Abstract
Background
Fetal ultrasound is an important component of antenatal care, but shortage of adequately trained healthcare workers has limited its adoption in low-to-middle-income countries. ...This study investigated the use of artificial intelligence for fetal ultrasound in under-resourced settings.
Methods
Blind sweep ultrasounds, consisting of six freehand ultrasound sweeps, were collected by sonographers in the USA and Zambia, and novice operators in Zambia. We developed artificial intelligence (AI) models that used blind sweeps to predict gestational age (GA) and fetal malpresentation. AI GA estimates and standard fetal biometry estimates were compared to a previously established ground truth, and evaluated for difference in absolute error. Fetal malpresentation (non-cephalic vs cephalic) was compared to sonographer assessment. On-device AI model run-times were benchmarked on Android mobile phones.
Results
Here we show that GA estimation accuracy of the AI model is non-inferior to standard fetal biometry estimates (error difference −1.4 ± 4.5 days, 95% CI −1.8, −0.9,
n
= 406). Non-inferiority is maintained when blind sweeps are acquired by novice operators performing only two of six sweep motion types. Fetal malpresentation AUC-ROC is 0.977 (95% CI, 0.949, 1.00,
n
= 613), sonographers and novices have similar AUC-ROC. Software run-times on mobile phones for both diagnostic models are less than 3 s after completion of a sweep.
Conclusions
The gestational age model is non-inferior to the clinical standard and the fetal malpresentation model has high AUC-ROCs across operators and devices. Our AI models are able to run on-device, without internet connectivity, and provide feedback scores to assist in upleveling the capabilities of lightly trained ultrasound operators in low resource settings.
Background
Etrasimod is an oral, selective, sphingosine 1‐phosphate (S1P) receptor1,4,5 modulator in development for immune‐mediated inflammatory disorders. Efficacy and safety of orally administered ...S1P receptor modulation in atopic dermatitis (AD) have not yet been examined.
Objective
To assess the efficacy and safety of etrasimod monotherapy in adults with moderate‐to‐severe AD.
Methods
In this phase 2, randomized, double‐blind, placebo‐controlled trial, participants (≥18 years) with moderate‐to‐severe AD defined as baseline validated Investigator's Global Assessment (vIGA‐AD) score ≥ 3, Eczema Area and Severity Index (EASI) score ≥ 16, and body surface area involvement ≥10% were randomized 1:1:1 to once‐daily oral etrasimod 1 mg, 2 mg or placebo for 12 weeks. The primary outcome was percent change in EASI score from baseline at week 12, assessed in the Full Analysis Set (all randomized participants). Key secondary outcomes were achievement of a vIGA‐AD score of 0 or 1 with a ≥2‐point improvement from baseline and EASI‐75 response at Week 12. Safety was assessed during the double‐blind period.
Results
One hundred and forty participants were randomized to etrasimod 2 mg (n = 47), 1 mg (n = 47) or placebo (n = 46). At Week 12, percent change in EASI score was −57.2% in the etrasimod 2‐mg group versus −48.4% in the placebo group (p = 0.18). A significantly greater proportion of participants receiving etrasimod 2 mg achieved vIGA‐AD scores of 0 or 1 with a ≥2‐point improvement at Week 12 versus placebo (29.8% vs. 13.0%; p = 0.045); however, EASI‐75 response was not statistically significant versus placebo. Treatment‐emergent adverse events (AEs) occurred in 59.6%, 40.4% and 47.8% of participants receiving etrasimod 2 mg, 1 mg and placebo, respectively. There were no serious AEs or deaths.
Conclusions
The primary outcome was not met, although efficacy was observed for etrasimod 2 mg on several clinician‐ and patient‐assessed measures, and both 1‐ and 2‐mg doses were well tolerated, warranting further clinical investigation in AD.
Introduction Solriamfetol, a selective dopamine and norepinephrine reuptake inhibitor, demonstrated robust wake-promoting effects in 12-week studies of excessive daytime sleepiness (EDS) associated ...with obstructive sleep apnea (OSA) or narcolepsy. Efficacy and safety of solriamfetol were evaluated from pooled analyses of these studies. Methods Data from 12-week studies (2 narcolepsy, 1 OSA) were evaluated. Efficacy assessments included change from baseline to week 12 on mean sleep latency on Maintenance of Wakefulness Test (MWT), Epworth Sleepiness Scale (ESS) score, and patient-reported improvement on Patient Global Impression of Change (PGI-C) scale. Safety was also assessed. Results Compared with participants with OSA (n=113 placebo, 343 solriamfetol combined doses), those with narcolepsy (n=105 placebo, 215 solriamfetol) were younger, with more females, and lower body mass index. Baseline MWT mean sleep latency and ESS scores were more severe for narcolepsy compared with OSA. Change from baseline to week 12 in MWT mean sleep latency increased in a dose-related manner compared with placebo, with least square (LS) mean differences of 2.2, 7.4, and 10.4 for 75, 150, and 300mg, respectively, for narcolepsy, and 4.7, 9.0, 11.1, and 13.0 for 37.5, 75, 150, and 300mg, respectively, for OSA. Dose-related effects were also observed for change from baseline to week 12 in ESS score, with LS mean differences of -1.8, -3.8, and -5.2 for 75, 150, and 300mg, respectively, for narcolepsy, and -2.0, -1.9, -4.5, and -4.8 for 37.5, 75, 150, and 300mg, respectively, for OSA. At week 12, the percentage of participants reported as improved on PGI-C was increased relative to placebo; results were similar between disorders. In the overall population, the most frequent (≥5%) adverse events were headache, nausea, decreased appetite, anxiety, nasopharyngitis, diarrhea, and dry mouth; the incidence was comparable in OSA and narcolepsy. Conclusion Solriamfetol showed consistent efficacy and safety findings in both narcolepsy and OSA subjects. Solriamfetol increased wakefulness and reduced sleepiness in both groups and the adverse events profile was similar for both groups. Support (If Any) Jazz Pharmaceuticals
Introduction Excessive daytime sleepiness (EDS) is a debilitating non-motor symptom affecting patients with Parkinson’s Disease (PD). Solriamfetol has demonstrated wake-promoting efficacy in clinical ...trials in narcolepsy and obstructive sleep apnea (OSA). Methods This was a phase 2, double-blind, placebo-controlled, randomized, 4-week, crossover trial. Eligible participants were 35-80 years of age, diagnosed with mild to moderate idiopathic PD (UK PDS Brain Bank Criteria), with Epworth Sleepiness Scale (ESS) score >11. Participants were randomized (3:3:1) to receive one week of: A) placebo, solriamfetol 75mg, 150mg, and 300mg, B) solriamfetol 75mg, 150mg, 300mg, and placebo, or C) four weeks of placebo. Safety and tolerability were primary objectives and included assessment of adverse events. Efficacy endpoints were change from baseline in mean sleep latency on the Maintenance of Wakefulness Test (MWT) and ESS score. Results Participants (n=66) were randomized (mean SD age, 64.6 8.5; 68.2% male) and n=62 completed the trial. At baseline, mean (SD) ESS score was 16.1 (2.9), and MWT sleep latency was 15.1 min (10.9). The most common treatment-emergent adverse events (≥5%) reported while taking solriamfetol were nausea (10.7%), dizziness (7.1%), dry mouth (7.1%), headache (7.1%), anxiety (5.4%), constipation (5.4%), and dyspepsia (5.4%). Least Square (LS) mean (SE) change from baseline in MWT (min) was 1.8 (1.9) for placebo, 0.4 (2.1) for 75mg (nominal p>0.05), 2.7 (2.2) for 150mg (nominal p>0.05), and 6.8 (2.1) for 300mg (nominal p=0.0098). LS mean (SE) change from baseline in ESS was -4.8 (0.6) for placebo, -4.8 (0.7) for 75mg, -5.0 (0.7) for 150mg and -5.7 (0.7) for 300mg; for change in ESS, all nominal p>0.05. Conclusion The safety and tolerability of solriamfetol in PD was demonstrated; participants were able to safely titrate to 300mg, and adverse events were similar to narcolepsy and OSA trials. Solriamfetol treatment improved sleep latency on the MWT at 300mg but not at lower doses. While ESS improvement with solriamfetol was not different from placebo, the large placebo response, likely multifactorial in basis, may have confounded interpretation. Support (If Any) Jazz Pharmaceuticals
Objective
Our aim was to investigate the effects of Spirulina on BV-2 microglial cell cytotoxicity and inflammatory genes expression.
Methods
BV-2 microglial cells were treated with ...lipopolysaccharide (LPS) (1 µg/ml) and various concentrations of Spirulina platensis water extract or its active component (C-phycocyanin (C-PC)) for 24 hours. Cytotoxicity (lactate dehydrogenase (LDH) release) and expression of inducible nitric oxide synthase (iNOS), cyclooxygenase-2 (COX-2), tumor necrosis factor-α (TNF-α), and interleukin-6 (IL-6) mRNAs were assayed.
Results
LPS increased LDH production and up-regulated expression of iNOS, COX-2, TNF-α, and IL-6 by BV-2 microglial cells. However, Spirulina platensis water extract and C-PC significantly reduced LPS-induced LDH release, and expression of iNOS, COX-2, TNF-α, and IL-6 mRNAs.
Conclusion
Spirulina can reduce the cytotoxicity and inhibit expression of inflammation-related genes of LPS-stimulated BV-2 microglial cells.
We examined the effects of hedges and the discourse marker
like
on how people recalled specific details about precise quantities in spontaneous speech. We found that listeners treated hedged ...information differently from
like-
marked information
,
although both are thought to be indicators of uncertainty or vagueness
.
In addition, hedges had different effects depending on whether speakers were (1) retelling conversations to another person or (2) answering questions about material they had heard. When retelling to another person, listeners were more likely to report information that was either unmarked or marked with a
like
than hedged information (Experiment 1). Yet when answering questions by themselves, hedges enhanced memory for details, in comparison with
like
s (Experiment 2). Hedges appear to provide pragmatic cues about what information is reliable enough to repeat in a conversational context. But although hedged information may be left out, it is not forgotten.
Two Techniques for Assessing Virtual Agent Personality Liu, Kris; Tolins, Jackson; Fox Tree, Jean E. ...
IEEE transactions on affective computing,
2016-Jan.-March-1, 2016-1-1, 20160101, Volume:
7, Issue:
1
Journal Article
Peer reviewed
Open access
Personality can be assessed with standardized inventory questions with scaled responses such as "How extraverted is this character?" or with open-ended questions assessing first impressions, such as ..."What personality does this character convey?" Little is known about how the two methods compare to each other, and even less is known about their use in the personality assessment of virtual agents. We tested what personality virtual agents conveyed through gesture alone when the agents were programmed to display introversion versus extraversion (Experiment 1) and high versus low emotional stability (Experiment 2). In Experiment 1, both measures indicated participants perceived the extraverted agent as extraverted, but the open-question technique highlighted the perception of both agents as highly agreeable whereas the inventory indicated that the extraverted agents were also perceived as more open to new experiences. In Experiment 2, participants perceived agents expressing high versus low emotional stability differently depending on assessment style. With inventory questions, the agents differed on both emotional stability and agreeableness. With the open-ended question, participants perceived the high stability agent as extraverted and the low stability agent as disagreeable. Inventory and open-ended questions provide different information about what personality virtual agents convey and both may be useful in agent development.
The Map Task (Anderson et al., 1991) and Tangram Task (Clark & Wilkes-Gibbs, 1986) are traditional referential communication tasks that are used in psycholinguistics research to demonstrate how ...conversational partners mutually agree on descriptions (or referring expressions) for landmarks or unusual target objects. These highly-controlled, laboratory-based tasks take place under conditions that are relatively unusual for naturally-occurring conversations (Speed, Wnuk, & Majid, 2016). In this study, we used the Artwalk Task (Liu, Fox Tree, & Walker, 2016) – a real world-situated blend of the Map Task and Tangram Task – to demonstrate that the process of negotiating referring expressions ‘in the wild’ is similar to the process that takes place in a laboratory. In Artwalk, participant pairs communicated via a Skype-to-mobile phone connection. One participant guided the other through a small downtown area with the goal of identifying public art objects, finding objects twice during two rounds. In addition to replicating laboratory results, we also found that acquaintanceship and extraversion influenced the number of unique descriptors used by dyads in this task. In Round 1, introverts in stranger dyads used fewer descriptors but introverts in friend dyads were indistinguishable from extraverts. The influence of extraversion declined by Round 2. This study suggests that referent negotiation observed in labs is generalizable but that naturalistic communication is subject to social and personality factors that may not be as influential in laboratory conditions.
This dissertation examines whether computer-mediated, text-based conversation (chat) between friends and strangers differ in efficiency and politeness over time. Experiment 1 is a longitudinal corpus ...collection task, which is analyzed to see if there are differences in how efficient friend and stranger dyads are at completing collaborative tasks and whether these differences persist across the three-week study. Experiment 1 participants did an online version of a traditional referential communication task (the tangram task) every week, which became practiced over time, as well as a novel puzzle task that changed every week. (Experiment 1 analysis only analyzes the tangram task data.) Experiment 2 uses stimuli taken from both tangram and puzzle tasks and looks at how third-party ‘over-reader’ judgments on politeness evolve across three weeks. Experiment 3 expands on this by systematically manipulating the dialogue taken from Experiment 1 to demonstrate that politeness is not purely determined by a speaker’s intention, as suggested by the dominant theory of politeness by Brown and Levinson (1987). The results of Experiment 1 indicate that there were few differences between the number of unique descriptive words that friend and stranger dyads used, though friends tended to take more turns than strangers. The results of Experiment 2 show that third-party over-readers are bad at explicitly distinguishing between friend and stranger dyads in both the practiced and novel tasks, though they do rate strangers as being more polite than friends at first; this difference evaporates by the second week. The results of Experiment 3 suggest that though an obviously impolite utterance will never be considered very polite (and vice versa), an interlocutor’s response to an utterance can nonetheless influence how polite an utterance sounds. Furthermore, those dyads thought to be friends are granted more flexibility in their utterances than those thought to be strangers: impolite utterances can be judged as neutral when over-readers think they are reading the conversation of friends but remains impolite when they think they are reading the conversation of strangers.