-
European Radiology Jun 2021Map the current landscape of commercially available artificial intelligence (AI) software for radiology and review the availability of their scientific evidence. (Review)
Review
OBJECTIVES
Map the current landscape of commercially available artificial intelligence (AI) software for radiology and review the availability of their scientific evidence.
METHODS
We created an online overview of CE-marked AI software products for clinical radiology based on vendor-supplied product specifications ( www.aiforradiology.com ). Characteristics such as modality, subspeciality, main task, regulatory information, deployment, and pricing model were retrieved. We conducted an extensive literature search on the available scientific evidence of these products. Articles were classified according to a hierarchical model of efficacy.
RESULTS
The overview included 100 CE-marked AI products from 54 different vendors. For 64/100 products, there was no peer-reviewed evidence of its efficacy. We observed a large heterogeneity in deployment methods, pricing models, and regulatory classes. The evidence of the remaining 36/100 products comprised 237 papers that predominantly (65%) focused on diagnostic accuracy (efficacy level 2). From the 100 products, 18 had evidence that regarded level 3 or higher, validating the (potential) impact on diagnostic thinking, patient outcome, or costs. Half of the available evidence (116/237) were independent and not (co-)funded or (co-)authored by the vendor.
CONCLUSIONS
Even though the commercial supply of AI software in radiology already holds 100 CE-marked products, we conclude that the sector is still in its infancy. For 64/100 products, peer-reviewed evidence on its efficacy is lacking. Only 18/100 AI products have demonstrated (potential) clinical impact.
KEY POINTS
• Artificial intelligence in radiology is still in its infancy even though already 100 CE-marked AI products are commercially available. • Only 36 out of 100 products have peer-reviewed evidence of which most studies demonstrate lower levels of efficacy. • There is a wide variety in deployment strategies, pricing models, and CE marking class of AI products for radiology.
Topics: Artificial Intelligence; Humans; Radiography; Radiology; Software
PubMed: 33856519
DOI: 10.1007/s00330-021-07892-z -
JAMA Dermatology Nov 2022
Topics: Humans; Netherton Syndrome; Dermatitis, Exfoliative; Dermoscopy
PubMed: 36169939
DOI: 10.1001/jamadermatol.2022.3796 -
Journal of the American Academy of... Dec 2020In keeping with the Journal's policies, we provide a listing of disclosures for all members of the editorial masthead and the ad hoc and guest editors (marked with an...
In keeping with the Journal's policies, we provide a listing of disclosures for all members of the editorial masthead and the ad hoc and guest editors (marked with an asterisk) as of October 21, 2020. This list, based on annually updated signed statements on file in the editorial office, includes all biomedical financial interests and potential conflicts of interest disclosed for the previous 24 months and the foreseeable future.
PubMed: 33248529
DOI: 10.1016/j.jaac.2020.10.014 -
The Urologic Clinics of North America Nov 2021Female sexual pain disorder or genito-pelvic pain/penetration disorder (GPPPD), previously known as dyspareunia, is defined as persistent or recurrent symptoms with one... (Review)
Review
Female sexual pain disorder or genito-pelvic pain/penetration disorder (GPPPD), previously known as dyspareunia, is defined as persistent or recurrent symptoms with one or more of the following for at least 6 months: marked vulvovaginal or pelvic pain during penetrative intercourse or penetration attempts, marked fear or anxiety about vulvovaginal or pelvic pain in anticipation of, during, or as a result of penetration, and marked tensing or tightening of the pelvic floor muscles during attempted vaginal penetration. In this review, we discuss etiology, diagnosis, and treatment for common disorders that cause GPPD.
Topics: Dyspareunia; Female; Humans
PubMed: 34602170
DOI: 10.1016/j.ucl.2021.06.007 -
Brain and Nerve = Shinkei Kenkyu No... May 2024Fisher syndrome is recognized as a variant of Guillain-Barré syndrome, encompassing acute onset immune-mediated neuropathies marked by the classical triad of ataxia,... (Review)
Review
Fisher syndrome is recognized as a variant of Guillain-Barré syndrome, encompassing acute onset immune-mediated neuropathies marked by the classical triad of ataxia, areflexia, and ophthalmoplegia. Generally, Fisher syndrome follows a self-limited course with a good prognosis. Ophthalmoplegia, typically bilateral, progresses to complete external ophthalmoplegia within 1-2 weeks. Ataxia, often very severe, may cause an inability to walk without support despite normal strength. Fisher syndrome is also frequently concomitant with additional clinical features, including ptosis, internal ophthalmoplegia, facial nerve palsy, sensory deficits, and bulbar palsy. The confirmation of an antecedent infection is often established. Among the ganglioside antibodies, anti-GQ1b antibodies exhibit positivity in over 80% of patients. The syndrome manifests in three distinct types: a partial subtype exhibiting only a subset of the triad symptoms, Bickerstaff's brainstem encephalitis marked by impaired consciousness and pyramidal tract signs, and an overlapping subtype with Guillain-Barré syndrome, characterized by weakness in the extremities.
Topics: Humans; Miller Fisher Syndrome; Gangliosides; Prognosis; Guillain-Barre Syndrome
PubMed: 38741489
DOI: 10.11477/mf.1416202636 -
Journal of the American Academy of... Dec 2019In keeping with the Journal's policies, we provide a listing of disclosures for all members of the editorial masthead and the ad hoc and guest editors (marked with an...
In keeping with the Journal's policies, we provide a listing of disclosures for all members of the editorial masthead and the ad hoc and guest editors (marked with an asterisk) as of October 3, 2019. This list, based on annually updated signed statements on file in the editorial office, includes all biomedical financial interests and potential conflicts of interest disclosed for the previous 24 months and the foreseeable future.
Topics: Conflict of Interest; Disclosure; Editorial Policies; Humans; Periodicals as Topic
PubMed: 31757400
DOI: 10.1016/j.jaac.2019.10.002 -
Brazilian Journal of Physical Therapy 2021Executive dysfunction and risk of falling are hallmarks of Parkinson's disease (PD). However, it is unclear how executive dysfunction predisposes people with PD to...
BACKGROUND
Executive dysfunction and risk of falling are hallmarks of Parkinson's disease (PD). However, it is unclear how executive dysfunction predisposes people with PD to falling.
OBJECTIVES
To: (i) identify sensorimotor, balance, and cardiovascular risk factors for falls that discriminate between those with normal executive function and those with mild and marked executive dysfunction in people with PD and (ii) determine whether mild and marked executive dysfunction are significant risk factors for falls when adjusting for PD duration and severity and freezing of gait (FOG).
METHODS
Using the Frontal Assessment Battery, 243 participants were classified into normal executive function (n = 87), mild executive dysfunction (n = 100), and marked executive dysfunction (n = 56) groups. Participants were asked if they had episodes of FOG in the last month and were assessed with the Movement Disorders Society - Unified Parkinson's Disease Rating Scale (MDS-UPDRS), the Hoehn and Yahr Scale, the physiological profile assessment, and tests of orthostatic hypotension, coordinated stability, and gait and were then followed-up prospectively for falls for 32-52 weeks.
RESULTS
Several PD-specific (elevated Hoehn and Yahr stage, higher MDS-UPDRS scale scores, a history of FOG, Postural Instability and Gait Difficulty subtype, and longer PD duration), sensorimotor (poor vision, knee extension weakness, slow simple reaction time), and balance (greater postural sway and poor controlled leaning balance) factors discriminated among the normal executive function and mild and marked executive dysfunction groups. Fall rates (mean ± SD) differed significantly among the groups (normal executive function: 1.0 ± 1.7; mild executive dysfunction: 2.8 ± 5.2; marked executive dysfunction: 4.7 ± 7.3) with the presence of both mild and marked executive dysfunction identified as significant risk factors for falls when adjusting for three measures of PD severity (Hoehn and Yahr scale scores, disease duration, and FOG).
CONCLUSIONS
Several PD-specific, sensorimotor, and balance factors differed significantly among the normal, mild, and marked executive dysfunction groups and both mild and marked executive dysfunction were identified as independent risk factors for falls in people with PD.
Topics: Cognitive Dysfunction; Executive Function; Gait Disorders, Neurologic; Humans; Parkinson Disease; Postural Balance; Risk Factors; Severity of Illness Index
PubMed: 33349526
DOI: 10.1016/j.bjpt.2020.11.005 -
Pain Management May 2022Better documentation of vulvar pain is needed. We examined pain locations marked on general body and genital specific outlines among women with vulvodynia. 62 women...
Better documentation of vulvar pain is needed. We examined pain locations marked on general body and genital specific outlines among women with vulvodynia. 62 women (mean age 32.1 ± 9.5 years) with vulvodynia marked their pain on a digital genital specific outline (22 segments) and 59 of those women also marked their pain on a digital general body outline (48 segments). We used ImageJ software to determine body surface area (BSA) for each outline. On the general body outline, 24/48 segments were marked; 22/22 segments were marked on the genital specific outline. There was a moderate correlation ( = 0.43; p = 0.001) between the BSA marked on the general body outline and the BSA marked on the genital area outline. Findings support concurrent validity of the BSA as a measure of pain location using either outline.
Topics: Adult; Documentation; Female; Humans; Pain; Vulvodynia; Young Adult
PubMed: 35060761
DOI: 10.2217/pmt-2021-0110