Previous Volume Research Articles

Association of Dual-Task Gait Cost and White Matter Hyperintensity Burden Poststroke: Results From the ONDRI

Background Acute change in gait speed while performing a mental task [dual-task gait cost (DTC)], and hyperintensity magnetic resonance imaging signals in white matter are both important disability predictors in older individuals with history of stroke (poststroke). It is still unclear, however, whether DTC is associated with overall hyperintensity volume from specific major brain regions in poststroke. Methods This is a cohort study with a total of 123 older (69 ± 7 years of age) participants with history of stroke were included from the Ontario Neurodegenerative Disease Research Initiative. Participants were clinically assessed and had gait performance assessed under single- and dual-task conditions. Structural neuroimaging data were analyzed to measure both, white matter hyperintensity (WMH) and normal appearing volumes. Percentage of WMH volume in frontal, parietal, occipital, and temporal lobes as well as subcortical hyperintensities in basal ganglia + thalamus were the main outcomes. Multivariate models investigated associations between DTC and hyperintensity volumes, adjusted for age, sex, years of education, global cognition, vascular risk factors, APOE4 genotype, residual sensorimotor symptoms from previous stroke and brain volume. Results There was a significant positive global linear association between DTC and hyperintensity burden (adjusted Wilks’ λ = .87, P = .01). Amongst all WMH volumes, hyperintensity burden from basal ganglia + thalamus provided the most significant contribution to the global association (adjusted β = .008, η2 = .03; P = .04), independently of brain atrophy. Conclusions In poststroke, increased DTC may be an indicator of larger white matter damages, specifically in subcortical regions, which can potentially affect the overall cognitive processing and decrease gait automaticity by increasing the cortical control over patients’ locomotion.

Ninety-day complication rate based on 532 Latarjet procedures in six high volume and seven low volume Dutch hospitals.

In this study, we provide insight into the 90-day complication rates following the Latarjet procedure. The data are collected from 2015 from multiple hospitals in the Netherlands, with different volumes of Latarjet procedures. Our second aim is to examine which of the patients' and surgical factors are associated with a complication. A retrospective chart review has been conducted in 13 hospitals between 2015 and 2022. Data regarding complications within 90 days of Latarjet procedures were extracted. The effect of sex, age, BMI, smoking, previous shoulder operations, fixation material, hospital volume, screw size, and operation time on the complication rate was assessed by multivariable logistic regression analysis. From the 532 included patients 58 (10.9%) had a complication. Most common complications were material failure (n=19; 3.6%) and nerve injuries (n=13; 2.4%). The risk of complications was lower for males than for females (Odds ratio 0.40, CI: 0.21:0.77, p=0.006). Age, BMI, smoking, previous shoulder operations, type of fixation material, hospital volume, screw size, and operation time were not associated with a complication. The 90-day complication rate after a Latarjet procedure is 10.9% and is higher in females than in males. Age, BMI, smoking, previous shoulder operations, type of fixation material, hospital volume, screw size, and operation time did not affect complication rate. We advise setting up a national registry to prevent underreporting of complications.

REliability of consensus-based segMentatIoN in raDiomic feature reproducibility (REMIND): A word of caution

ObjectiveTo evaluate the reliability of consensus-based segmentation in terms of reproducibility of radiomic features. MethodsIn this retrospective study, three tumor data sets were investigated: breast cancer (n = 30), renal cell carcinoma (n = 30), and pituitary macroadenoma (n = 30). MRI was utilized for breast and pituitary data sets, while CT was used for renal data set. 12 readers participated in the segmentation process. Consensus segmentation was created by making corrections on a previous region or volume of interest. Four experiments were designed to evaluate the reproducibility of radiomic features. Reliability was assessed with intraclass correlation coefficient (ICC) with two cut-off values: 0.75 and 0.9. ResultsConsidering the lower bound of the 95% confidence interval and the ICC threshold of 0.90, at least 61% of the radiomic features were not reproducible in the inter-consensus analysis. In the susceptibility experiment, at least half (54%) became non-reproducible when the first reader is replaced with a different reader. In the intra-consensus analysis, at least about one-third (32%) were non-reproducible when the same second reader segmented the image over the same first reader two weeks later. Compared to inter-reader analysis based on independent single readers, the inter-consensus analysis did not statistically significantly improve the rates of reproducible features in all data sets and analyses. ConclusionsDespite the positive connotation of the word “consensus”, it is essential to REMIND that consensus-based segmentation has significant reproducibility issues. Therefore, the usage of consensus-based segmentation alone should be avoided unless a reliability analysis is performed, even if it is not practical in clinical settings.

Social media engagement and cryptocurrency performance.

Cryptocurrencies are highly speculative assets with large price volatility. If one could forecast their behavior, this would make them more attractive to investors. In this work we study the problem of predicting the future performance of cryptocurrencies using social media data. We propose a new model to measure the engagement of users with topics discussed on social media based on interactions with social media posts. This model overcomes the limitations of previous volume and sentiment based approaches. We use this model to estimate engagement coefficients for 48 cryptocurrencies created between 2019 and 2021 using data from Twitter from the first month of the cryptocurrencies' existence. We find that the future returns of the cryptocurrencies are dependent on the engagement coefficients. Cryptocurrencies whose engagement coefficients have extreme values have lower returns. Low engagement coefficients signal a lack of interest, while high engagement coefficients signal artificial activity which is likely from automated accounts known as bots. We measure the amount of bot posts for the cryptocurrencies and find that generally, cryptocurrencies with more bot posts have lower future returns. While future returns are dependent on both the bot activity and engagement coefficient, the dependence is strongest for the engagement coefficient, especially for short-term returns. We show that simple investment strategies which select cryptocurrencies with engagement coefficients exceeding a fixed threshold perform well for holding times of a few months.

Cadaveric study investigating the femoral nerve-sparing volume for pericapsular nerve group (PENG) block

BackgroundThis cadaveric study investigated the maximum effective volume of dye in 90% of cases (MEV90) required to stain the iliac bone between the anterior inferior iliac spine (AIIS) and the...

95% effective volume of ropivacaine for ultrasound‑guided supra‑inguinal fascia iliaca compartment block

BackgroundHip arthroplasty is effective in treating hip diseases, such as osteoarthritis and hip fracture, but it often brings severe trauma and pain. In recent years, ultrasound-guided supra-inguinal fascia iliaca compartment block(S-FICB) has become a widely used nerve block method for analgesia in hip arthroplasty.MethodsFifty-three patients preparing for hip arthroplasty were prospectively enrolled. S-FICB was performed under ultrasound guidance, and inject 0.33% ropivacaine into the space. Using the biased-coin design (BCD) sequential allocation method. The initial volume of 0.33% ropivacaine was 30ml. In case of failure, the next patient received a higher volume (defined as the previous volume with an increment of 1.2 mL). If the previous patient had a successful block, the next patient was randomized to a lower volume (defined as the previous volume with a decrement of 1.2 mL), with a probability of b = 0.05, or the same volume, with a probability of 1 − b = 0.95. The study was stopped when 45 successful blocks were achieved.ResultsForty-five patients (84.9%) were blocked successfully. The 95% effective volume (EV95) was 34.06ml (95%CI 33.35 ~ 36.28ml). There were 31 patients with non-fracture in this study. The quadriceps muscle strength decreased in only two patients. Moreover, they both received 34.8ml of ropivacaine for S-FICB. Twenty-two patients had hip fractures. There were 3 patients (14%) with failed blocks and 19 patients (86%) with successful blocks. However, all fracture patients experienced less pain after S-FICB.ConclusionEV95 of 0.33% ropivacaine for ultrasound-guided S-FICB was 34.06ml.Trial registrationThe trial was registered at the Chinese Clinical Trial Registry (registration number: ChiCTR2100052214, registration date: 2021 October 22).

Abstract 129: Cerebral Oxygen Extraction Fraction Predicts White Matter Lesion Progression In Patients With A Monogenic Cerebral Small Vessel Disease

Background: A rare, monogenic cerebral small vessel disease (cSVD), retinal vasculopathy with cerebral leukoencephalopathy and systemic manifestations (RVCL-S), is associated with progressive cerebral ischemia and accelerated vascular cognitive impairment, resulting in premature death. We hypothesized that low cerebral blood flow (CBF) and elevated oxygen extraction fraction (OEF), as metrics of microvascular ischemia, would predict growth of white matter lesions (WML) and other neuroimaging manifestations of cSVD. Methods: We prospectively performed sequential brain MRI in a cohort of RVCL-S participants. Pseudocontinuous arterial spin labeling and asymmetric spin echo quantified CBF and OEF in normal appearing white matter (NAWM), respectively. WMLs were manually delineated on FLAIR. WM volumes were segmented and quantified. Diffusion tensor imaging (DTI) was used to measure NAWM mean diffusivity (MD). Results: Each of 14 RVCL-S participants underwent a median of 4.5 scans (IQR 3 - 6.75) with a median of 6.5 months (IQR 5.8 - 8.6) between scans performed over 2.9 years (IQR 2.0 - 4.2). Elevated NAWM OEF from the previous MRI, but not CBF, was associated with WML growth (ρ = 0.672, p < 0.0001), WM atrophy (ρ = 0.654, p < 0.0001), and increased MD (ρ = 0.714, p < 0.0001, Figure). After adjusting for age, sex, previous WML volume, and participant, previous OEF remained an independent predictor of WML growth (β = 7.04 (1.08, 13.01), p = 0.021). NAWM OEF was not retained in the mixed models predicting WM atrophy and MD. Conclusion: We found evidence that hypoxic-ischemic physiology, as measured by elevated OEF in NAWM, independently predicted WML growth. Previous OEF was associated with WM atrophy and decrease in microstructural integrity on follow-up. This work suggests that ischemia in normal brain regions may be a harbinger of disease progression in patients with RVCL-S, an inherited cSVD. Additionally, OEF may serve as a potential predictive biomarker in sporadic cSVD.

What is the global glacier ice volume outside the ice sheets?

AbstractA recent study (Millan and others, 2022a, Nature Geoscience 15(2), 124–129) claims that ice volume contained in all glaciers outside the ice sheets and its potential contribution to sea level is 20% less than previously estimated. However, the apparent decrease is largely due to differences in choice of domain, as the study excludes 80% of the glacier area in the Antarctic periphery that was included in previous global glacier volume estimates. The issue highlights the difficulty in separating glaciers from the ice-sheet proper, especially in Antarctica, and the need for both the glacier and ice-sheet communities to develop standards and protocols to avoid double-counting in global ice volume and mass-change assessments and projections. Process-based inversion models have replaced earlier scaling methods, but large uncertainties in global glacier volume estimation remain due to the ill-posed nature of the inversion problem and poorly constrained parameters emphasizing the need for more direct ice thickness observations.

The Topographic Imaginary: Attending to Place in Contemporary French Photography

The Topographic Imaginary: Attending to Place in Contemporary French Photography

Is sleep a barrier to physical activity practice?

Is sleep a barrier to physical activity practice?

Withdrawal of bevacizumab is associated with rebound growth of vestibular schwannomas in neurofibromatosis type 2-related schwannomatosis patients.

Neurofibromatosis type 2 (NF2)-related schwannomatosis is an autosomal dominant tumor-predisposition syndrome characterized by bilateral vestibular schwannomas (VS). In patients with VS associated with NF2, vascular endothelial growth factor A inhibitor, bevacizumab, is a systemic treatment option. The aim of this study is to retrospectively evaluate NF2 patient responses to bevacizumab on VS growth and symptom progression. This is a retrospective analysis of patients seen at the Mayo Clinic Rochester Multidisciplinary NF2 Clinic. Out of 76 patients with NF2 evaluated between 2020 and 2022, we identified 19 that received treatment with bevacizumab. Thirteen of these patients discontinued bevacizumab after median treatment duration of 12.2 months. The remaining 6 patients are currently receiving bevacizumab treatment for a median duration of 9.4 months as of March, 2023. Fifteen patients had evaluable brain MRI data, which demonstrated partial responses in 5 patients, stable disease in 8, and progression in 2. Within 6 months of bevacizumab discontinuation, 5 patients had rebound growth of their VS greater than 20% from their previous tumor volume, while 3 did not. Three patients with rebound growth went on to have surgery or irradiation for VS management. Our single-institution experience confirms prior studies that bevacizumab can control progression of VS and symptoms associated with VS growth. However, we note that there is the potential for rapid VS growth following bevacizumab discontinuation, for which we propose heightened surveillance imaging and symptom monitoring for at least 6 months upon stopping anti-VEGF therapy.

Unspoken Magic by Emily Lloyd-Jones

Reviewed by: Unspoken Magic by Emily Lloyd-Jones April Spisak Lloyd-Jones, Emily Unspoken Magic. Greenwillow, 2023 [320p] Trade ed. ISBN 9780063058033 $16.99 E-book ed. ISBN 9780063058064 $9.99 Reviewed from digital galleys R Gr. 4-6 Six months after the events of Unseen Magic (BCCB 01/22), skittish protagonist Fin is much sturdier on her feet, confident in her own ability to solve problems and bolstered by her two best friends. She’s looking forward to a lazy spring break, but the arrival of a myth-busters film crew, drawn to her magical town known as a “hot spot for weirdness,” means Fin has to stop them from learning any of Aldermere’s secrets, including Fin’s unexpected discovery of a baby bigfoot. A giant rush of tourists would wreak havoc on Fin’s home, where creatures can roam on the outskirts, toll bridges are carefully avoided by those in the know, and the magically disappearing tea shop so prominent in the previous volume continues to do its thing. Lloyd-Jones offers a worthy return to Aldermere in this well-crafted sequel: the villains are more complex and troubled rather than evil, the three friends are scrappy and clever, sharing strengths and supporting each other in their weaknesses, and the baby bigfoot is absurdly endearing. A quick pace keeps things moving, as the book tracks Fin and friends’ efforts to avoid the film crew while also desperately looking for the baby’s family. Readers will likely feel the same sense of urgency as the trio as they protect this winsome town. [End Page 126] Copyright © 2022 The Board of Trustees of the University of Illinois

Research on Predicting Amazon Stock Price Based on Linear Regression and Decision Tree Algorithms

Stock price prediction is really popular in finance. A good stock price prediction can benefit investors. In this study, the stock price of Amazon was predicted using decision tree and linear regression. Besides this study compared the accuracy and prediction results of two algorithms. The prediction models use the previous stock price and volume as the predictor. This study finds that the Decision Tree algorithm fit a better model than the Linear Regression algorithm. It indicates that the Decision Tree algorithm fits a better model than the Linear Regression algorithm. Moreover, this study forecasts the Amazon's stock price for the next 60 days based on the two models. This research helps investors choose whether and when to buy Amazon stock.

CONCORDANCE OF REPRODUCTIVE AND THYROID HORMONE MEASUREMENTS BETWEEN VENIPUNCTURE AND CAPILLARY BLOOD SAMPLES THROUGHOUT THE MENSTRUAL CYCLE

At-home testing of reproductive and thyroid hormones are commercially available to assess reproductive health, however, there is limited evidence of the reliability and validity of the capillary blood sampling method utilised in these tests. Previous literature reports blood volume and collection tube type affects the measurement of hormones in venipuncture samples. We sought to assess the intra and inter sample variability in venipuncture and capillary blood and the effect of blood collection tube type on reproductive and thyroid hormone measurement.

High intraperitoneal interleukin-6 levels predict ultrafiltration (UF) insufficiency in peritoneal dialysis patients: A prospective cohort study.

IntroductionUF insufficiency is a major limitation in PD efficiency and sustainability. Our study object to investigate the efficacy of intraperitoneal inflammation marker, IL-6 level as a predictor of UF insufficiency in continuous ambulatory peritoneal dialysis (CAPD) patients.MethodsStable prevalent CAPD patients were enrolled in this prospective study. IL-6 concentration in the overnight effluent was determined and expressed as the IL-6 appearance rate (IL-6 AR). Patients were divided into two groups according to the median of IL-6 AR and prospectively followed up until death, transfer to permanent HD, recovery of renal function, kidney transplantation, transfer to other centers, lost to follow-up or to the end of study (January 31, 2021). Factors associated with UF capacity as well as dialysate IL-6 AR were assessed by multivariable linear regression. Cox proportional hazards model was used to examine the association between dialysate IL-6 AR and UF insufficiency.ResultsA total of 291 PD patients were enrolled, including 148 males (51%) with a mean age of 56.6 ± 14.1 years and a median PD duration of 33.4 (12.7–57.5) months. No correlation was found between dialysate IL-6 AR and UF capacity at baseline. PD duration was found positively correlated with baseline dialysate IL-6 AR, while 24h urine volume was negatively correlated with baseline dialysate IL-6 AR (P < 0.05). By the end of study, UF insufficiency was observed in 56 (19.2%) patients. Patients in the high IL-6 AR group showed a significantly inferior UF insufficiency-free survival when compared with their counterparts in the low IL-6 AR group (P = 0.001). In the multivariate Cox regression analysis, after adjusting for DM, previous peritonitis episode and 24h urine volume, higher baseline dialysate IL-6 AR (HR 3.639, 95% CI 1.776–7.456, P = 0.002) were associated with an increased risk of UF insufficiency. The area under the ROC curve (AUC) for baseline IL-6 AR to predict UF insufficiency was 0.663 (95% CI, 0.580–0.746; P < 0.001).ConclusionOur study suggested that the dialysate IL-6 AR could be a potential predictor of UF insufficiency in patients undergoing PD.

Trading volume and realized volatility forecasting: Evidence from the China stock market

AbstractThe existing contradictory findings on the contribution of trading volume to volatility forecasting prompt us to seek new solutions to test the sequential information arrival hypothesis (SIAH). Departing from other empirical analyses that mainly focus on sophisticated testing methods, this research offers new insights into the volume‐volatility nexus by decomposing and reconstructing the trading activity into short‐run components that typically represent irregular information flow and long‐run components that denote extreme information flow in the stock market. We are the first to attempt at incorporating an improved empirical mode decomposition (EMD) method to investigate the volatility forecasting ability of trading volume along with the Heterogeneous Autoregressive (HAR) model. Previous trading volume is used to obtain the decompositions to forecast the future volatility to ensure an ex ante forecast, and both the decomposition and forecasting processes are carried out by the rolling window scheme. Rather than trading volume by itself, the results show that the reconstructed components are also able to significantly improve out‐of‐sample realized volatility (RV) forecasts. This finding is robust both in one‐step ahead and multiple‐step ahead forecasting horizons under different estimation windows. We thus fill the gap in studies by (1) extending the literature on the volume‐volatility linkage to EMD‐HAR analysis and (2) providing a clear view on how trading volume helps improve RV forecasting accuracy.

ОПТИМІЗАЦІЯ ТЕХНОЛОГІЇ ХЛІБА З ВИКОРИСТАННЯМ БОРОШНА ГАРБУЗОВОГО

Bread and bakery products are widely used as basic food around the world. Recently, bakery products have been widely researched to develop functional foods by enriching active ingredients such as dietary fiber, biologically active peptides, minerals, vitamins, etc. to increase their nutritional and biological value. Bakery products are diversified by adding new ingredients. Laboratory and mathematical-statistical methods were used for research. The use of pumpkin flour for bread enrichment was analyzed. It was found that bread baking rate varied from 13.3±0.3% to 13.8±0.3% depending on the experiment variant. Variation coefficients of the samples were less than 3. Bread drying varied from 5.1±0.4% to 5.3±0.3 depending on the experiment variant. The sample variation was insignificant, but this indicator approached 10% and ranged from 4.5 to 7.2. Data samples from analytical replicates of the bread volume indicator had better quality indicators compared to shrinkage, which was due to insignificant data variation. There was a noticeable change in volume indicator depending on the research option from 158±3 cm3/100 g of dough to 220±3 cm3/100 g of dough. An increase in the proportion of pumpkin flour in bread resulted in volume decrease. Product volume changed similarly compared to 100 g of a mixture of wheat flour and pumpkin flour. Variation coefficients of these samples were quite low (coef V = 0.35–1.36). Similar to the previous product volume, the specific volume of dough and bread has changed. Sample variation of analytical replicates was insignificant (coef V = 0.78–2.00). Bread weight from 100 g of flour did not change significantly depending on the experiment variant, and the samples of analytical repetitions did not vary significantly. There have been noticeable changes in bread volume to dough volume. Depending on the experiment variant, bread volume varied from 2.1±0.02 (control) to 1.5±0.04 (20). The probability of sample variation of analytical replicates was quite low. Product convexity decreased from 0.48±0.02 (5) to 0.45±.02 (20) depending on the experiment variant. The variation of the sample data was insignificant (coef V = 2.12–4.44). The obtained results of primary statistical processing indicate high quality indicators and determine the possibility of data using for further statistical processing.

The Letters of Ernest Hemingway, V: 1932–1934 ed. by Sandra Spanier and Miriam B. Mandel

Reviewed by: The Letters of Ernest Hemingway, V: 1932–1934ed. by Sandra Spanier and Miriam B. Mandel William Blazek The Letters of Ernest Hemingway, V: 1932–1934. Ed. by S andraSP anierand M iriamB. M andelin association with K ristaQ uesenberry, V ernaK ale, and A lbertJ. D efazio III. Cambridge: Cambridge University Press. 2020. lxxxviii+699 pp. £22.99. ISBN 978–0–521–89737–2. Patrick Hemingway comments about his father in this book's Introduction: 'I think that his letters are one of the great records of the first two-thirds of the twentieth century' (p. xxviii). The fifth volume of the Ernest Hemingway's Letters Project, spanning the period from January 1932 to mid-1934, provides firm support for that assertion, building a vibrant picture of the author in his prime. During these two and a half years, Hemingway completed his bullfighting-cum-writing manual Death in the Afternoon(November 1932) and published his third collection of short stories, Winner Take Nothing(October 1933), along with other stories for popular [End Page 494]literary magazines and non-fiction articles for the newly established Esquiremen's magazine. Behind the public products of his craft and the growing celebrity of the man, his letters reveal the compulsive drive and sheer hard labour that went into his writing, 'my life work' (p. 369), always honed to his own exacting standards. Confidently telling his editor at Scribners, Max Perkins, that ' all the timeI can write better stories than anybody else writing' (p. 542), he explains: 'I am trying to make, before I get through, a picture of the whole world—or as much of it as I have seen. Boiling it down always, rather than spreading it out thin' (p. 508). He was a tough but fair negotiator with his publishers during these early years of the Great Depression, insistent on the quantity of photographs to be included in Death in the Afternoon, berating them for not advertising Winner Take Nothingstrongly enough, admonishing them for delays in providing proofs or timidity in censoring words, while always determined in his aim to write 'truly'. The sources for most of his writing were activities that thrilled and tested him. The previous volume of letters chronicled his introduction to big-game rifle hunting in Montana and Wyoming, and this collection sees him developing that avocation as well as immersing himself in deep-sea fishing in the Gulf of Mexico between Key West and Havana. The final portion of these letters finds him on his first African hunting safari, travelling with his second wife, Pauline Pfeiffer, on an expensive trip funded by her generous uncle Gus (a reliable benefactor during the marriage). 'I like to shoot a rifle and I like to kill,' Hemingway reported to a journalist friend, 'and Africa is where you do that' (p. 374). The carnage was severe. Between the Montana mountains, Caribbean waters, and African plains his contribution to the Anthropocene included the killing of grizzly bears, elk, eagles, grouse, jackrabbits, some unfortunate magpies and doves, fifty-four swordfish in one season—among them a record-breaking 12 foot 8 inch long, 468-pound black marlin and a 119.5-pound sailfish—and lions, rhinos, buffaloes, kudus, impalas, elands, gazelles, other antelopes, a leopard, cheetahs, zebras, warthogs, several hyenas, and various native birds. The excitement and challenge of marlin fishing was his chief passion during these years, engaged through intense research and experience in the same way in which he became an expert analyst of bullfighting. In time, when knowledge settled into reflection, he would write books about the Caribbean and Africa; but in what would prove this mid-life period, he wrote short stories in the morning, from 5 a.m. or earlier, leaving all afternoon for fishing—by the end of this volume in his new 38-foot cabin cruiser, the Pilar. Battling with giant bears and powerful fish proved easier on his ego than the increasingly antagonistic relationship Hemingway developed with critics, magazine editors, and fellow writers. The origins of his fight with Max Eastman over a critical review of Death in the Afternoonare presented...

Automated Cardiac Chamber Size and Cardiac Physiology Measurement in Water Fleas by U-Net and Mask RCNN Convolutional Networks.

Simple SummaryWith the rapid development of technology, artificial intelligent become a major breakthrough that can help human with laborious job. Previously cardiac imaging in Daphnia was also suffer from laborious and tedious process to extract some information from it. Thus the aim of this study was to develop a simple artificial intelligent based method to help anyone in this field to perform analysis in fast, reliable, and less tedious manner. In this study, we compare U-Net and Mask RCNN and found out that Mask RCNN was perform better than U-Net in cardiac chamber area estimation. From this data, several parameter like heart rhythm, stroke volume, ejection fraction, fractional shortening, and cardiac output can be extracted. The validation was done by comparing the normal and Roundup exposed group and it show that Roundup can increase the stroke volume, cardiac output, and the shortening fraction of Daphnia magna.Water fleas are an important lower invertebrate model that are usually used for ecotoxicity studies. Contrary to mammals, the heart of a water flea has a single chamber, which is relatively big in size and with fast-beating properties. Previous cardiac chamber volume measurement methods are primarily based on ImageJ manual counting at systolic and diastolic phases which suffer from low efficiency, high variation, and tedious operation. This study provides an automated and robust pipeline for cardiac chamber size estimation by a deep learning approach. Image segmentation analysis was performed using U-Net and Mask RCNN convolutional networks on several different species of water fleas such as Moina sp., Daphnia magna, and Daphnia pulex. The results show that Mask RCNN performs better than U-Net at the segmentation of water fleas’ heart chamber in every parameter tested. The predictive model generated by Mask RCNN was further analyzed with the Cv2.fitEllipse function in OpenCV to perform a cardiac physiology assessment of Daphnia magna after challenging with the herbicide of Roundup. Significant increase in normalized stroke volume, cardiac output, and the shortening fraction was observed after Roundup exposure which suggests the possibility of heart chamber alteration after roundup exposure. Overall, the predictive Mask RCNN model established in this study provides a convenient and robust approach for cardiac chamber size and cardiac physiology measurement in water fleas for the first time. This innovative tool can offer many benefits to other research using water fleas for ecotoxicity studies.

Predicting Visual Acuity in Patients Treated for AMD.

The leading diagnostic tool in modern ophthalmology, Optical Coherence Tomography (OCT), is not yet able to establish the evolution of retinal diseases. Our task is to forecast the progression of retinal diseases by means of machine learning technologies. The aim is to help the ophthalmologist to determine when early treatment is needed in order to prevent severe vision impairment or even blindness. The acquired data are made up of sequences of visits from multiple patients with age-related macular degeneration (AMD), which, if not treated at the appropriate time, may result in irreversible blindness. The dataset contains 94 patients with AMD and there are 161 eyes included with more than one medical examination. We used various techniques from machine learning (linear regression, gradient boosting, random forest and extremely randomised trees, bidirectional recurrent neural network, LSTM network, GRU network) to handle technical challenges such as how to learn from small-sized time series, how to handle different time intervals between visits, and how to learn from different numbers of visits for each patient (1–5 visits). For predicting the visual acuity, we performed several experiments with different features. First, by considering only previous measured visual acuity, the best accuracy of 0.96 was obtained based on a linear regression. Second, by considering numerical OCT features such as previous thickness and volume values in all retinal zones, the LSTM network reached the highest score (). Third, by considering the fundus scan images represented as embeddings obtained from the convolutional autoencoder, the accuracy was increased for all algorithms. The best forecasting results for visual acuity depend on the number of visits and features used for predictions, i.e., 0.99 for LSTM based on three visits (monthly resampled series) based on numerical OCT values, fundus images, and previous visual acuities.