Median Absolute Error Research Articles

Platform-independent estimation of human physiological time from single blood samples.

Abundant epidemiological evidence links circadian rhythms to human health, from heart disease to neurodegeneration. Accurate determination of an individual's circadian phase is critical for precision diagnostics and personalized timing of therapeutic interventions. To date, however, we still lack an assay for physiological time that is accurate, minimally burdensome to the patient, and readily generalizable to new data. Here, we present TimeMachine, an algorithm to predict the human circadian phase using gene expression in peripheral blood mononuclear cells from a single blood draw. Once trained on data from a single study, we validated the trained predictor against four independent datasets with distinct experimental protocols and assay platforms, demonstrating that it can be applied generalizably. Importantly, TimeMachine predicted circadian time with a median absolute error ranging from 1.65 to 2.7 h, regardless of systematic differences in experimental protocol and assay platform, without renormalizing the data or retraining the predictor. This feature enables it to be flexibly applied to both new samples and existing data without limitations on the transcriptomic profiling technology (microarray, RNAseq). We benchmark TimeMachine against competing approaches and identify the algorithmic features that contribute to its performance.

Cell Tree Rings: the structure of somatic evolution as a human aging timer

Biological age is typically estimated using biomarkers whose states have been observed to correlate with chronological age. A persistent limitation of such aging clocks is that it is difficult to establish how the biomarker states are related to the mechanisms of aging. Somatic mutations could potentially form the basis for a more fundamental aging clock since the mutations are both markers and drivers of aging and have a natural timescale. Cell lineage trees inferred from these mutations reflect the somatic evolutionary process, and thus, it has been conjectured, the aging status of the body. Such a timer has been impractical thus far, however, because detection of somatic variants in single cells presents a significant technological challenge. Here, we show that somatic mutations detected using single-cell RNA sequencing (scRNA-seq) from thousands of cells can be used to construct a cell lineage tree whose structure correlates with chronological age. De novo single-nucleotide variants (SNVs) are detected in human peripheral blood mononuclear cells using a modified protocol. A default model based on penalized multiple regression of chronological age on 31 metrics characterizing the phylogenetic tree gives a Pearson correlation of 0.81 and a median absolute error of ~4 years between predicted and chronological ages. Testing of the model on a public scRNA-seq dataset yields a Pearson correlation of 0.85. In addition, cell tree age predictions are found to be better predictors of certain clinical biomarkers than chronological age alone, for instance glucose, albumin levels, and leukocyte count. The geometry of the cell lineage tree records the structure of somatic evolution in the individual and represents a new modality of aging timer. In addition to providing a numerical estimate of “cell tree age,” it unveils a temporal history of the aging process, revealing how clonal structure evolves over life span. Cell Tree Rings complements existing aging clocks and may help reduce the current uncertainty in the assessment of geroprotective trials.

Accuracy of Modern and Traditional Intraocular Lens Power Calculation Formulas in Pediatric Cataract Surgery.

To compare the accuracy of modern intraocular lens (IOL) power calculation formulas with that of older formulas, such as SRK/T and Hoffer Q, in pediatric cataract surgery. This retrospective study included 100 eyes of 100 children who underwent routine cataract surgery with primary IOL implantation in a bag. This study used four IOLMaster 700 integrated formulas: SRK/T, Hoffer Q, Haigis, and Barrett Universal II (BUII). In addition, the following formulas were used: EVO 2.0, Hill RBF 3.0, Hoffer QST, Kane, and PEARL DGS, which are available online. There was a statistically significant difference between SRK/T and most other formulas, except for Hoffer Q, Hoffer QST, and BUII (p < 0.05). SRK/T yielded the lowest median absolute error (MedAE) of 0.63 D. This was followed by the BUII (0.66 D), Hoffer Q, and Hoffer QST (0.68 D). SRK/T also yielded the highest percentage of cases within ± 0.50 D (43% of the cases). For patients aged 2 to 5 years, SRK/T formula yielded statistically significantly better results than all other included formulas (p < 0.05) with MedAE = 0.44 D, 58.33% and 87.50% of the cases were within ± 0.50 D and ± 1.0 D of intended refraction, respectively. The SRK/T formula showed the best IOL power calculation results in pediatric cataract surgery, followed by BUII, Hoffer Q, and Hoffer QST. In children aged 2-5 years, the SRK/T formula outperformed all other formulas, followed by the BUII and Hoffer QST formulas. In children older than 5 years, there was no statistically significant difference between the different formulas (p > 0.05); Hoffer Q and SRK/T showed slightly better MedAE in this age group (5-10 years).

Assessment of Sensorized Insoles in Balance and Gait in Individuals With Parkinson's Disease.

Individuals with Parkinson's disease (PD) are characterized by gait and balance disorders limiting their independence and quality of life. Home-based rehabilitation programs, combined with drug therapy, demonstrated to be beneficial in the daily-life activities of PD subjects. Sensorized shoes can extract balance- and gait-related data in home-based scenarios and allow clinicians to monitor subjects' activities. In this study, we verified the capability of a pair of sensorized shoes (including pressure-sensitive insoles and one inertial measurement unit) in assessing ground-level walking and body weight shift exercises. The shoes can potentially be combined with a sensory biofeedback module that provides vibrotactile cues to individuals. Sensorized shoes have been assessed in terms of the capability of detecting relevant gait events (heel strike, flat foot, toe off), estimating spatiotemporal parameters of gait (stance, swing, and double support duration, stride length), estimating gait variables (vertical ground-reaction force, vGRF; coordinate of the center of pressure along the longitudinal axes of the feet, yCoP; and the dorsiflexion angle of the feet, Pitch angle). The assessment compared the outcomes with those extracted from the gold standard equipment, namely force platforms and a motion capture system. Results of this comparison with 9 PD subjects showed an overall median absolute error lower than 0.03 s in detecting the foot-contact, foot-off, and heel-off gait events while performing ground-level walking and lower than 0.15 s in body weight shift exercises. The computation of spatiotemporal parameters of gait showed median errors of 1.62 % of the stance phase duration and 0.002 m of the step length. Regarding the estimation of vGRF, yCoP, and Pitch angle, the median across-subjects Pearson correlation coefficient was 0.90, 0.94, and 0.91, respectively. These results confirm the suitability of the sensorized shoes for quantifying biomechanical features during body weight shift and gait exercises of PD and pave the way to exploit the biofeedback modules of the bidirectional interface in future studies.

A Comprehensive Evaluation of 16 Old and New Intraocular Lens Power Calculation Formulas in Pediatric Eyes.

To compare the accuracy of 16 intraocular lens (IOL) power calculation formulas in pediatric cataract eyes. The data records of pediatric patients who had been implanted with three IOL models (SA60AT, MA60AC, and enVista-MX60) between 2012 and 2018 were analyzed. The accuracy of 16 IOL power calculation methods was evaluated: Barrett Universal II (BUII), Castrop, EVO 2.0, Haigis, Hill-RBF 3.0, Hoffer Q, Hoffer QST, Holladay 1, Kane, LSF AI, Naeser 2, Pearl-DGS, SRK/T, T2, VRF, and VRF-G. The non-optimized (ULIB/IOLcon) and optimized constants were used for IOL power calculation. The mean prediction error (PE), Performance Index (FPI), and all descriptive statistics were calculated. Ninety-seven eyes of 97 pediatric patients aged 13.2 (IQR 11.2-17.1) were included. No statistically significant difference (HS-test) was observed (p > 0.818) except for the Hoffer Q, and Naeser 2 (P = 0.014). With optimized lens constants, the best FPI indices were obtained by Hoffer Q (0.256) and VRF-G (0.251) formulas, followed by Hill-RBF 3.0 and BUII, with an index of 0.248. The highest FPI indices with non-optimized constants showed SRK/T and T2 formulas (0.246 and 0.245, respectively), followed by VRF-G and Holladay 1, with an index of 0.244. The best median absolute error values (MedAE) were achieved by Hoffer Q (0.50 D), VRF-G (0.53 D), and Hill-RBF 3.0 (0.54 D), all P ≥ 0.074. Our results place the Hoffer Q, VRF-G, Hill-RBF 3.0, and BUII formulas as more accurate predictors of postoperative refraction in pediatric cataract surgery.

Calculating Relative Lung Perfusion Using Fluoroscopic Sequences and Image Analysis: The Fluoroscopic Flow Calculator.

Maldistribution of pulmonary blood flow in patients with congenital heart disease impacts exertional performance and pulmonary artery growth. Currently, measurement of relative pulmonary perfusion can only be performed outside the catheterization laboratory. We sought to develop a tool for measuring relative lung perfusion using readily available fluoroscopy sequences. A retrospective cohort study was conducted on patients with conotruncal anomalies who underwent lung perfusion scans and subsequent cardiac catheterizations between 2011 and 2022. Inclusion criteria were nonselective angiogram of pulmonary vasculature, oblique angulation ≤20°, and an adequate view of both lung fields. A method was developed and implemented in 3D Slicer's SlicerHeart extension to calculate the amount of contrast that entered each lung field from the start of contrast injection and until the onset of levophase. The predicted perfusion distribution was compared with the measured distribution of pulmonary blood flow and evaluated for correlation, accuracy, and bias. In total, 32% (79/249) of screened studies met the inclusion criteria. A strong correlation between the predicted flow split and the measured flow split was found (R2=0.83; P<0.001). The median absolute error was 6%, and 72% of predictions were within 10% of the true value. Bias was not systematically worse at either extreme of the flow distribution. The prediction was found to be more accurate for either smaller and younger patients (age 0-2 years), for right ventricle injections, or when less cranial angulations were used (≤20°). In these cases (n=40), the prediction achieved R2=0.87, median absolute error of 5.5%, and 78% of predictions were within 10% of the true flow. The current study demonstrates the feasibility of a novel method for measuring relative lung perfusion using conventional angiograms. Real-time measurement of lung perfusion at the catheterization laboratory has the potential to reduce unnecessary testing, associated costs, and radiation exposure. Further optimization and validation is warranted.

The effect of patient age on some new and older IOL power calculation formulas.

To assess the accuracy of intraocular lens (IOL) power calculation in different age groups using various IOL calculation formulas. Data from 421 eyes of 421 patients ≥60 years old (ages: 60-69, n = 131; 70-74, n = 105; 75-84, n = 158 and ≥85, n = 27), who underwent uneventful cataract surgery with SN60WF IOL implantation at John A. Moran Eye Center, Salt Lake City, USA, were retrospectively obtained. The SD of the prediction error (PE), median and mean absolute PEs and the percentage of eyes within ±0.25, ±0.50, ±0.75 and ±1.00 D were calculated after constant optimizations for the following formulas: Barrett Universal II (BUII), Emmetropia Verifying Optical (EVO) 2.0, Haigis, Hoffer Q, Hoffer QST, Holladay 1, Kane, Radial Basis Function (RBF) 3.0 and SRK/T. Results were compared between the different age groups. Predictability rates within 0.25D were lower for the eldest age group compared with the other groups using the EVO 2.0 (33% vs. 37%-53%, p = 0.045), Kane (26% vs. 35%-50%, p = 0.034) and SRK/T (22% vs. 31%-49%, p = 0.002). Higher median absolute refractive errors for all formulas were observed in the oldest group [range: 0.39 D (Haigis, Hoffer QSR)-0.48 D (Kane)], followed by the youngest group [range: 0.30 D (RBF 3.0)-0.39 D (Holladay 1, SRK/T)] but did not reach statistical significance. No significant differences between the groups in the distribution parameter were seen. Current IOL power calculation formulas may have variable accuracy for different age groups. This should be taken into account when planning cataract surgery to improve refractive outcomes.

Word Recognition with a Cochlear Implant in Relation to Prediction and Electrode Position.

the word recognition score (WRS) achieved with cochlear implants (CIs) varies widely. To account for this, a predictive model was developed based on patients' age and their pre-operative WRS. This retrospective study aimed to find out whether the insertion depth of the nucleus lateral-wall electrode arrays contributes to the deviation of the CI-achieved WRS from the predicted WRS. patients with a pre-operative maximum WRS > 0 or a pure-tone audiogram ≥80 dB were included. The insertion depth was determined via digital volume tomography. fifty-three patients met the inclusion criteria. The median WRS achieved with the CI was 70%. The comparison of pre- and post-operative scores achieved with a hearing aid and a CI respectively in the aided condition showed a median improvement of 65 percentage points (pp). A total of 90% of the patients improved by at least 20 pp. The majority of patients reached or exceeded the prediction, with a median absolute error of 11 pp. No significant correlation was found between the deviation from the predicted WRS and the insertion depth. our data support a previously published model for the prediction of the WRS after cochlear implantation. For the lateral-wall electrode arrays evaluated, the insertion depth did not influence the WRS with a CI.

Machine learning framework for the real-time reconstruction of regional 4D ocean temperature fields from historical reanalysis data and real-time satellite and buoy surface measurements

The ability to model 4D properties of near-coast ocean regions in real time is valuable for both general environmental monitoring and for specialized industry applications. We present a computationally parsimonious framework to build improved spatiotemporal models that combine dynamics inferred from historical high-fidelity model outputs and real-time sensor measurements. We are motivated by a temperature data set of the Massachusetts Bay from sensors that can only obtain measurements at the ocean’s surface. We first apply standard principal component analysis (PCA) to a historical reanalysis data set of the time-evolving 3D (x,y,z) temperature field. Next, we train a temporal convolutional neural network (TCN) to predict the time coefficients of the vertical PCA modes, and their variance, as a function of surface temperature. Simultaneously, we estimate the time-evolving 2D (x,y) surface temperature field from the satellite and buoy measurements with multi-fidelity Gaussian process regression (GPR). Finally, the surface temperature is used as input to the neural network to probabilistically predict the PCA coefficients and reconstruct the full 4D temperature field. The results are compared to in-situ measurements at all depths, and the median absolute error is found to be 0.97°C. Overall, the proposed framework is able to produce more accurate models in less time, and the uncertainty quantification can be leveraged for future decision-making.

Forecasting influenza hospital admissions within English sub-regions using hierarchical generalised additive models

BackgroundSeasonal influenza places a substantial burden annually on healthcare services. Policies during the COVID-19 pandemic limited the transmission of seasonal influenza, making the timing and magnitude of a potential resurgence difficult to ascertain and its impact important to forecast.MethodsWe have developed a hierarchical generalised additive model (GAM) for the short-term forecasting of hospital admissions with a positive test for the influenza virus sub-regionally across England. The model incorporates a multi-level structure of spatio-temporal splines, weekly cycles in admissions, and spatial correlation. Using multiple performance metrics including interval score, coverage, bias, and median absolute error, the predictive performance is evaluated for the 2022-2023 seasonal wave. Performance is measured against autoregressive integrated moving average (ARIMA) and Prophet time series models.ResultsAcross the epidemic phases the hierarchical GAM shows improved performance, at all geographic scales relative to the ARIMA and Prophet models. Temporally, the hierarchical GAM has overall an improved performance at 7 and 14 day time horizons. The performance of the GAM is most sensitive to the flexibility of the smoothing function that measures the national epidemic trend.ConclusionsThis study introduces an approach to short-term forecasting of hospital admissions for the influenza virus using hierarchical, spatial, and temporal components. The methodology was designed for the real time forecasting of epidemics. This modelling framework was used across the 2022-2023 winter for healthcare operational planning by the UK Health Security Agency and the National Health Service in England.

Forecasting daily COVID-19 cases with gradient boosted regression trees and other methods: evidence from U.S. cities.

There is a vast literature on the performance of different short-term forecasting models for country specific COVID-19 cases, but much less research with respect to city level cases. This paper employs daily case counts for 25 Metropolitan Statistical Areas (MSAs) in the U.S. to evaluate the efficacy of a variety of statistical forecasting models with respect to 7 and 28-day ahead predictions. This study employed Gradient Boosted Regression Trees (GBRT), Linear Mixed Effects (LME), Susceptible, Infectious, or Recovered (SIR), and Seasonal Autoregressive Integrated Moving Average (SARIMA) models to generate daily forecasts of COVID-19 cases from November 2020 to March 2021. Consistent with other research that have employed Machine Learning (ML) based methods, we find that Median Absolute Percentage Error (MAPE) values for both 7-day ahead and 28-day ahead predictions from GBRTs are lower than corresponding values from SIR, Linear Mixed Effects (LME), and Seasonal Autoregressive Integrated Moving Average (SARIMA) specifications for the majority of MSAs during November-December 2020 and January 2021. GBRT and SARIMA models do not offer high-quality predictions for February 2021. However, SARIMA generated MAPE values for 28-day ahead predictions are slightly lower than corresponding GBRT estimates for March 2021. The results of this research demonstrate that basic ML models can lead to relatively accurate forecasts at the local level, which is important for resource allocation decisions and epidemiological surveillance by policymakers.

Vertically Resolved Global Ocean Light Models Using Machine Learning

The vertical distribution of light and its spectral composition are critical factors influencing numerous physical, chemical, and biological processes within the oceanic water column. In this study, we present vertically resolved models of downwelling irradiance (ED) at three different wavelengths and photosynthetically available radiation (PAR) on a global scale. These models rely on the SOCA (Satellite Ocean Color merged with Argo data to infer bio-optical properties to depth) methodology, which is based on an artificial neural network (ANN). The new light models are trained with light profiles (ED/PAR) acquired from BioGeoChemical-Argo (BGC-Argo) floats. The model inputs consist of surface ocean color radiometry data (i.e., Rrs, PAR, and kd(490)) derived by satellite and extracted from the GlobColour database, temperature and salinity profiles originating from BGC-Argo, as well as temporal components (day of the year and local time in cyclic transformation). The model outputs correspond to ED profiles at the three wavelengths of the BGC-Argo measurements (i.e., 380, 412, and 490 nm) and PAR profiles. We assessed the retrieval of light profiles by these light models using three different datasets: BGC-Argo profiles that were not used for the training (i.e., 20% of the initial database); data from four independent BGC-Argo floats that were used neither for the training nor for the 20% validation dataset; and the SeaBASS database (in situ data collected from various oceanic cruises). The light models show satisfactory predictions when thus compared with real measurements. From the 20% validation database, the light models retrieve light variables with high accuracies (root mean squared error (RMSE)) of 76.42 μmol quanta m−2 s−1 for PAR and 0.04, 0.08, and 0.09 W m−2 nm−1 for ED380, ED412, and ED490, respectively. This corresponds to a median absolute percent error (MAPE) that ranges from 37% for ED490 and PAR to 39% for ED380 and ED412. The estimated accuracy metrics across these three validation datasets are consistent and demonstrate the robustness and suitability of these light models for diverse global ocean applications.

Efficacy of corneal curvature on the accuracy of 8 intraocular lens power calculation formulas in 302 highly myopic eyes.

To investigate the effect of corneal curvature (K) on the accuracy of 8 intraocular lens formulas in highly myopic eyes. Eye Hospital and School of Ophthalmology and Optometry, Wenzhou Medical University, Wenzhou, China. Retrospective consecutive case series. 302 eyes (302 patients) were analyzed in subgroups based on the K value. The mean refractive error, mean absolute error (MAE), median absolute error (MedAE), root-mean-square absolute prediction error (RMSAE) and proportions of eyes within ±0.25 diopter (D), ±0.50 D, ±0.75 D, ±1.00 D were statistical analyzed. Emmetropia Verifying Optical (EVO) 2.0, Kane, and Radial Basis Function (RBF) 3.0 had the lower MAE (≤0.28) and RMSAE (≤0.348) and highest percentage of eyes within ±0.50 D (≥83.58%) in the flat (K ≤ 43 D) and steep K (K > 45 D) groups. Hoffer QST had the lowest MedAE (0.19), RMSAE (0.351) and the highest percentage of eyes within ±0.50 D (82.98%) in the normal K group (43 < K ≤ 45 D). When axial length (AL) ≤28 mm, all formulas showed close RMSAE values (0.322 to 0.373) in flat K group. When AL >28 mm, RBF 3.0 achieved the lowest MAE (≤0.24), MedAE (≤0.17) and RMSAE (≤0.337) across all subgroups. EVO 2.0, Kane, and RBF 3.0 were the most accurate in highly myopic eyes with a flat or steep K. Hoffer QST is recommended for long eyes with normal K values. RBF 3.0 showed the highest accuracy when AL >28 mm, independent of corneal curvature.

Review of the targeting accuracy of frameless and frame-based robot-assisted deep brain stimulation electrode implantation in pediatric patients using the Neurolocate module.

The Neurolocate module is a 3D frameless patient registration module that is designed for use with the Neuromate stereotactic robot. Long-term electrical stimulation of the globus pallidus internus (GPi) and subthalamic nucleus (STN) via deep brain electrode implantation is particularly successful in a select group of movement disorders in pediatric patients. This study aimed to review the targeting accuracy of deep brain stimulation (DBS) electrode implantation in a single center, comparing standard frame-based techniques to the frameless Neurolocate module. Twenty-four pediatric patients underwent implantation of bilateral DBS electrodes under general anesthesia during the period of August 2018-August 2022. All patients underwent robot-assisted stereotactic implantation of DBS electrodes using an intraoperative O-arm 3D scanner to confirm the final electrode position. These coordinates were compared with the planned entry and target, with attention to depth, radial, directional, and absolute errors, in addition to Euclidean distance (ED). The primary outcome evaluated the accuracy and safety of the Neurolocate frameless technology compared with standard frame-based techniques. Of the 24 bilateral DBS electrode implantations performed, 62.5% used Neurolocate technology: 87.5% were delivered to the GPi and the remaining 12.5% to the STN. The mean patient age was 11.0 (range 4-18) years and 70.8% were male. The median absolute errors in x-, y-, and z-axes were 0.35, 0.75, and 0.9 mm, respectively, using the Neurolocate module compared with 0.30, 0.95, and 1.1 mm using the standard frame-based technique. The median ED from the planned target to the actual electrode position with the Neurolocate module was 1.28 mm versus 1.69 mm using standard frame-based techniques. No major perioperative complications occurred. Stereotactic robot-assisted DBS implantation with the frameless Neurolocate module is safe for use in the pediatric population, showing good surgical accuracy and no inferiority to standard frame-based techniques. The Neurolocate module for robotic DBS surgery has the potential to improve surgical targeting accuracy, surgical time, patient comfort, and safety.

Prospective evaluation of the ESCRS online calculator for calculation of a multifocal intraocular lens.

To evaluate a recently introduced ESCRS online calculator for intraocular lens (IOL) calculation of a multifocal IOL in refractive lens exchange and cataract surgery in a prospective setting. Department of Ophthalmology, Goethe University Frankfurt, Germany. Prospective, consecutive case series. We included eyes that received lens extraction and multifocal IOL implantation. We compared the mean prediction error (MPE), mean and median absolute prediction error (MAE, MedAE) of the online calculator provided by the European Society of Cataract and Refractive Surgeons (ESCRS), and number of eyes within ±0.5, ±1.0, ±2.0 diopters (D) of target refraction. Additionally, the SRK/T formula was included for comparison as well. Postoperative spherical equivalent was measured at 3 months. Only one eye per patient was included. Eighty-eight eyes from 88 patients with mean age of 62 years ± 9.5 were included. The MedAE was low for all formulas and ranged from 0.26D (Kane), Hill-RBF (0.27D), Hoffer QST (0.27D), Barrett (0.28D), EVO (0.29D), Cooke K6 (0.27D), 0.30D (Pearl DGS) to 0.31D (SRK/T). No statistically significant difference was found (p = 0.627). Considering the number of eyes within ±0.5D of the calculated refraction the best performing was again the Hill-RBF (84%, 74 eyes), again followed by Kane (71, 81%), EVO, Pearl DGS, Hoffer QST, Barrett (each 80%, 70 eyes),Cooke K6 (78%, 69 eyes), and SRK/T (74%). Again, no statistically significant difference was found (p = 0.39). Using recently introduced ESCRS online IOL calculator in multifocal intraocular lenses leads to a high number of eyes reaching target refraction and low prediction errors. All formulas performed similar well. However, Hill-RBF showed the highest number of eyes within ±0.5D, but no significance was found regarding this.

Comparison of intraocular lens power calculation formulas in patients with a history of acute primary angle-closure attack

BackgroundTo compare the accuracy of nine intraocular lens (IOL) power calculation formulas, including three traditional formulas (SRK/T, Haigis, and Hoffer Q) and six new-generation formulas (Barrett Universal II [BUII], Hill-Radial Basis Function [RBF] 3.0, Kane, Emmetropia verifying optical [EVO], Ladas Super, and Pearl-DGS) in patients who underwent cataract surgery after acute primary angle closure (APAC).MethodsIn this retrospective cross-sectional study, 44 eyes of 44 patients (APAC) and 60 eyes of 60 patients (control) were included. We compared the mean absolute error, median absolute error (MedAE), and prediction error after surgery. Subgroup analyses were performed on whether axial length (AL) or preoperative laser peripheral iridotomy affected the postoperative refractive outcomes.ResultsIn the APAC group, all formulas showed higher MedAE and more myopic shift than the control group (all P < 0.05). In APAC eyes with AL ≥ 22 mm, there were no differences in MedAEs according to the IOL formulas; however, in APAC eyes with AL < 22 mm, Haigis (0.49 D) showed lower MedAE than SRK/T (0.82 D) (P = 0.036) and Hill-RBF 3.0 (0.54 D) showed lower MedAE than SRK/T (0.82 D), Hoffer Q (0.75 D) or Kane (0.83 D) (P = 0.045, 0.036 and 0.027, respectively). Pearl-DGS (0.63 D) showed lower MedAE than Hoffer Q (0.75 D) and Kane (0.83 D) (P = 0.045 and 0.036, respectively). Haigis and Hill-RBF 3.0 showed the highest percentage (46.7%) of eyes with PE within ± 0.5 D in APAC eyes with AL < 22 mm. Iridectomized eyes did not show superior precision than the non-iridotomized eyes in the APAC group.ConclusionsRefractive errors in the APAC group were more myopic than those in the control group. Haigis and Hill-RBF 3.0 showed high precision in the eyes with AL < 22 mm in the APAC group.

An Optimized Model Based on Deep Learning and Gated Recurrent Unit for COVID-19 Death Prediction.

The COVID-19 epidemic poses a worldwide threat that transcends provincial, philosophical, spiritual, radical, social, and educational borders. By using a connected network, a healthcare system with the Internet of Things (IoT) functionality can effectively monitor COVID-19 cases. IoT helps a COVID-19 patient recognize symptoms and receive better therapy more quickly. A critical component in measuring, evaluating, and diagnosing the risk of infection is artificial intelligence (AI). It can be used to anticipate cases and forecast the alternate incidences number, retrieved instances, and injuries. In the context of COVID-19, IoT technologies are employed in specific patient monitoring and diagnosing processes to reduce COVID-19 exposure to others. This work uses an Indian dataset to create an enhanced convolutional neural network with a gated recurrent unit (CNN-GRU) model for COVID-19 death prediction via IoT. The data were also subjected to data normalization and data imputation. The 4692 cases and eight characteristics in the dataset were utilized in this research. The performance of the CNN-GRU model for COVID-19 death prediction was assessed using five evaluation metrics, including median absolute error (MedAE), mean absolute error (MAE), root mean squared error (RMSE), mean square error (MSE), and coefficient of determination (R2). ANOVA and Wilcoxon signed-rank tests were used to determine the statistical significance of the presented model. The experimental findings showed that the CNN-GRU model outperformed other models regarding COVID-19 death prediction.

The accuracy of intraocular lens power calculation formulas based on artificial intelligence in highly myopic eyes: a systematic review and network meta-analysis.

To systematically compare and rank the accuracy of AI-based intraocular lens (IOL) power calculation formulas and traditional IOL formulas in highly myopic eyes. We screened PubMed, Web of Science, Embase, and Cochrane Library databases for studies published from inception to April 2023. The following outcome data were collected: mean absolute error (MAE), percentage of eyes with a refractive prediction error (PE) within ±0.25, ±0.50, and ±1.00 diopters (D), and median absolute error (MedAE). The network meta-analysis was conducted by R 4.3.0 and STATA 17.0. Twelve studies involving 2,430 adult myopic eyes (with axial lengths >26.0 mm) that underwent uncomplicated cataract surgery with mono-focal IOL implantation were included. The network meta-analysis of 21 formulas showed that the top three AI-based formulas, as per the surface under the cumulative ranking curve (SUCRA) values, were XGBoost, Hill-RBF, and Kane. The three formulas had the lowest MedAE and were more accurate than traditional vergence formulas, such as SRK/T, Holladay 1, Holladay 2, Haigis, and Hoffer Q regarding MAE, percentage of eyes with PE within ±0.25, ±0.50, and ±1.00 D. The top AI-based formulas for calculating IOL power in highly myopic eyes were XGBoost, Hill-RBF, and Kane. They were significantly more accurate than traditional vergence formulas and ranked better than formulas with Wang-Koch AL modifications or newer generations of formulas such as Barrett and Olsen. https://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42022335969.

Comparison of the Karney Polygon Method and the Shoelace Method for Calculating Area

In calculating the area of an area, latitude and longitude coordinates are based on data from Global Administrative Region Database and Google Earth can be used. The aim of this research is to calculate the area. This research uses the Karney and Shoelace method to determine its accuracy based on Median Absolute Percentage Error in calculating the area of an area. Median Absolute Percentage Error results use data based on Global Administration The Regional Database by applying the polygon method proposed by Karney is 18.73%, and the percentage is 18.19% by applying the Shoelace method. Based on Google Earth data, implementation the method proposed by Karney obtained a percentage of 19.14%, and the application of shoelaces method obtained a percentage of 19.72%. In this case, Karney polygons and the Shoelace method has good accuracy because the value is below 20%. The proposed Shoelace method is easier to perform understand compared to the Karney method for calculating land area because it uses the Universal Transverse Mercator coordinate system, which projects points on the Earth's surface onto a flat plane.

Abstract 11609: Developing a Novel Method for Measuring Relative Lung Perfusion at the Catheterization Laboratory

Background: Maldistribution of pulmonary blood flow (Qp) is common in patients with congenital heart disease and is associated with worse clinical outcomes. Currently, measurement of Qp-split can only be performed outside the catheterization laboratory, using either lung perfusion scans or cardiac magnetic resonance imaging. Aim: We sought to develop and evaluate a tool for measuring Qp-split using readily available fluoroscopy sequences. Methods: A retrospective cohort study of patients with conotruncal anomalies who underwent perfusion scan and subsequent cardiac catheterization. Inclusion criteria were non-selective angiogram of pulmonary vasculature, oblique angulation ≤20°, and an adequate view of both lung fields. A method was developed and implemented in 3D Slicer to calculate the amount of contrast that entered each lung field from the start of contrast-injection and until the onset of levophase. The predicted perfusion distribution was compared to the distribution measured by lung scan. Results: In total 32% (79/249) of screened studies met inclusion criteria. There was strong correlation between the predicted Qp-split and the measured Qp-split (R 2 =0.83, p&lt;0.001) with median absolute error (MAE) of 6%. Bias was not systematically worse at either extreme of flow distribution. Factors associated with better prediction were smaller BSA, younger age, right ventricle (vs. pulmonary artery) angiograms, and cranial angulations ≤20°. In cases with one or more of these conditions (n=40), the prediction achieved R 2 =0.87, MAE of 5.5%, and 78% of predictions were within 10% of true flow. Conclusions: Data from conventional angiograms can be used to provide accurate real-time measurement of relative perfusion of the left and right lungs. This has the potential to reduce unnecessary testing, associated costs, and radiation exposure.