ABSTRACT
Decrease in cognitive performance after sleep deprivation followed by recovery after sleep suggests its key role, and especially non-rapid eye movement (NREM) sleep, in the maintenance of cognition. It remains unknown whether brain network reorganization in NREM sleep stages N2 and N3 can uniquely be mapped onto individual differences in cognitive performance after a recovery nap following sleep deprivation. Using resting state functional magnetic resonance imaging (fMRI), we quantified the integration and segregation of brain networks during NREM sleep stages N2 and N3 while participants took a 1-hour nap following 24-hour sleep deprivation, compared to well-rested wakefulness. Here, we advance a new analytic framework called the hierarchical segregation index (HSI) to quantify network segregation across spatial scales, from whole-brain to the voxel level, by identifying spatio-temporally overlapping large-scale networks and the corresponding voxel-to-region hierarchy. Our results show that network segregation increased in the default mode, dorsal attention and somatomotor networks during NREM sleep compared to wakefulness. Segregation within the visual, limbic, and executive control networks exhibited N2 versus N3 sleep-specific voxel-level patterns. More segregation during N3 was associated with worse recovery of working memory, executive attention, and psychomotor vigilance after the nap. The level of spatial resolution of network segregation varied among brain regions and was associated with the recovery of performance in distinct cognitive tasks. We demonstrated the sensitivity and reliability of voxel-level HSI to provide key insights into within-region variation, suggesting a mechanistic understanding of how NREM sleep replenishes cognition after sleep deprivation.
ABSTRACT
With promising artificial intelligence (AI) algorithms receiving FDA clearance, the potential impact of these models on clinical outcomes must be evaluated locally before their integration into routine workflows. Robust validation infrastructures are pivotal to inspecting the accuracy and generalizability of these deep learning algorithms to ensure both patient safety and health equity. Protected health information concerns, intellectual property rights, and diverse requirements of models impede the development of rigorous external validation infrastructures. The authors propose various suggestions for addressing the challenges associated with the development of efficient, customizable, and cost-effective infrastructures for the external validation of AI models at large medical centers and institutions. The authors present comprehensive steps to establish an AI inferencing infrastructure outside clinical systems to examine the local performance of AI algorithms before health practice or systemwide implementation and promote an evidence-based approach for adopting AI models that can enhance radiology workflows and improve patient outcomes.
ABSTRACT
Sleep is essential for optimal functioning and health. Interconnected to multiple biological, psychological and socio-environmental factors (i.e., biopsychosocial factors), the multidimensional nature of sleep is rarely capitalized on in research. Here, we deployed a data-driven approach to identify sleep-biopsychosocial profiles that linked self-reported sleep patterns to inter-individual variability in health, cognition, and lifestyle factors in 770 healthy young adults. We uncovered five profiles, including two profiles reflecting general psychopathology associated with either reports of general poor sleep or an absence of sleep complaints (i.e., sleep resilience) respectively. The three other profiles were driven by the use of sleep aids and social satisfaction, sleep duration and cognitive performance, and sleep disturbance linked to cognition and mental health. Furthermore, identified sleep-biopsychosocial profiles displayed unique patterns of brain network organization. In particular, somatomotor network connectivity alterations were involved in the relationships between sleep and biopsychosocial factors. These profiles can potentially untangle the interplay between individuals' variability in sleep, health, cognition and lifestyle - equipping research and clinical settings to better support individual's well-being.
ABSTRACT
Sleep is essential for optimal functioning and health. Interconnected to multiple biological, psychological and socio-environmental factors (i.e., biopsychosocial factors), the multidimensional nature of sleep is rarely capitalized on in research. Here, we deployed a data-driven approach to identify sleep-biopsychosocial profiles that linked self-reported sleep patterns to inter-individual variability in health, cognition, and lifestyle factors in 770 healthy young adults. We uncovered five profiles, including two profiles reflecting general psychopathology associated with either reports of general poor sleep or an absence of sleep complaints (i.e., sleep resilience) respectively. The three other profiles were driven by sedative-hypnotics-use and social satisfaction, sleep duration and cognitive performance, and sleep disturbance linked to cognition and mental health. Furthermore, identified sleep-biopsychosocial profiles displayed unique patterns of brain network organization. In particular, somatomotor network connectivity alterations were involved in the relationships between sleep and biopsychosocial factors. These profiles can potentially untangle the interplay between individuals' variability in sleep, health, cognition and lifestyle - equipping research and clinical settings to better support individual's well-being.
ABSTRACT
PURPOSE: Osteoporotic vertebral compression fractures (OVCFs) are a highly prevalent source of morbidity and mortality, and preventive treatment has been demonstrated to be both effective and cost effective. To take advantage of the information available on existing chest and abdominal radiographs, the authors' study group has developed software to access these radiographs for OVCFs with high sensitivity and specificity using an established artificial intelligence deep learning algorithm. The aim of this analysis was to assess the potential cost-effectiveness of implementing this software. METHODS: A deterministic expected-value cost-utility model was created, combining a tree model and a Markov model, to compare the strategies of opportunistic screening for OVCFs against usual care. Total costs and total quality-adjusted life-years were calculated for each strategy. Screening and treatment costs were considered from a limited societal perspective, at 2022 prices. RESULTS: In the base case, assuming a cost of software implantation of $10 per patient screened, the screening strategy dominated the nonscreening strategy: it resulted in lower cost and increased quality-adjusted life-years. The lower cost was due primarily to the decreased costs associated with fracture treatment and decreased probability of requiring long-term care in patients who received preventive treatment. The screening strategy was dominant up to a cost of $46 per patient screened. CONCLUSIONS: Artificial intelligence-based opportunistic screening for OVCFs on existing radiographs can be cost effective from a societal perspective.
ABSTRACT
STUDY OBJECTIVE: To provide a comprehensive assessment of sleep state misperception in insomnia disorder (INS) and good sleepers (GS) by comparing recordings performed for one night in-lab (PSG and night review) and during several nights at-home (actigraphy and sleep diaries). METHODS: Fifty-seven INS and 29 GS wore an actigraphy device and filled a sleep diary for two weeks at-home. They subsequently completed a PSG recording and filled a night review in-lab. Sleep perception index (subjective/objective × 100) of sleep onset latency (SOL), sleep duration (TST) and wake duration (TST) were computed and compared between methods and groups. RESULTS: GS displayed a tendency to overestimate TST and WASO but correctly perceived SOL. The degree of misperception was similar across methods within the GS group. In contrast, INS underestimated their TST and overestimated their SOL both in-lab and at-home, yet the severity of misperception of SOL was larger at-home than in-lab. Finally, INS overestimated WASO only in-lab while correctly perceiving it at-home. While only the degree of TST misperception was stable across methods in INS, misperception of SOL and WASO were dependent on the method used. CONCLUSIONS: We found that GS and INS exhibit opposite patterns and severity of sleep misperception. While the degree of misperception in GS was similar across methods, only sleep duration misperception was reliably detected by both in-lab and at-home methods in INS. Our results highlight that, when assessing sleep misperception in insomnia disorder, the environment and method of data collection should be carefully considered.
Subject(s)
Actigraphy , Sleep Initiation and Maintenance Disorders , Humans , Polysomnography/methods , Actigraphy/methods , Sleep Initiation and Maintenance Disorders/diagnosis , Sleep , Sleep LatencyABSTRACT
Cross-frequency coupling (CFC) between brain oscillations during non-rapid-eye-movement (NREM) sleep (e.g. slow oscillations [SO] and spindles) may be a neural mechanism of overnight memory consolidation. Declines in CFC across the lifespan might accompany coinciding memory problems with ageing. However, there are few reports of CFC changes during sleep after learning in older adults, controlling for baseline effects. Our objective was to examine NREM CFC in healthy older adults, with an emphasis on spindle activity and SOs from frontal electroencephalogram (EEG), during a learning night after a declarative learning task, as compared to a baseline night without learning. Twenty-five older adults (M [SD] age = 69.12 [5.53] years; 64% female) completed a two-night study, with a pre- and post-sleep word-pair associates task completed on the second night. SO-spindle coupling strength and a measure of coupling phase distance from the SO up-state were both examined for between-night differences and associations with memory consolidation. Coupling strength and phase distance from the up-state peak were both stable between nights. Change in coupling strength between nights was not associated with memory consolidation, but a shift in coupling phase towards (vs. away from) the up-state peak after learning predicted better memory consolidation. Also, an exploratory interaction model suggested that associations between coupling phase closer to the up-state peak and memory consolidation may be moderated by higher (vs. lower) coupling strength. This study supports a role for NREM CFC in sleep-related memory consolidation in older adults.
Subject(s)
Memory Consolidation , Humans , Female , Male , Aged , Sleep , Learning , Sleep, REM , ElectroencephalographyABSTRACT
A 16-month-old neutered male domestic shorthair cat weighing 2.7 kg was referred for further evaluation of acute generalized muscle weakness and paraparesis after a long-standing history of polyuria-polydipsia. The diagnosis of hypodipsic/adipsic hypernatremia relied on the key findings of absent spontaneous drinking despite hypernatremia and a hyperosmolar state (444.8 mOsm/kg, reference interval 280 to 310 mOsm/kg). Brain MRI revealed severe multifocal anatomic anomalies of the rostral calvarium and the forebrain, suggestive of encephaloclastic porencephaly. Involvement of the thalamic and hypothalamic regions could have been responsible for the cat's adipsic hypernatremia. The unique aspects of this case were the rare description of central nervous system disease leading to hypodipsia, and the history of chronic polydipsia before the acute onset of hypodipsia. Key clinical message: Multifocal abnormalities of the forebrain can present with polyuria-polydipsia syndrome, hypodipsia/adipsia, or both, depending on the stage of the disease. This likely happens when the hypothalamic and thalamic regions are affected, since they regulate antidiuretic hormone release and thirst, respectively.
Hypernatrémie hypodipsique après polydipsie ancienne chez un chat suspect de traumatisme crânien néonatal. Un chat domestique à poil court mâle castré âgé de 16 mois et pesant 2,7 kg a été référé pour une évaluation plus approfondie de faiblesse musculaire aiguë généralisée et de paraparésie après une longue histoire de polyurie-polydipsie. Le diagnostic d'hypernatrémie hypodipsique/adipsique reposait sur les principales conclusions de l'absence d'abreuvement spontané malgré l'hypernatrémie et un état hyperosmolaire (444,8 mOsm/kg, intervalle de référence de 280 à 310 mOsm/kg). L'IRM du cerveau a révélé des anomalies anatomiques multifocales sévères de la calotte crânienne rostrale et du prosencéphale évoquant une porencéphalie encéphaloclastique. L'atteinte des régions thalamique et hypothalamique pourrait être responsable de l'hypernatrémie adipsique du chat. Les aspects uniques de ce cas étaient la description rare d'une maladie du système nerveux central conduisant à l'hypodipsie, et l'histoire de la polydipsie chronique avant l'apparition aiguë de l'hypodipsie.Message clinique clé :Les anomalies multifocales du cerveau antérieur peuvent présenter un syndrome de polyurie-polydipsie, une hypodipsie/adipsie, ou les deux, selon le stade de la maladie. Cela se produit probablement lorsque les régions hypothalamique et thalamique sont affectées, car elles régulent respectivement la libération d'hormone antidiurétique et la soif.(Traduit par Dr Serge Messier).
Subject(s)
Cat Diseases , Craniocerebral Trauma , Hypernatremia , Male , Cats , Animals , Hypernatremia/diagnosis , Hypernatremia/veterinary , Polyuria/etiology , Polyuria/veterinary , Thirst , Polydipsia/diagnosis , Polydipsia/etiology , Polydipsia/veterinary , Craniocerebral Trauma/veterinary , Cat Diseases/diagnosisABSTRACT
BACKGROUND: Whether obstructive sleep apnea (OSA) increases the risk of cognitive decline and how sex and age influence this association is not clear. Here, we characterized the sex- and age-specific associations between OSA risk and 3-year cognitive change in middle-aged and older adults. METHODS: We included 24,819 participants aged 45-85 (52% women) from the Canadian Longitudinal Study on Aging. OSA risk was measured at baseline using the STOP combined to body mass index (STOP-B). Neuropsychological tests assessed memory, executive functioning, and psychomotor speed at baseline and at 3-year follow-up. We conducted age- and sex-specific linear mixed models to estimate the predictive role of baseline STOP-B score on 3-year cognitive change. RESULTS: Men at high-risk for OSA aged 45-59 years showed a steeper decline in psychomotor speed (+13.2 [95% CI: -1.6, 27.9]) compared to men at low-risk. Men at high-risk for OSA aged 60-69 showed a steeper decline in mental flexibility (-1.2 [-1.9, -0.5]) and processing speed (+0.6 [0.3, 0.9]) than those at low-risk. Women at high-risk for OSA aged 45-59 showed a steeper decline in processing speed (+0.1 [-0.2, 0.4]) than women at low-risk, while women at high-risk ≥70 years had a steeper decline in memory (-0.2 [-0.6, 0.1]) and processing speed (+1.0 [0.4, 1.5]). CONCLUSIONS: Associations between OSA risk and cognitive decline over 3 years depend on age and sex. Being at high-risk for OSA is associated with a generalized cognitive decline in attention and processing speed, while a memory decline is specific to older women (≥70 years).
Subject(s)
Cognitive Dysfunction , Sleep Apnea, Obstructive , Aged , Female , Humans , Male , Middle Aged , Aging , Canada/epidemiology , Cognition , Cognitive Dysfunction/complications , Longitudinal Studies , Sleep Apnea, Obstructive/complications , Sleep Apnea, Obstructive/epidemiology , Aged, 80 and overABSTRACT
RATIONALE AND OBJECTIVES: Spinal osteoporotic compression fractures (OCFs) can be an early biomarker for osteoporosis but are often subtle, incidental, and underreported. To ensure early diagnosis and treatment of osteoporosis, we aimed to build a deep learning vertebral body classifier for OCFs as a critical component of our future automated opportunistic screening tool. MATERIALS AND METHODS: We retrospectively assembled a local dataset, including 1790 subjects and 15,050 vertebral bodies (thoracic and lumbar). Each vertebral body was annotated using an adaption of the modified-2 algorithm-based qualitative criteria. The Osteoporotic Fractures in Men (MrOS) Study dataset provided thoracic and lumbar spine radiographs of 5994 men from six clinical centers. Using both datasets, five deep learning algorithms were trained to classify each individual vertebral body of the spine radiographs. Classification performance was compared for these models using multiple metrics, including the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, and positive predictive value (PPV). RESULTS: Our best model, built with ensemble averaging, achieved an AUC-ROC of 0.948 and 0.936 on the local dataset's test set and the MrOS dataset's test set, respectively. After setting the cutoff threshold to prioritize PPV, this model achieved a sensitivity of 54.5% and 47.8%, a specificity of 99.7% and 99.6%, and a PPV of 89.8% and 94.8%. CONCLUSION: Our model achieved an AUC-ROC>0.90 on both datasets. This testing shows some generalizability to real-world clinical datasets and a suitable performance for a future opportunistic osteoporosis screening tool.
Subject(s)
Deep Learning , Fractures, Compression , Osteoporosis , Spinal Fractures , Male , Humans , Fractures, Compression/diagnostic imaging , Retrospective Studies , Bone Density , Spinal Fractures/diagnostic imaging , Osteoporosis/complications , Osteoporosis/diagnostic imaging , Lumbar Vertebrae/diagnostic imaging , AlgorithmsABSTRACT
STUDY OBJECTIVES: To compare overnight declarative memory consolidation and non-rapid eye movement (NREM) sleep electroencephalogram (EEG) oscillations in older adults with obstructive sleep apnea (OSA) to a control group and assess slow-wave activity (SWA) and sleep spindles as correlates of memory consolidation. METHODS: Forty-six older adults (24 without OSA and 22 with OSA) completed a word-pair associate's declarative memory task before and after polysomnography. Recall and recognition were expressed as a percentage of the morning relative to evening scores. Power spectral analysis was performed on EEG recorded at frontal (F3-M2, F4-M1) and central (C3-M2, C4-M1) sites. We calculated NREM absolute slow oscillation (0.25-1 Hz) and delta (0.5-4.5 Hz) EEG power, and slow (11-13 Hz) spindle density (number of events per minute of N2 sleep) and fast (13-16 Hz) spindle density. RESULTS: There were no significant differences in overnight recall and recognition between OSA (mean age 58.7 ± 7.1 years, apnea-hypopnea index (AHI) 41.9 ± 29.7 events/hour) and non-OSA (age 61.1 ± 10.3 years, AHI 6.6 ± 4.2 events/hour) groups. The OSA group had lower fast spindle density in the frontal region (p = 0.007). No between-group differences in SWA were observed. In the Control group, overnight recognition positively correlated with slow spindle density in frontal (rho = 0.555, p = 0.020) and central regions (rho = 0.490, p = 0.046). Overnight recall was not related to SWA or spindle measures in either group. CONCLUSIONS: Older adults with OSA had deficits in fast sleep spindles but showed preserved overnight declarative memory consolidation. It is possible that compensatory mechanisms are being recruited by OSA patients to preserve declarative memory consolidation despite the presence of sleep spindle deficits.
Subject(s)
Memory Consolidation , Sleep Apnea, Obstructive , Humans , Aged , Middle Aged , Eye Movements , Sleep , ElectroencephalographyABSTRACT
PURPOSE: Many MRI sequences are sensitive to motion and its associated artifacts. The linearized geometric solution (LGS), a balanced steady-state free precession (bSSFP) off-resonance signal demodulation technique, is evaluated with respect to motion artifact resilience. THEORY AND METHODS: The mechanism and extent of LGS motion artifact resilience is examined in simulated, flow phantom, and in vivo clinical imaging. Motion artifact correction capabilities are decoupled from susceptibility artifact correction when feasible to permit controlled analysis of motion artifact correction when comparing the LGS with standard and phase-cycle-averaged (complex sum) bSSFP imaging. RESULTS: Simulations reveal that the LGS demonstrates motion artifact reduction capabilities similar to standard clinical bSSFP imaging techniques, with slightly greater resilience in high SNR regions and for shorter-duration motion. Flow phantom experiments assert that the LGS reduces shorter-duration motion artifact error by â¼24%-65% relative to the complex sum, whereas reconstructions exhibit similar error reduction for constant motion. In vivo analysis demonstrates that in the internal auditory canal/orbits, the LGS was deemed to have less artifact in 24%/49% and similar artifact in 76%/51% of radiological assessments relative to the complex sum, and the LGS had less artifact in 97%/81% and similar artifact in 3%/16% of assessments relative to standard bSSFP. Only 2 of 63 assessments deemed the LGS inferior to either complex sum or standard bSSFP in terms of artifact reduction. CONCLUSION: The LGS provides sufficient bSSFP motion artifact resilience to permit robust elimination of susceptibility artifacts, inspiring its use in a wide variety of applications.
Subject(s)
Image Enhancement , Image Interpretation, Computer-Assisted , Image Enhancement/methods , Image Interpretation, Computer-Assisted/methods , Algorithms , Artifacts , Magnetic Resonance Imaging/methods , Phantoms, ImagingABSTRACT
STUDY OBJECTIVES: To examine the longitudinal association between probable insomnia status and both subjective and objective memory decline in middle-aged and older adults. METHODS: 26 363 participants, ≥45 years, completed baseline and follow-up (3 years after baseline) self-reported evaluations of sleep and memory, and neuropsychological testing in the following cognitive domains: memory, executive functions, and psychomotor speed. Participants were categorized as having probable insomnia disorder (PID), insomnia symptoms only (ISO), or no insomnia symptoms (NIS), based on sleep questionnaires. Participants were further grouped based on their sleep change over time. Prospective odds of self-reported memory worsening were assessed using logistic regression, and associations between insomnia and cognitive performance were assessed via linear mixed-effects modeling, adjusted for demographic, lifestyle, and medical factors. RESULTS: An increased odds (OR 1.70; 95% CI 1.29-2.26) of self-reported memory worsening was observed for NIS participants at baseline who developed PID at follow-up compared to those who developed ISO or remained NIS. Additionally, participants whose sleep worsened from baseline to follow-up (i.e. transitioned from NIS to ISO, ISO to PID, or NIS to PID) displayed increased odds (OR 1.22; 95% CI 1.10-1.34) of subjective memory worsening at follow-up compared to those who remained insomnia-free or improved their sleep. There were no significant associations between the development of PID or worsening sleep and performance on neuropsychological tests. CONCLUSIONS: These findings of an increased odds for subjective memory decline in middle-aged and older adults with insomnia disorder suggest insomnia may be an important target for early interventions addressing age-related cognitive decline.
Subject(s)
Sleep Initiation and Maintenance Disorders , Middle Aged , Humans , Aged , Sleep Initiation and Maintenance Disorders/complications , Sleep Initiation and Maintenance Disorders/epidemiology , Longitudinal Studies , Prospective Studies , Cognition , Canada , Aging , Memory Disorders/complicationsABSTRACT
STUDY OBJECTIVES: To assess the effects of Cognitive Behavioral Therapy for insomnia (CBTi) on subjective and objective measures of sleep, sleep-state misperception and cognitive performance. METHODS: We performed a randomized-controlled trial with a treatment group and a wait-list control group to assess changes in insomnia symptoms after CBTi (8 weekly group sessions/3 months) in 62 participants with chronic insomnia. To this end, we conducted a multimodal investigation of sleep and cognition including subjective measures of sleep difficulties (Insomnia Severity Index [ISI]; sleep diaries) and cognitive functioning (Sahlgrenska Academy Self-reported Cognitive Impairment Questionnaire), objective assessments of sleep (polysomnography recording), cognition (attention and working memory tasks), and sleep-state misperception measures, collected at baseline and at 3-months post-randomization. We also assessed ISI one year after CBTi. Our main analysis investigated changes in sleep and cognition after 3 months (treatment versus wait-list). RESULTS: While insomnia severity decreased and self-reported sleep satisfaction improved after CBTi, we did not find any significant change in objective and subjective sleep measures (e.g., latency, duration). Degree of discrepancy between subjective and objective sleep (i.e., sleep misperception) in sleep latency and sleep duration decreased after CBTi suggesting a better perception of sleep after CBTi. In contrast, both objective and subjective cognitive functioning did not improve after CBTi. CONCLUSIONS: We showed that group-CBTi has a beneficial effect on variables pertaining to the subjective perception of sleep, which is a central feature of insomnia. However, we observed no effect of CBTi on measures of cognitive functioning.
Subject(s)
Cognitive Behavioral Therapy , Sleep Initiation and Maintenance Disorders , Cognition , Humans , Sleep , Sleep Initiation and Maintenance Disorders/therapy , Treatment OutcomeABSTRACT
Determining the prevalence and characteristics of individuals susceptible to present with obstructive sleep apnea (OSA) is essential for developing targeted and efficient prevention and screening strategies. We included 27,210 participants aged ≥45 years old (50.3% women) from the Canadian Longitudinal Study on Aging. Using the STOP questionnaire combined to the percentage of body fat (%BF), we estimated the prevalence of individuals at high-risk for OSA in a sex and age-specific manner, and tested the relation with comorbidities, menopause and systemic inflammation. The prevalence was 17.5%, and was lower in women (13.1%) than in men (21.9%). A high level of high-sensitivity C-reactive protein was the strongest factor associated with OSA risk and this association was 1.3-2.3 times higher in women than in men. OSA risk increased with age, cardiovascular diseases, diabetes mellitus, anxio-depressive symptoms, asthma and arthritis. In women, post-menopausal status was associated with a high OSA risk. Nearly 1 adult out of 5 older than 45 is at risk for OSA in Canada. Comorbidities, menopause and systemic inflammation, more than age, explain increased OSA prevalence. Considering this high prevalence and associations with medical and mental comorbidities, health care practitioners should incorporate systematic OSA screening in their clinical procedures.
Subject(s)
Sleep Apnea, Obstructive , Aged , Aging , Canada/epidemiology , Female , Humans , Inflammation/complications , Longitudinal Studies , Male , Middle Aged , Prevalence , Risk Factors , Sleep Apnea, Obstructive/complicationsABSTRACT
RATIONALE AND OBJECTIVES: Osteoporosis affects 9% of individuals over 50 in the United States and 200 million women globally. Spinal osteoporotic compression fractures (OCFs), an osteoporosis biomarker, are often incidental and under-reported. Accurate automated opportunistic OCF screening can increase the diagnosis rate and ensure adequate treatment. We aimed to develop a deep learning classifier for OCFs, a critical component of our future automated opportunistic screening tool. MATERIALS AND METHODS: The dataset from the Osteoporotic Fractures in Men Study comprised 4461 subjects and 15,524 spine radiographs. This dataset was split by subject: 76.5% training, 8.5% validation, and 15% testing. From the radiographs, 100,409 vertebral bodies were extracted, each assigned one of two labels adapted from the Genant semiquantitative system: moderate to severe fracture vs. normal/trace/mild fracture. GoogLeNet, a deep learning model, was trained to classify the vertebral bodies. The classification threshold on the predicted probability of OCF outputted by GoogLeNet was set to prioritize the positive predictive value (PPV) while balancing it with the sensitivity. Vertebral bodies with the top 0.75% predicted probabilities were classified as moderate to severe fracture. RESULTS: Our model yielded a sensitivity of 59.8%, a PPV of 91.2%, and an F1 score of 0.72. The areas under the receiver operating characteristic curve (AUC-ROC) and the precision-recall curve were 0.99 and 0.82, respectively. CONCLUSION: Our model classified vertebral bodies with an AUC-ROC of 0.99, providing a critical component for our future automated opportunistic screening tool. This could lead to earlier detection and treatment of OCFs.
Subject(s)
Deep Learning , Fractures, Compression , Osteoporosis , Spinal Fractures , Male , Female , Humans , Fractures, Compression/diagnostic imaging , Spinal Fractures/diagnostic imaging , Osteoporosis/diagnostic imaging , RadiographyABSTRACT
BACKGROUND: The association between obstructive sleep apnea and cognitive functioning is not yet fully understood and could be influenced by factors such as sex, age and systemic inflammation. We determined the sex- and age-specific association between obstructive sleep apnea risk and cognitive performance, and the influence of systemic inflammation on this association. METHODS: We included 25,899 participants from the Canadian Longitudinal Study of Aging comprehensive cohort, aged 45-85 years (51% women). We conducted sex- and age-specific (45-59; 60-69; ≥70) general linear models between obstructive sleep apnea risk and cognitive scores, and tested the moderating and mediating effects of high-sensitivity C-reactive protein levels. Obstructive sleep apnea risk was estimated by combining the STOP and whole-body fat percentage. Cognitive tests assessed episodic verbal memory, executive functions and psychomotor speed. Levels of high-sensitivity C-reactive protein were obtained through blood samples. RESULTS: Higher obstructive sleep apnea risk was associated with poorer episodic memory in women aged 45-59 years, and poorer executive function (p < 0.05 on multiple tests) in women aged 45-59 and 60-69 years. No such association was found in men. High-sensitivity C-reactive protein levels mediated some associations between obstructive sleep apnea risk and executive function in women and men aged <70 years. CONCLUSIONS: Being at high-risk for obstructive sleep apnea is associated with poorer cognition in women aged <70 years. These associations were partly mediated by systemic inflammation. These results underscore the importance of obstructive sleep apnea diagnosis, treatment and appropriate follow-up, particularly in middle-aged women who might already show signs of early cognitive impairments.
Subject(s)
C-Reactive Protein , Sleep Apnea, Obstructive , Aging , Canada/epidemiology , Cognition , Female , Humans , Inflammation/complications , Longitudinal Studies , Male , Memory Disorders/complications , Middle Aged , Sleep Apnea, Obstructive/complications , Sleep Apnea, Obstructive/diagnosis , Sleep Apnea, Obstructive/epidemiologyABSTRACT
OBJECTIVE: This study aimed to assess the changes and values on follow-up computed tomography (F/U-CT) for isolated falcine (F-SDH) and tentorial (T-SDH) subdural hematomas (SDHs). METHOD: Fifty-four cases of isolated F-SDH and/or T-SDH were retrospectively reviewed. Subdural hematoma morphology, mass effect on the adjacent parenchyma, and interval change at F/U-CT were evaluated. Subdural hematoma size was measured parallel and perpendicular to the falx/tentorium (long or short axis, respectively). RESULTS: Short-axis increase on F/U-CT was seen only in 5 F-SDHs (16%) and 7 T-SDHs (19%), with a maximum of a 2-mm increase. Long-axis growth was more prominent and frequent, seen in 18 F-SDH patients (56.2%) and 19 T-SDH patients (51.4%), with maximum change of up to 43 mm. Falcine SDH and T-SDH were ipsilateral and contiguous in 77.8% of patients. Minimal mass effect was seen in 13 patients (24.1%), which was resolved or stable on F/U-CT. Anticoagulation did not affect SDH size. No patients required neurosurgery or died. CONCLUSIONS: Based on our limited data, the current standard of F/U-CT may be unnecessary in patients with isolated F-SDH and/or T-SDH, which expand minimally along the short axis without a significant mass effect. Characteristic anatomic structure of the tentorium and falx, and their connectivity may direct SDH expansion and limit mass effect as well as injury to the adjacent parenchyma.
Subject(s)
Dura Mater/diagnostic imaging , Hematoma, Subdural/diagnostic imaging , Tomography, X-Ray Computed/methods , Humans , Retrospective StudiesABSTRACT
"Big data" has changed the way businesses operate in finance, insurance, communications, manufacturing, and logistics, with companies reporting successful outcomes from the implementation of data-driven analytics. Health care has slowly started leveraging big data analysis to identify more cost-efficient and effective care for patients. Business intelligence software aims to help with this transition, converting large data sets into useful, actionable information. Radiology practices have used business intelligence toolkits in the past to increase reading room productivity, scanner efficiency, and patient throughput. Although these tactics have driven down costs and increased volumes, an essential aspect of radiology practice growth-consumer satisfaction-remains largely unexplored. The first commandment of marketing is "know thy customer," which is the key to increasing radiology's value to referring clinicians who use our services. Our article explores the business case behind a basic business intelligence model, giving any radiologist the instruments to access and draw business conclusions from their radiology information system data.