 decision tree, and random forest. DL included an explainable artificial intelligence (XAI) procedure for understanding results. The best overall performances (70% accuracy for the binary outcome and root mean square error = 9.47 for the continuous outcome) were achieved using DL. XAI revealed left DLPFC activation was the strongest feature used to make binary classification decisions, with a classification activation threshold (adjusted beta = .017) intermediate to the healthy control mean (adjusted beta = .15, 95% CI = −0.02 to 0.31) and patient mean (adjusted beta = −.13, 95% CI = −0.37 to 0.11). Our results suggest DL is more powerful than shallow ML methods for predicting symptomatic improvement. The left DLPFC may be a functional target for future biomarker development as its activation was particularly important for predicting improvement.

 
more » « less
Award ID(s):
1910306
NSF-PAR ID:
10453308
Author(s) / Creator(s):
 ;  ;  
Publisher / Repository:
Wiley Blackwell (John Wiley & Sons)
Date Published:
Journal Name:
Human Brain Mapping
Volume:
42
Issue:
4
ISSN:
1065-9471
Page Range / eLocation ID:
p. 1197-1205
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Importance

    Screening with low-dose computed tomography (CT) has been shown to reduce mortality from lung cancer in randomized clinical trials in which the rate of adherence to follow-up recommendations was over 90%; however, adherence to Lung Computed Tomography Screening Reporting & Data System (Lung-RADS) recommendations has been low in practice. Identifying patients who are at risk of being nonadherent to screening recommendations may enable personalized outreach to improve overall screening adherence.

    Objective

    To identify factors associated with patient nonadherence to Lung-RADS recommendations across multiple screening time points.

    Design, Setting, and Participants

    This cohort study was conducted at a single US academic medical center across 10 geographically distributed sites where lung cancer screening is offered. The study enrolled individuals who underwent low-dose CT screening for lung cancer between July 31, 2013, and November 30, 2021.

    Exposures

    Low-dose CT screening for lung cancer.

    Main Outcomes and Measures

    The main outcome was nonadherence to follow-up recommendations for lung cancer screening, defined as failing to complete a recommended or more invasive follow-up examination (ie, diagnostic dose CT, positron emission tomography–CT, or tissue sampling vs low-dose CT) within 15 months (Lung-RADS score, 1 or 2), 9 months (Lung-RADS score, 3), 5 months (Lung-RADS score, 4A), or 3 months (Lung-RADS score, 4B/X). Multivariable logistic regression was used to identify factors associated with patient nonadherence to baseline Lung-RADS recommendations. A generalized estimating equations model was used to assess whether the pattern of longitudinal Lung-RADS scores was associated with patient nonadherence over time.

    Results

    Among 1979 included patients, 1111 (56.1%) were aged 65 years or older at baseline screening (mean [SD] age, 65.3 [6.6] years), and 1176 (59.4%) were male. The odds of being nonadherent were lower among patients with a baseline Lung-RADS score of 1 or 2 vs 3 (adjusted odds ratio [AOR], 0.35; 95% CI, 0.25-0.50), 4A (AOR, 0.21; 95% CI, 0.13-0.33), or 4B/X, (AOR, 0.10; 95% CI, 0.05-0.19); with a postgraduate vs college degree (AOR, 0.70; 95% CI, 0.53-0.92); with a family history of lung cancer vs no family history (AOR, 0.74; 95% CI, 0.59-0.93); with a high age-adjusted Charlson Comorbidity Index score (≥4) vs a low score (0 or 1) (AOR, 0.67; 95% CI, 0.46-0.98); in the high vs low income category (AOR, 0.79; 95% CI, 0.65-0.98); and referred by physicians from pulmonary or thoracic-related departments vs another department (AOR, 0.56; 95% CI, 0.44-0.73). Among 830 eligible patients who had completed at least 2 screening examinations, the adjusted odds of being nonadherent to Lung-RADS recommendations at the following screening were increased in patients with consecutive Lung-RADS scores of 1 to 2 (AOR, 1.38; 95% CI, 1.12-1.69).

    Conclusions and Relevance

    In this retrospective cohort study, patients with consecutive negative lung cancer screening results were more likely to be nonadherent with follow-up recommendations. These individuals are potential candidates for tailored outreach to improve adherence to recommended annual lung cancer screening.

     
    more » « less
  2. Background

    Recently, there has been mounting evidence suggesting the efficacy of steroid‐eluting stents (SES) for management of chronic rhinosinusitis after endoscopic sinus surgery (ESS). This meta‐analysis serves to evaluate the efficacy of SES in improving postoperative outcomes after ESS.

    Methods

    A systematic literature search was performed of PubMed for articles published between 1985 and 2018. The outcome variables were reported at, on average, 30 days postintervention.

    Results

    Seven of the 76 published studies, all of which were industry‐sponsored, were included for a collective cohort of 444 SES and 444 control sinuses. In patients who received SES vs controls, collective odds ratios (ORs) for postoperative need for intervention, surgery, and oral steroid were 0.45 (95% confidence interval [CI], 0.33‐0.62;p< 0.001), 0.30 (95% CI, 0.18‐0.52;p< 0.001), and 0.58 (95% CI, 0.40‐0.84;p= 0.004), respectively. In addition, collective ORs for frontal sinus ostia (FSO) patency, moderate‐to‐severe adhesion/scarring, and increase in polyp score were 2.53 (95% CI, 1.61‐3.97;p< 0.001), 0.28 (95% CI, 0.13‐0.59;p< 0.001), and 0.42 (95% CI, 0.25‐0.74;p= 0.002), respectively. Collective mean differences for FSO/ethmoid inflammation and FSO diameter were −10.86 mm (p< 0.001) and +1.34 mm (p< 0.001), respectively.

    Conclusion

    Aggregate evidence suggests that SES can improve ESS outcomes by reducing rates of postoperative intervention and recurrent polyposis and inflammation, while promoting FSO patency. All included and analyzed studies were industry‐sponsored and ruling‐out publication bias was not possible. Future independent and nonsponsored studies to further evaluate SES's long‐term efficacy are warranted.

     
    more » « less
  3. Abstract Objective

    Common obesity‐associated genetic variants at the fat mass and obesity‐associated (FTO) locus have been associated with appetitive behaviors and altered structure and function of frontostriatal brain regions. The authors aimed to investigate the influence ofFTOvariation on frontostriatal appetite circuits in early life.

    Methods

    Data were drawn from RESONANCE, a longitudinal study of early brain development. Growth trajectories of nucleus accumbens and frontal lobe volumes, as well as total gray matter and white matter volume, by risk allele (AA) carrier status onFTOsingle‐nucleotide polymorphism rs9939609 were examined in 228 children (102 female, 126 male) using magnetic resonance imaging assessments obtained from infancy through middle childhood. The authors fit functional concurrent regression models with brain volume outcomes over age as functional responses, andFTOgenotype, sex, BMIzscore, and maternal education were included as predictors.

    Results

    Bootstrap pointwise 95% CI for regression coefficient functions in the functional concurrent regression models showed that the AA group versus the group with no risk allele (TT) had greater nucleus accumbens volume (adjusted for total brain volume) in the interval of 750 to 2250 days (2–6 years).

    Conclusions

    These findings suggest that common genetic risk for obesity is associated with differences in early development of brain reward circuitry and argue for investigating dynamic relationships among genotype, brain, behavior, and weight throughout development.

     
    more » « less
  4. Abstract

    The human spleen contracts in response to stress‐induced catecholamine secretion, resulting in a temporary rise in haemoglobin concentration ([Hb]). Recent findings highlighted enhanced splenic response to exercise at high altitude in Sherpa, possibly due to a blunted splenic response to hypoxia. To explore the potential blunted splenic contraction in Sherpas at high altitude, we examined changes in spleen volume during hyperoxic breathing, comparing acclimatized Sherpa with acclimatized individuals of lowland ancestry. Our study included 14 non‐Sherpa (7 female) residing at altitude for a mean continuous duration of 3 months and 46 Sherpa (24 female) with an average of 4 years altitude exposure. Participants underwent a hyperoxic breathing test at altitude (4300 m; barrometric pressure = ∼430 torr;  = ∼90 torr). Throughout the test, we measured spleen volume using ultrasonography and monitored oxygen saturation (). During rest, Sherpa exhibited larger spleens (226 ± 70 mL) compared to non‐Sherpa (165 ± 34 mL;P < 0.001; effect size (ES) = 0.95, 95% CI: 0.3–1.6). In response to hyperoxia, non‐Sherpa demonstrated 22 ± 12% increase in spleen size (35 ± 17 mL, 95% CI: 20.7–48.9;P < 0.001; ES = 1.8, 95% CI: 0.93–2.66), while spleen size remained unchanged in Sherpa (−2 ± 13 mL, 95% CI: −2.4 to 7.3;P = 0.640; ES = 0.18, 95% CI: −0.10 to 0.47). Our findings suggest that Sherpa and non‐Sherpas of lowland ancestry exhibit distinct variations in spleen volume during hyperoxia at high altitude, potentially indicating two distinct splenic functions. In Sherpa, this phenomenon may signify a diminished splenic response to altitude‐related hypoxia at rest, potentially contributing to enhanced splenic contractions during physical stress. Conversely, non‐Sherpa experienced a transient increase in spleen size during hyperoxia, indicating an active tonic contraction, which may influence early altitude acclimatization in lowlanders by raising [Hb].

     
    more » « less
  5. Abstract During the Coronavirus Disease 2019 (COVID-19) epidemic, many health professionals used social media to promote preventative health behaviors. We conducted a randomized controlled trial of the effect of a Facebook advertising campaign consisting of short videos recorded by doctors and nurses to encourage users to stay at home for the Thanksgiving and Christmas holidays ( NCT04644328 and AEARCTR-0006821 ). We randomly assigned counties to high intensity ( n  = 410 (386) at Thanksgiving (Christmas)) or low intensity ( n  = 410 (381)). The intervention was delivered to a large fraction of Facebook subscribers in 75% and 25% of randomly assigned zip codes in high- and low-intensity counties, respectively. In total, 6,998 (6,716) zip codes were included, and 11,954,109 (23,302,290) users were reached at Thanksgiving (Christmas). The first two primary outcomes were holiday travel and fraction leaving home, both measured using mobile phone location data of Facebook users. Average distance traveled in high-intensity counties decreased by −0.993 percentage points (95% confidence interval (CI): –1.616, −0.371; P = 0.002) for the 3 days before each holiday compared to low-intensity counties. The fraction of people who left home on the holiday was not significantly affected (adjusted difference: 0.030; 95% CI: −0.361, 0.420; P = 0.881). The third primary outcome was COVID-19 infections recorded at the zip code level in the 2-week period starting 5 days after the holiday. Infections declined by 3.5% (adjusted 95% CI: −6.2%, −0.7%; P = 0.013) in intervention compared to control zip codes. Social media messages recorded by health professionals before the winter holidays in the United States led to a significant reduction in holiday travel and subsequent COVID-19 infections. 
    more » « less