Strengths, weaknesses, opportunities and threats of using AI-enabled technology in sleep medicine: a commentary.

Over the past few years, artificial intelligence (AI) has emerged as a powerful tool used to efficiently automate several tasks across multiple domains. Sleep medicine is perfectly positioned to leverage this tool due to the wealth of physiological signals obtained through sleep studies or sleep tracking devices and abundance of accessible clinical data through electronic medical records. However, caution must be applied when utilizing AI, due to intrinsic challenges associated with novel technology. The Artificial Intelligence in Sleep Medicine committee of the American Academy of Sleep Medicine (AASM) reviews advancements in AI within the sleep medicine field. In this article, the Artificial Intelligence in Sleep Medicine committee members provide a commentary on the scope of AI technology in sleep medicine. The commentary identifies three pivotal areas in sleep medicine which can benefit from AI technologies: clinical care, lifestyle management and population health management. This article provides a detailed analysis of the strengths, weaknesses, opportunities, and threats associated with using AI enabled technologies in each pivotal area. Finally, the article broadly reviews barriers and challenges associated with using AI enabled technologies and offers possible solutions.

Pivotal Clinical Study to Evaluate the Safety and Effectiveness of the MANTA Percutaneous Vascular Closure Device.

BACKGROUND: Open surgical closure and small-bore suture-based preclosure devices have limitations when used for transcatheter aortic valve replacement, percutaneous endovascular abdominal aortic aneurysm repair, or percutaneous thoracic endovascular aortic aneurysm repair. The MANTA vascular closure device is a novel collagen-based technology designed to close large bore arteriotomies created by devices with an outer diameter ranging from 12F to 25F. In this study, we determined the safety and effectiveness of the MANTA vascular closure device. METHODS AND RESULTS: A prospective, single arm, multicenter investigation in patients undergoing transcatheter aortic valve replacement, percutaneous endovascular abdominal aortic aneurysm repair, or thoracic endovascular aortic aneurysm repair at 20 sites in North America. The primary outcome was time to hemostasis. The primary safety outcomes were accessed site-related vascular injury or bleeding complications. A total of 341 patients, 78 roll-in, and 263 in the primary analysis cohort, were entered in the study between November 2016 and September 2017. For the primary analysis cohort, transcatheter aortic valve replacement was performed in 210 (79.8%), and percutaneous endovascular abdominal aortic aneurysm repair or thoracic endovascular aortic aneurysm repair was performed in 53 (20.2%). The 14F MANTA was used in 42 cases (16%), and the 18F was used in 221 cases(84%). The mean effective sheath outer diameter was 22F (7.3 mm). The mean time to hemostasis was 65±157 seconds with a median time to hemostasis of 24 seconds. Technical success was achieved in 257 (97.7%) patients, and a single device was deployed in 262 (99.6%) of cases. Valve Academic Research Consortium-2 major vascular complications occurred in 11 (4.2%) cases: 4 received a covered stent (1.5%), 3 had access site bleeding (1.1%), 2 underwent surgical repair (0.8%), and 2 underwent balloon inflation (0.8%). CONCLUSIONS: In a selected population, this study demonstrated that the MANTA percutaneous vascular closure device can safely and effectively close large bore arteriotomies created by current generation transcatheter aortic valve replacement, percutaneous endovascular abdominal aortic aneurysm repair, and thoracic endovascular aortic aneurysm repair devices. CLINICAL TRIAL REGISTRATION: URL: https://www.clinicaltrials.gov . Unique identifier: NCT02908880.

Fast patient-specific Monte Carlo brachytherapy dose calculations via the correlated sampling variance reduction technique.

PURPOSE: To demonstrate potential of correlated sampling Monte Carlo (CMC) simulation to improve the calculation efficiency for permanent seed brachytherapy (PSB) implants without loss of accuracy. METHODS: CMC was implemented within an in-house MC code family (PTRAN) and used to compute 3D dose distributions for two patient cases: a clinical PSB postimplant prostate CT imaging study and a simulated post lumpectomy breast PSB implant planned on a screening dedicated breast cone-beam CT patient exam. CMC tallies the dose difference, ΔD, between highly correlated histories in homogeneous and heterogeneous geometries. The heterogeneous geometry histories were derived from photon collisions sampled in a geometrically identical but purely homogeneous medium geometry, by altering their particle weights to correct for bias. The prostate case consisted of 78 Model-6711 (125)I seeds. The breast case consisted of 87 Model-200 (103)Pd seeds embedded around a simulated lumpectomy cavity. Systematic and random errors in CMC were unfolded using low-uncertainty uncorrelated MC (UMC) as the benchmark. CMC efficiency gains, relative to UMC, were computed for all voxels, and the mean was classified in regions that received minimum doses greater than 20%, 50%, and 90% of D(90), as well as for various anatomical regions. RESULTS: Systematic errors in CMC relative to UMC were less than 0.6% for 99% of the voxels and 0.04% for 100% of the voxels for the prostate and breast cases, respectively. For a 1 × 1 × 1 mm(3) dose grid, efficiency gains were realized in all structures with 38.1- and 59.8-fold average gains within the prostate and breast clinical target volumes (CTVs), respectively. Greater than 99% of the voxels within the prostate and breast CTVs experienced an efficiency gain. Additionally, it was shown that efficiency losses were confined to low dose regions while the largest gains were located where little difference exists between the homogeneous and heterogeneous doses. On an AMD 1090T processor, computing times of 38 and 21 sec were required to achieve an average statistical uncertainty of 2% within the prostate (1 × 1 × 1 mm(3)) and breast (0.67 × 0.67 × 0.8 mm(3)) CTVs, respectively. CONCLUSIONS: CMC supports an additional average 38-60 fold improvement in average efficiency relative to conventional uncorrelated MC techniques, although some voxels experience no gain or even efficiency losses. However, for the two investigated case studies, the maximum variance within clinically significant structures was always reduced (on average by a factor of 6) in the therapeutic dose range generally. CMC takes only seconds to produce an accurate, high-resolution, low-uncertainly dose distribution for the low-energy PSB implants investigated in this study.

Estimating statistical uncertainty of Monte Carlo efficiency-gain in the context of a correlated sampling Monte Carlo code for brachytherapy treatment planning with non-normal dose distribution.

Correlated sampling Monte Carlo methods can shorten computing times in brachytherapy treatment planning. Monte Carlo efficiency is typically estimated via efficiency gain, defined as the reduction in computing time by correlated sampling relative to conventional Monte Carlo methods when equal statistical uncertainties have been achieved. The determination of the efficiency gain uncertainty arising from random effects, however, is not a straightforward task specially when the error distribution is non-normal. The purpose of this study is to evaluate the applicability of the F distribution and standardized uncertainty propagation methods (widely used in metrology to estimate uncertainty of physical measurements) for predicting confidence intervals about efficiency gain estimates derived from single Monte Carlo runs using fixed-collision correlated sampling in a simplified brachytherapy geometry. A bootstrap based algorithm was used to simulate the probability distribution of the efficiency gain estimates and the shortest 95% confidence interval was estimated from this distribution. It was found that the corresponding relative uncertainty was as large as 37% for this particular problem. The uncertainty propagation framework predicted confidence intervals reasonably well; however its main disadvantage was that uncertainties of input quantities had to be calculated in a separate run via a Monte Carlo method. The F distribution noticeably underestimated the confidence interval. These discrepancies were influenced by several photons with large statistical weights which made extremely large contributions to the scored absorbed dose difference. The mechanism of acquiring high statistical weights in the fixed-collision correlated sampling method was explained and a mitigation strategy was proposed.

Family-based association between Alzheimer's disease and variants in UBQLN1.

BACKGROUND: Recent analyses suggest that the known Alzheimer's disease genes account for less than half the genetic variance in this disease. The gene encoding ubiquilin 1 (UBQLN1) is one of several candidate genes for Alzheimer's disease located near a well-established linkage peak on chromosome 9q22. METHODS: We evaluated 19 single-nucleotide polymorphisms in three genes within the chromosome 9q linkage region in 437 multiplex families with Alzheimer's disease from the National Institute of Mental Health (NIMH) sample (1439 subjects). We then tested the single-nucleotide polymorphisms showing a positive result in an independently identified set of 217 sibships discordant for Alzheimer's disease (Consortium on Alzheimer's Genetics [CAG] sample; 489 subjects) and assessed the functional effect of an implicated single-nucleotide polymorphism in brain tissue from 25 patients with Alzheimer's disease and 17 controls. RESULTS: In the NIMH sample, we observed a significant association between Alzheimer's disease and various single-nucleotide polymorphisms in UBQLN1. We confirmed these associations in the CAG sample. The risk-conferring haplotype in both samples was defined by a single intronic single-nucleotide polymorphism located downstream of exon 8. The risk allele was associated with a dose-dependent increase in an alternatively spliced UBQLN1 (lacking exon 8) transcript in RNA extracted from brain samples of patients with Alzheimer's disease. CONCLUSIONS: Our findings suggest that genetic variants in UBQLN1 on chromosome 9q22 substantially increase the risk of Alzheimer's disease, possibly by influencing alternative splicing of this gene in the brain.

Genetic association of Alzheimer's disease with multiple polymorphisms in alpha-2-macroglobulin.

Alpha-2-Macroglobulin (A2M) is a highly plausible candidate gene for Alzheimer's disease (AD) in a region of chromosome 12 that has numerous independent reports of genetic linkage. We previously reported that a 5 bp deletion in A2M was associated with AD in a subset of the National Institute of Health (NIMH) Genetics Initiative AD family sample. Efforts to replicate this association finding in case - control samples have been largely negative, while those in family samples have been more positive. We hypothesized that variable findings regarding this deletion, along with variable reports of association with V1000I, another polymorphism in the gene, result from linkage disequilibrium in the area as well as ascertainment differences between family-based and case-control studies. Thus, we resequenced the A2M locus to identify novel polymorphisms to test for genetic association with AD. We identified seven novel polymorphisms and tested them in the full NIMH sample of 1439 individuals in 437 families. We found significant genetic association of the 5 bp deletion and two novel polymorphisms with AD. Substantial linkage disequilibrium was detected across the gene as a whole, and haplotype analysis also showed significant association between AD and groups of A2M polymorphisms. Several of these polymorphisms and haplotypes remain significantly associated with AD even after correction for multiple testing. Taken together, these findings, and the positive reports in other family-based studies, continue to support a potential role for A2M or a nearby gene in AD. However, the negative case - control studies suggest that any underlying pathogenic polymorphisms have a modest effect, and may operate primarily among individuals with a family history of AD.