BACKGROUND: The escalating global prevalence of obesity has necessitated the exploration of novel diagnostic approaches. Recent scientific inquiries have indicated potential alterations in voice characteristics associated with obesity, suggesting the feasibility of using voice as a noninvasive biomarker for obesity detection.
OBJECTIVE: This study aims to use deep neural networks to predict obesity status through the analysis of short audio recordings, investigating the relationship between vocal characteristics and obesity.
METHODS: A pilot study was conducted with 696 participants, using self-reported BMI to classify individuals into obesity and nonobesity groups. Audio recordings of participants reading a short script were transformed into spectrograms and analyzed using an adapted YOLOv8 model (Ultralytics). The model performance was evaluated using accuracy, recall, precision, and F1-scores.
RESULTS: The adapted YOLOv8 model demonstrated a global accuracy of 0.70 and a macro F1-score of 0.65. It was more effective in identifying nonobesity (F1-score of 0.77) than obesity (F1-score of 0.53). This moderate level of accuracy highlights the potential and challenges in using vocal biomarkers for obesity detection.
CONCLUSIONS: While the study shows promise in the field of voice-based medical diagnostics for obesity, it faces limitations such as reliance on self-reported BMI data and a small, homogenous sample size. These factors, coupled with variability in recording quality, necessitate further research with more robust methodologies and diverse samples to enhance the validity of this novel approach. The findings lay a foundational step for future investigations in using voice as a noninvasive biomarker for obesity detection.

BACKGROUND: Dual-task training is an emerging field used for people with Parkinson disease (PD) to improve their physical and cognitive well-being, but the patients\' acceptability, safety, and adherence to such training in online settings are unknown.
OBJECTIVE: This study aims to evaluate the acceptability of a dual-task cognitive and motor online training program for people with PD as a group online community program.
METHODS: People with PD were invited to participate in an online program (PD3 Move) consisting of physical and vocal exercises in response to different cognitive challenges displayed as dynamic backgrounds on Zoom. The program ran twice per week for 16 weeks. Patient acceptability was assessed at 4 months by monitoring attendance rates and feedback from an exit questionnaire emailed to all participants assessing satisfaction, perceived benefit, safety, and willingness to continue and recommend to others.
RESULTS: The online program was delivered to 15 participants (n=9, 60%, females) with a diagnosis of PD, a mean age of 69.4 (SD 9.3) years, and Hoehn and Yahr (H&Y) stages I-IV. The attendance rate was high, with participants coming to more than 13 (81%) of the sessions. Participants were very satisfied (n=8, 53%) or satisfied (n=7, 47%) with the program. Participants reported that what they most liked were the new cognitive physical challenges. The 3 main facilitators to participating were perceiving the benefits, instructor\'s flexibility and engagement, and the social interaction moments with others. The 3 main difficulties were dealing with motor fluctuations (n=3, 20%), difficulties in using technology (n=2, 13%), and difficulty hearing instructions due to hearing loss (n=2, 13%). Patients had favorable perceived benefits of the program, with 14 (93%) considering it very useful for the current management of health and 1 (7%) moderately useful. No adverse events were reported, and all participants said that they were willing to continue the program and recommend it to others.
CONCLUSIONS: Our findings suggest that the online cognitive and motor program was well received, safe, and perceived to be of benefit to this group of medically stable people with PD in H&Y stages I-IV. Access to specialized care and enhancement of long-term adherence to regular exercise can be achieved with online community group programs.

UNASSIGNED: 4D (3D + time) indices of tissue impedance using power Doppler (PD) ultrasound (US) can be measured with spatial-temporal image correlation (STIC) imaging. We wished to evaluate their repeatability and their influence under changes to US machine settings and regional differences within the placenta.
UNASSIGNED: A total of 46 healthy women were recruited at 20-34 weeks of gestation. A total of 9940 3D frames from 644 4D data sets were analysed providing both 3D and 4D indices of vascularity. 4D vs. 3D indices were compared with different machine settings, across the cardiac cycle and in the different placenta regions to assess regional variability.
UNASSIGNED: 3D and 4D indices significantly decreased as wall motion filter (WMF) was increased (P < 0.001). Repeatability decreased as WMF increased (ICC; low1 = 0.80; high1 = 0.60). Indices were significantly lower at the maternal aspect (P = 0.002-0.009) of the placenta and showed less repeatability (ICC; 0.42-0.79) than the fetal aspect (ICC 0.49-0.88). 4D repeatability was good in the central region (ICC 0.80-0.81) but poor in the periphery (ICC 0.45-0.59), while 3D indices were good and comparable between regions (ICC; 0.80 central; 0.81 peripheral).
UNASSIGNED: This study supports the future use of WMF \'low1\' and PD to generate more reliable 4D indices values. For 3D indices, HD Flow may improve Doppler signal sensitivity. Regarding placental regional variability, the fetal plate and the central region demonstrated more repeatable 4D indices. 4D PD indices have potential to overcome the limitations of VOCAL™ indices and provide an internally standardised measure of localised impedance in vascular beds.

OBJECTIVE: Incomplete healing of the uterine scar after cesarean section may result in formation of a niche. The aim of this study is to identify the potential risk factors for the improper uterine healing after cesarean section in women with single layer, full thickness uterine closure with the use of two- and three-dimensional transvaginal ultrasonography.
METHODS: 204 women with a history of at least one low transverse cesarean section (CS) with a single layer uterine closure participated in the study. Residual myometrial thickness (RMT), adjacent myometrial thickness (AMT), width (W), depth (D) and volume of the niche, RMT/AMT, RMT/D, RMT/W ratio and clinical characteristics were analyzed.
RESULTS: A niche after cesarean section was found in 153 cases. However only five patients had a RMT < 2.2 mm, and 35 had an RMT/AMT ratio ≤ 0.5. The RMT and RMT/AMT ratio among women who had undergone more than one cesarean section was lower than among women who underwent the first cesarean section. No statistically significant relationship was found between the incidence of niche, its parameters and cervical dilation, uterine contractions, cesarean section in the second stage of labor, type of uterus incision expansion and flexion, operator\'s experience.
CONCLUSIONS: Healing of the uterine cesarean section scar in women with single-layer continuous suture covering the entire thickness of the myometrium, excluding the decidua is not affected by the mode of caesarean section, type of uterine incision expansion and flexion, operator\'s experience, stage of labor at the time of caesarean section.

BACKGROUND: The potential role of antinuclear antibodies (ANA) in recurrent pregnancy loss (RPL) pathogenesis is still debated, although some evidences suggest that they could affect pregnancy outcome, leading to a higher miscarriage rate in these patients. A hypothesized mechanism is through changes in uterine flow in pre-conceptional stage, by modifying endometrial receptivity in RPL. However, scant data are available, in pregnancy, about their role in RPL placental perfusion, also in relation to its potential treatments, such as low molecular weight heparin (LMWH). The aim of this study is to retrospectively further investigate the correlation between two-dimensional (2D) and three-dimensional (3D) uterine and placental flow indexes and the presence or the absence of ANA in women with unexplained RPL (uRPL), treated or not treated with LMWH.
METHODS: 2D Doppler measurement of pulsatility index (PI) of the uterine arteries and 3D ultrasonography determination of vascularization index (VI), flow index (FI) and vascularization flow index (VFI) was carried out with the aid of the virtual organ computer-aided analysis (VOCAL) technique in LMWH treated (n 24) and not treated-uRPL patients (n 20) and in the relative control group (n 27), each group divided in ANA+ and ANA- subgroups. Serum assay for the presence of ANA was performed in all women.
RESULTS: No differences were found in PI, VFI and VI values, by comparing the different groups. A difference in VI values was found for ANA- patients between RPL women not treated with LMWH and the treated ones (p = 0,01), which have lower VI values and similar to controls. By considering only ANA- treated and not treated RPL patients, the ROC curve shows an area of 0,80 and at the VI cut-off of 11,08 a sensitivity of 85% and a specificity of 67%.
CONCLUSIONS: LMWH could exert a potential beneficial effect in restoring the physiological blood flow supply in terms of VI in uRPL ANA- status, suggesting to include ANA and VI investigations in the RPL diagnostic algorithm in a research context, since further studies are needed to clarify this challenging hypothesis in order to try to ameliorate ANA and abnormal placental vascularization negative influence on RPL pregnancy outcome .

OBJECTIVE: The purpose of this study was to replicate a previous investigation to assess with two intact children\'s choirs and a high school choir the potential effects of three choral warm-up procedures (vocal-only, physical-only, physical/vocal combination) on acoustic and perceptual measures of choral sound.
METHODS: The researchers tested three videotaped, 5-minute, choral warm-up procedures on two children\'s and one high school choir. After participating in a warm-up procedure, each choir was recorded singing a folk song for long-term average spectra and pitch analysis. Singer participants responded to a questionnaire about preferences after each warm-up procedure. Warm-up procedures and recording sessions occurred during each choir\'s regular rehearsal time and in each choir\'s regular rehearsal space during three consecutive rehearsals.
RESULTS: Long-term average spectra results demonstrated more resonant singing after the physical/vocal warm-up for two of the three choirs. Pitch analysis results indicated that two of the three choirs sang \"in-tune\" after participating in the physical/vocal warm-up and two choirs sang \"in-tune\" after participating in the physical-only warm-up. Singer questionnaire responses showed a preference for the physical/vocal combination warm-up, and singer ranking of the three procedures indicated the physical/vocal warm-up as the most favored for readiness to sing.
CONCLUSIONS: This study replication indicates similar conclusions as the original investigation with university choruses: a combination choral warm-up that includes both physical and vocal aspects is preferred by singers of all ages, enables more resonant singing, and more in-tune singing. Findings from these investigations provide choral educators with compelling information concerning efficient and effective choral warm-up procedures.

Purpose: The aim of this study was to compare volumetric parameters in the abnormal and normal posterior fossa using the Virtual Organ Computer-aided AnaLysis (VOCAL™) technique to determine whether fetuses with an abnormal posterior fossa have different volumes.Methods: A prospective study was conducted on 17 fetuses with an abnormal posterior fossa including, Dandy Walker malformation (DWM) (n = 6), vermian hypoplasia (VH) (n = 3), mega cisterna magna (MCM) (n = 8), and 99 healthy control fetuses from 20 to 34 weeks\' gestation. Measurement of the fetal cisterna magna and cerebellar volume was performed in the standard transcerebellar plane through the VOCAL™ method. To establish the correlation of volumes with gestational age, polynomial regression analysis was performed. For comparison between groups, univariate ANCOVA was performed using gestational age as a covariate. The reliability was analyzed by the intraclass correlation coefficient (ICC).Results: Cerebellar volume and cisterna magna volume were correlated with gestational age. Posterior fossa volume was significantly larger in DWM (p < .0001) and MCM (p < .0001) in comparison to the control group. In VH group, cisterna magna volume does not seem to expand (p = .298). Cerebellar volume does not seem to change in subgroups when the influence of gestational age is discarded (p = .09). The ratio of cerebellar volume to the cisterna magna volume decreases significantly in abnormal fetuses (p < .0001). Good intraobserver and interobserver reliabilities were found for both cerebellum and cisterna magna measurements.Conclusions: Volume analysis may have a role in discrimination of different posterior fossa pathologies.

OBJECTIVE: The objective of this study is to estimate optimal cut-off values for mean fetal lung volume (FLV) and pulmonary artery resistance index (PA-RI) as non-invasive measures to predict neonatal respiratory distress syndrome (RDS) in preterm fetuses.
METHODS: A prospective study conducted at Ain Shams University Maternity Hospital, Egypt from May 2015 to July 2017: 80 eligible women diagnosed with preterm labor were recruited at 32-36 weeks\' gestation. Before delivery, three-dimensional ultrasound was used to estimate FLV using virtual organ computer-aided analysis (VOCAL), while PA-RI was measured by Doppler ultrasonography.
RESULTS: A total of 80 women were examined. Thirty-seven (46%) of the newborns developed neonatal RDS. FLV was significantly lower in neonates who developed RDS (p = .04), whereas PARI was significantly higher in those who did not (p = .02). Cut-off values of FLV ≤27.2 cm3 and PARI ≥0.77 predicted the subsequent development of RDS. Combining both cut-offs generated a more sensitive and specific methodical approach for the prediction of RDS (sensitivity 100%, specificity 88.5%).
CONCLUSIONS: Measurement of FLV or PA-RI can predict RDS in preterm fetuses. Combined use of both measures bolstered their predictive significance.

To test the hypothesis that third trimester placental biometry and volume can be measured by two-dimensional (2D) and three-dimensional (3D) ultrasound in utero, determining which method of measurement was most strongly correlated with true placental size ex vivo.
Singleton pregnancies underwent placental ultrasound within seven days of delivery (n = 87, 29(+3)-41(+5) weeks). Length and width (linear and curvilinear) and depth were estimated. Placental volume (PV) was estimated using 2D ellipse and shell techniques and 3D rotational (15⁰ and 30⁰ rotation angles) and multiplanar (5 and 10 mm slicing intervals) techniques. Measurements were compared to their true correlates following delivery. Intra- and inter-observer reliabilities of candidate placental size estimates were assessed by intraclass correlation coefficient (ICC).
Curvilinear placental length (Rs = 0.24, p = 0.031), width (Rs = 0.27, p = 0.013) and depth (Rs = 0.31, p = 0.0056) correlated well with ex vivo measurements. All methods of PV estimation were related to ex vivo volume (Rs ≥ 0.32, p < 0.01) but not placental weight (p > 0.05); 30° rotational estimation demonstrated the strongest biological correlation (Rs = 0.40, p = 0.0004). Intra- and inter-observer placental size measurements intraclass correlation coefficients were suboptimal (0.59-0.70 and 0.10-0.58 respectively).
We have demonstrated that it is possible to obtain information about the size of the third trimester placenta in utero using 2D and 3D ultrasound. However it is essential that the reliability (particularly interobserver reliability) of these estimates is improved prior to prospective studies to determine their predictive value.