Mean Absolute Prediction Error Research Articles

Forecasting seasonal influenza activity in Canada-Comparing seasonal Auto-Regressive integrated moving average and artificial neural network approaches for public health preparedness.

Public health preparedness is based on timely and accurate information. Time series forecasting using disease surveillance data is an important aspect of preparedness. This study compared two approaches of time series forecasting: seasonal auto-regressive integrated moving average (SARIMA) modelling and the artificial neural network (ANN) algorithm. The goal was to model weekly seasonal influenza activity in Canada using SARIMA and compares its predictive accuracy, based on root mean square prediction error (RMSE) and mean absolute prediction error (MAE), to that of an ANN. An initial SARIMA model was fit using automated model selection by minimizing the Akaike information criterion (AIC). Further inspection of the autocorrelation function and partial autocorrelation function led to 'manual' model improvements. ANNs were trained iteratively, using an automated process to minimize the RMSE and MAE. A total of 378, 462 cases of influenza was reported in Canada from the 2010-2011 influenza season to the end of the 2019-2020 influenza season, with an average yearly incidence risk of 20.02 per 100,000 population. Automated SARIMA modelling was the better method in terms of forecasting accuracy (per RMSE and MAE). However, the ANN correctly predicted the peak week of disease incidence while the other models did not. Both the ANN and SARIMA models have shown to be capable tools in forecasting seasonal influenza activity in Canada. It was shown that applying both in tandem is beneficial, SARIMA better forecasted overall incidence while ANN correctly predicted the peak week.

Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer

This research introduces the Enhanced Scale-Aware efficient Transformer (ESAE-Transformer), a novel and advanced model dedicated to predicting Exhaust Gas Temperature (EGT). The ESAE-Transformer merges the Multi-Head ProbSparse Attention mechanism with the established Transformer architecture, significantly optimizing computational efficiency and effectively discerning key temporal patterns. The incorporation of the Multi-Scale Feature Aggregation Module (MSFAM) further refines 2 s input and output timeframe. A detailed investigation into the feature dimensionality was undertaken, leading to an optimized configuration of the model, thereby improving its overall performance. The efficacy of the ESAE-Transformer was rigorously evaluated through an exhaustive ablation study, focusing on the contribution of each constituent module. The findings showcase a mean absolute prediction error of 3.47∘R, demonstrating strong alignment with real-world environmental scenarios and confirming the model’s accuracy and relevance. The ESAE-Transformer not only excels in predictive accuracy but also sheds light on the underlying physical processes, thus enhancing its practical application in real-world settings. The model stands out as a robust tool for critical parameter prediction in aero-engine systems, paving the way for future advancements in engine prognostics and diagnostics.

Virtual Meter with Flow Pattern Recognition Using Deep Learning Neural Networks: Experiments and Analyses

Summary Operators often require real-time measurement of fluid flow rates in each well of their fields, which allows better control of production. However, petroleum is a complex multiphase mixture composed of water, gas, oil, and other sediments, which makes its flow challenging to measure and monitor. A critical issue is how the liquid component interacts with the gaseous phase, also known as the flow pattern. For example, sometimes liquids can accumulate in the lower part of the pipeline and block the flow completely, causing a gas pressure buildup that can lead to unstable flow regimes or even accidents (blowouts). On the other hand, some flow patterns can also facilitate sediment deposition, leading to obstructions and reduced production. Thus, this work aims to show that deep neural networks can act as a virtual flowmeter (VFM) using only a history of production, pressure, and temperature telemetry, accurately estimating the flow of all fluids in real time. In addition, these networks can also use the same input data to detect and recognize flow patterns that can harm the regular operation of the wells, allowing greater control without requiring additional costs or the installation of any new equipment. To demonstrate the feasibility of this approach and provide data to train the neural networks, a water-air loop was constructed to resemble an oil well. This setup featured inclined and vertical transparent pipes to generate and observe different flow patterns and sensors to record temperature, pressure, and volumetric flow rates. The results show that deep neural networks achieved up to 98% accuracy in flow pattern prediction and 1% mean absolute prediction error (MAPE) in flow rates, highlighting the capability of this technique to provide crucial insights into the behavior of multiphase flow in risers and pipelines.

Correction of axial length measurement error by IOLMaster 700 could improve refractive prediction accuracy in silicone oil-filled eyes.

To determine whether correcting the axial length (AL) measurement error of the IOLMaster 700 could improve the refractive prediction accuracy in silicone oil-filled eyes. This study included 265 cataract patients (265 eyes) with silicone oil tamponade who were scheduled for phacoemulsification with intraocular lens (IOL) implantation. The performances of various formulas, including Barrett Universal II, Emmetropia Verifying Optical, Hoffer-QST, Kane, Ladas Super Formula, Pearl-DGS, Radial Basis Function and traditional formulas (Haigis, Hoffer Q, Holladay 1 and SRK/T), were evaluated. The refractive prediction errors (PE) calculated with measured AL (ALmeas) and corrected AL with silicone oil adjustment (SOAL) were compared. Subgroup analysis was performed based on the ALmeas (<23 mm; 23-26 mm; ≥26 mm). Using SOAL significantly reduced the hyperopic PE of formulas when compared to ALmeas (-0.05 to 0.17 D vs 0.15 to 0.38 D, p < 0.001). After applying AL correction, all formulas showed a lower mean absolute PE (0.47-0.57 D vs 0.50-0.69 D). The percentage of eyes within ±1.0 D of PE increased from 84.91%-88.68% to 89.81%-91.32% for new formulas and from 78.11%-83.40% to 85.66%-88.68% for traditional formulas, with the use of SOAL. Subgroup analysis showed that the majority of formulas with SOAL in prediction accuracy for eyes with an AL ≥26 mm (p < 0.05). The refractive prediction accuracy in silicone oil-filled eyes was improved by correcting the AL measurement error of the IOLMaster 700, especially for long eyes.

Combination of Artificial Neural Networks and Principal Component Analysis for the Simultaneous Quantification of Dyes in Multi-Component Aqueous Mixtures

Dyes are organic compounds capable of transmitting their color to materials, which is why they are widely used, for example, in textile fibers, leather, paper, plastic, and the food industry. In the dying process, measuring the dye’s content is extremely important to evaluate the process efficiency and minimize the dye’s discharge in wastewater, but most of the time, dyes are present in multi-component mixtures; hence, quantification by spectrophotometric methods presents a great challenge because the signal obtained in the measurement overlaps the components in the mixture. In order to overcome this issue, the use of the high-performance liquid chromatography (HPLC) method is recommended; however, it has the disadvantage of being an expensive technique, complex, and requiring excessive sample preparation. In recent years, some direct spectrophotometric methods based on multivariate regression algorithms for the quantification of dyes in bicomponent mixtures have been reported. This study presents a new framework that uses a combined ANN and principal component analysis (PCA) model for the determination of the concentration of three dyes in aqueous mixtures: Tartrazine (TZ), Amaranth Red (AR), and Blue 1 CFC (B1) dyes. The PCA–ANN model was trained and validated with ternary mixture samples of TZ, AR, and B1, and with known different compositions, spectra absorbance samples were measured in a UV-Vis spectrophotometer at wavelengths between 350–700 nm with intervals of 1 nm. The PCA–ANN model showed a mean absolute prediction error and correlation coefficient (r2) of less than 1% and greater than 0.99, respectively. The results demonstrate that the PCA–ANN model is a quick and highly accurate alternative in the simultaneous determination of dyes in ternary aqueous mixtures.

Effect of Posterior Keratometry on the Accuracy of 10 Intraocular Lens Calculation Formulas: Standard Keratometry versus Total Keratometry.

To investigate the effect of posterior keratometry (PK) on the accuracy of 10 intraocular lens (IOL) power calculation formulas using standard keratometry (K) and total keratometry (TK). This is a retrospective consecutive case-series study. The IOL power was calculated using K and TK measured by IOLMaster 700 in 6 new-generation formulas (Barrett Universal II, Emmetropia Verifying Optical (EVO) 2.0, RBF Calculator 3.0, Hoffer QST, Kane, and Ladas Super Formula) and 4 traditional formulas (Haigis, Hoffer Q, Holladay 1, and SRK/T). The arithmetic prediction error (PE) and mean absolute PE (MAE) were evaluated. The locally-weighted scatterplot smoothing was performed to assess the relationship between PE and PK. A total of 576 patients (576 eyes) who underwent cataract surgery were included. Compared with using K, all formulas using TK showed a hyperopic shift in the whole group. Specifically, for eyes with PK exceeding -5.90 D, all formulas using TK exhibited a hyperopic shift (all P < 0.001), while eyes with PK less than -5.90 D showed a myopic shift (all P < 0.001). The MAE of new-generation formulas calculated with TK and K showed no statistical differences, while the MAE of traditional formulas with TK was larger (TK: 0.34 ~ 0.43 D; K: 0.33 ~ 0.42 D, all P < 0.05). The prediction bias of formulas with TK increased as PK deviated from -5.90 D. TK did not improve the prediction accuracy of new-generation formulas, and even performed worse in traditional formulas.

Non-destructive prediction of the total viable count (TVC) in Fujian oysters (Crassostrea angulata) based on the colorimetric sensor array

The total viable count (TVC) is a traditional method for evaluating seafood freshness. This study aimed to predict the TVC of Fujian oysters stored at 4℃ by using the colorimetric sensing array (CSA) technique combined with imaging and visible near-infrared (Vis-NIR) information channels. An optimal quantitative prediction model based on partial least squares (PLS) was established by combining feature variable selection with a data fusion strategy. All three data-fusion strategies showed better predictive performance than the individual datasets. The high-level fusion strategy performed the best, with a root mean square error of prediction (RMSEP) of 0.17, mean absolute error of prediction (MAEP) of 0.14, coefficient of determination of prediction (Rp2) of 0.9822, and residual prediction deviation (RPD) of 7.37. The experimental results showed that CSA combined with multiple detection channels could be effectively used to predict the TVC of Fujian oysters. In this study, a reliable and comprehensive evaluation model was established to achieve a rapid and accurate prediction of oyster freshness.

Refractive Predictability of Two Intraocular Lens Power Formulas in Long, Medium, and Short Eyes Using a Swept Source Optical Coherence Tomography Biometer.

To compare the refractive predictability of Argos measurements with Barrett Universal II (BUII) and Barrett True Axial Length (BTAL) formulas in a large sample of long, medium, and short axial length (AL) eyes. A retrospective chart review identified 445 eyes of 247 patients for inclusion. The Argos was used for preoperative biometry, and BUII formula for intraocular lens (IOL) power calculations. Back calculations were performed using data from the Argos for the BTAL formula. Data were collected for postoperative absolute prediction error (APE), refractive outcomes, and monocular uncorrected and distance corrected visual acuities at distance (UDVA, CDVA). Overall, mean APE was 0.36 ± 0.33 D for BUII and for 0.34 ± 0.32 D BTAL (p = 0.04). In short AL eyes, mean APE was 0.45 ± 0.37 D for BUII and for 0.37 ± 0.31 D BTAL (p < 0.001). No significant differences between BUII and BTAL were identified for long AL or medium AL eyes. The percentages of eyes with APE of 0.5 D or less in long, medium, and short eyes were 79%, 79% and 51%, respectively, for BUII and 82%, 78% and 69%, respectively, for BTAL. The prediction accuracies were high with both the BUII and BTAL formulas in long, medium, and short eyes, leading to excellent refractive outcomes. The BTAL formula may have lower absolute prediction error in short eyes compared to BUII.

Outcomes After Implantation of a Trifocal Toric Intraocular Lens Using Intraoperative Aberrometry, Digital Image Tracking, and Femtosecond Laser.

To evaluate the refractive and visual acuity outcomes when using trifocal toric intraocular lenses (IOLs), femtosecond laser assisted cataract surgery (FLACS), swept-source optical coherence tomography (SS-OCT) biometry, digital image tracking (DT) and intraoperative aberrometry (IA). This prospective, single-arm, observational study of refractive and visual outcomes included 40 eyes of 34 subjects. Preoperative biometry was performed with the Argos, FLACS and digital marking with LenSx, and IA and DT with ORA. Eyes were implanted with the Clareon PanOptix toric IOL. Study outcome measures included absolute prediction error, residual refractive astigmatism, and monocular uncorrected and distance corrected visual acuity at distance (UDVA, CDVA), intermediate (UIVA, DCIVA; 60cm), and near (UNVA, DCNVA; 40cm). Mean absolute prediction error (spherical equivalent) was 0.43 ± 0.36 D, and the percentage of eyes with absolute prediction error ≤ 0.5 D was 72.5% (29/40 eyes). Mean residual astigmatism was 0.36 ± 0.65 D, and the percentage of eyes with residual astigmatism ≤ 0.5 D was 80% (32/40 eyes). Monocular UDVA, UIVA, and UNVA was 20/25 or better in 75%, 64%, and 87% of eyes respectively. Monocular CDVA, DCIVA, and DCNVA was 20/25 or better in 95%, 64%, and 87% of eyes respectively. The results of this study suggest that trifocal toric implantation with SS-OCT, FLACS, DT, and IA can provide excellent refractive and visual outcomes.

Comparison of nine machine learning regression models in predicting hospital length of stay for patients admitted to a general medicine department

BackgroundThe General Medicine (GM) department has the highest patient volume and heterogeneity among other hospital specialties. Closely examining hospitalization data is crucial because patients come with various conditions or traits. Length of stay (LoS) in hospitals is often used as an efficiency indicator. It is influenced by various factors, including the patient's medical background, demographics, and type of diseases/signs/symptoms at the triage. LoS is a variable that can vary widely, making it difficult to estimate it promptly and accurately, but doing so is highly beneficial. Moreover, efficiently grouping and managing patients based on their expected LoS remains a significant challenge for healthcare organizations. ObjectivesThis study aimed to compare the predictive ability of nine Machine Learning (ML) regression models in estimating the actual number of LoS days using demographics and clinical information recorded at admission as independent variables. MethodsWe analyzed data collected on patients hospitalized at the GM department of the Sant'Orsola-Malpighi University Hospital in Bologna, Italy, who were admitted through the Emergency Department. The data were collected from January 1, 2022, to October 26, 2022. Nine ML regression models were used to predict LoS by analyzing historical data and patient information. The models' performance was assessed through root mean squared prediction error (RMSPE) and mean absolute prediction error (MAPE). Moreover, we used K-means clustering to group patients' medical and organizational criticalities (such as diseases, signs, symptoms, and administrative problems) into four clusters. Feature Importance plots and SHAP (SHapley Additive exPlanations) values were employed to identify the more essential features and enhance the interpretability of the results. ResultsWe analyzed the LoS of 3757 eligible patients, which showed an average of 13 days and a standard deviation of 11.8 days. We randomly divided patients into a training cohort of 2630 (70 %) and a test cohort of 1127 (30 %). The predictive performance of the different models was between 11.00 and 16.16 days for RMSPE and between 7.52 and 10.78 days for MAPE. The eXtreme Gradient Boosting Regression (XGBR) model had the lowest prediction error, both in terms of RMSPE (11.00 days) and MAE (7.52 days). Sex, arrival via own vehicle/walk-in, ambulance arrival, light blue risk category, age 70 or older, and orange risk category are some of the top features. ConclusionThe ML models evaluated in this study reported good predictive performance, with the XGBR model exhibiting the lowest prediction error. This model holds the potential to aid physicians in administering appropriate clinical interventions for patients in the GM department. This model can also help healthcare services predict the resources necessary to better manage hospitalization.

Interchangeability of bilateral anterior chamber depth in intraocular lens power calculation and its application in unilateral lens subluxation

Aims/Purpose: To assess the interchangeability of bilateral anterior chamber depth (ACD) in intraocular lens (IOL) power calculation, and to evaluate whether using the unaffected fellow eye's ACD can enhance refractive results in unilateral lens subluxation.Methods: Axial length (AL), keratometry (K) and ACD were obtained by IOLMaster 700. In cataract surgery candidates (Group 1), the virtual implantation of the same IOL model was used. The predictive results closest to the Plano of the Kane formula, using the right eye's biometry (AL, K and ACD), served as a benchmark. The results of the corresponding IOL power were further calculated by substituting the left eye's ACD for the right eye's one and compared with the benchmark. Eyes with unilateral lens subluxation (Group 2) underwent in‐the‐bag IOL placement after the capsular hook(s) implantation, with refraction conducted at least 1 month post‐operatively. Prediction errors (PE) of the Kane formula with or without the unaffected fellow eye's ACD were compared.Results: 392 eyes of 196 patients were analysed, including 173 candidates and 23 patients with unilateral subluxated lenses. In Group 1, there was no significant difference in bilateral ACD (p = 0.30). The predictive refraction using the right eye's ACD was −0.16 ± 0.10 diopter (D), and that obtained by the left eye's one was −0.16 ± 0.11 D (p = 0.64), with an absolute difference of 0.03 ± 0.03 D. In Group 2, the ACD was 2.89 ± 0.86 mm of the affected eye and 3.14 ± 0.37 mm of the fellow eye (p = 0.17). The median absolute PE, mean absolute PE and the percentage of PEs within ±0.50 D using the affected eye's ACD were 0.50 D, 0.59 D and 52.17%. Using the unaffected eye's ACD improved the outcomes to 0.45D, 0.52 D and 60.87%.Conclusions: Bilateral ACD values are interchangeable in routine IOL power calculation, and using the unaffected fellow eye's ACD can improve its accuracy in cases of unilateral lens subluxation undergoing in‐the‐bag IOL implantation.

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.

Refractive Predictability between Standard and Total Keratometry during the Femtosecond Laser-Assisted Cataract Surgery with Monofocal Intraocular Lens with Enhanced Intermediate Function.

We aimed to compare the accuracy of the intraocular lens (IOL) calculation formula using the standard keratometry (K) and total K (TK) during the femtosecond laser-assisted cataract surgery (FLACS) with a monofocal IOL with enhanced intermediate function using currently used formulas. A retrospective review of 125 eyes from 125 patients who had undergone FLACS with implantation of monofocal IOL with enhanced intermediate function was conducted. The predicted refractive power was calculated using an optical biometer (IOLmaster 700) according to the K and TK in the Barrett Universal II, SRK/T, Haigis, and Holladay 2 formulas. Absolute prediction error (APE) obtained from the actual postoperative refractive outcomes and the refractive error predicted in each formula was compared one month after surgery. Mean APE ranged between 0.29 and 0.39 diopters (D) regardless of the calculation formula and the method of measuring corneal curvature. Significant differences were observed in the APE from the four formulas and the two keratometric measurements (p = 0.014). In a total of 125 eyes from 125 patients, the mean APE was lowest with the Barrett Universal II formula. Across all formulas, both the mean APE and the median APE tended to be lower for K than for TK, although there was no significant difference. Approximately 70% to 80% of the patients were included within 0.5 D of the refractive error across all formulas. The percentage of eyes within 0.5 D of APE outcomes was not statistically different between the K and TK data when using each formula. Keratometric measurements considering the poster corneal curvature did not show any additional advantages when implanting the monofocal IOL with enhanced intermediate function during the FLACS.

Outcomes of Secondary Intracapsular Intraocular Lens Implantation in Patients following Rhegmatogenous Retinal Detachment.

This study reports the outcomes of a secondary IOL implantation technique in patients that suffered from rhegmatogenous retinal detachment combined with a cataract, which included reopening the capsular bag, enabling secondary intracapsular intraocular lens (IOL) implantation. We included consecutive cases with rhegmatogenous retinal detachment (RRD) treated with vitrectomy and silicone oil tamponade, and subsequent secondary IOL implantation during silicone oil removal between September 2019 and June 2022. Demographics, pre- and postoperative clinical data, and complications were collected. Visual and refractive outcomes and IOL position were evaluated. Thirty eyes were included and followed up for a mean of 24.2 ± 5.06 months. Compared with the preoperative values, no significant changes were observed in the intraocular pressure (p = 0.170) and endothelial cell density (p = 0.336); however, the best-corrected visual acuity (Snellen: 20/83 vs. 20/38; logMAR: 0.66 ± 0.23 vs. 0.37 ± 0.32; p < 0.001) and spherical equivalent (p < 0.001) improved significantly. The mean prediction error (ME) was -0.45 ± 0.68 D (-1.9-0.54 D), and the mean absolute prediction error (MAE) was 0.62 ± 0.52 D (0.01-1.9 D). The macula-on subgroup demonstrated significantly better refractive outcomes than the macula-off subgroup (ME, p = 0.046; MAE, p = 0.008). The IOL was well positioned, with a mean horizontal and vertical tilt and decentration of 0.53 ± 0.49° and 0.21 ± 0.16 mm, and 0.54 ± 0.45° and 0.22 ± 0.16 mm, respectively. Secondary intracapsular IOL implantation provided a good and stable IOL position and satisfactory refractive outcomes, and is a feasible treatment option for patients with RRD.

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.

Pretreatment patient-specific quality assurance prediction based on 1D complexity metrics and 3D planning dose: classification, gamma passing rates, and DVH metrics

PurposeHighly modulated radiotherapy plans aim to achieve target conformality and spare organs at risk, but the high complexity of the plan may increase the uncertainty of treatment. Thus, patient-specific quality assurance (PSQA) plays a crucial role in ensuring treatment accuracy and providing clinical guidance. This study aims to propose a prediction model based on complexity metrics and patient planning dose for PSQA results.Materials and methodsPlanning dose, measurement-based reconstructed dose and plan complexity metrics of the 687 radiotherapy plans of patients treated in our institution were collected for model establishing. Global gamma passing rate (GPR, 3%/2mm,10% threshold) of 90% was used as QA criterion. Neural architecture models based on Swin-transformer were adapted to process 3D dose and incorporate 1D metrics to predict QA results. The dataset was divided into training (447), validation (90), and testing (150) sets. Evaluation of predictions was performed using mean absolute error (MAE) for GPR, planning target volume (PTV) HI and PTV CI, mean absolute percentage error (MAPE) for PTV D95, PTV D2 and PTV Dmean, and the area under the receiver operating characteristic (ROC) curve (AUC) for classification. Furthermore, we also compare the prediction results with other models based on either only 1D or 3D inputs.ResultsIn this dataset, 72.8% (500/687) plans passed the pretreatment QA under the criterion. On the testing set, our model achieves the highest performance, with the 1D model slightly surpassing the 3D model. The performance results are as follows (combine, 1D, and 3D transformer): The AUCs are 0.92, 0.88 and 0.86 for QA classification. The MAEs of prediction are 0.039, 0.046, and 0.040 for 3D GPR, 0.018, 0.021, and 0.019 for PTV HI, and 0.075, 0.078, and 0.084 for PTV CI. Specifically, for cases with 3D GPRs greater than 90%, the MAE could achieve 0.020 (combine). The MAPE of prediction is 1.23%, 1.52%, and 1.66% for PTV D95, 2.36%, 2.67%, and 2.45% for PTV D2, and 1.46%, 1.70%, and 1.71% for PTV Dmean.ConclusionThe model based on 1D complexity metrics and 3D planning dose could predict pretreatment PSQA results with high accuracy and the complexity metrics play a leading role in the model. Furthermore, dose-volume metric deviations of PTV could be predicted and more clinically valuable information could be provided.

Refractive Predictability of a Swept Source Optical Coherence Tomography Biometer in Long and Short Eyes Implanted with Extended Depth of Focus Intraocular Lenses.

To determine the refractive predictability of Argos (Movu, a Santec company) measurements and the Barrett Universal II formula in long and short eyes implanted with an extended depth of focus (EDOF) intraocular lens (IOL). This retrospective, non-interventional study included 86 eyes (55 long and 31 short) of 55 patients. Preoperative biometry was performed using the Argos. Preoperative IOL power formulas were the preprogrammed Barrett Universal II (BUII). Data were collected for refractive outcomes, postoperative prediction error (directional and absolute), and monocular corrected distance visual acuity (CDVA, Snellen). The mean absolute prediction error for BUII was 0.27 ± 0.26 D overall, 0.24 ± 0.20 D in long eyes, and 0.33 ± 0.33 D in short eyes. Overall, the percentage of eyes with ≤ 0.5 D prediction error was 84% for BUII. In long eyes, the percentage of eyes with ≤ 0.5 D prediction error was 90% for BUII. In short eyes, the percentage of eyes with ≤ 0.5 D prediction error was 74% for BUII. The percentage of eyes with ≤ 0.5 D of MRSE was 89% for long eyes and 94% for short eyes. Visual acuities were excellent in both long and short eyes, with > 90% of eyes 20/25 or better in each group. The prediction error of Argos using BUII was low in long and short eyes at one month after EDOF IOL implantation.

Accuracy of the PEARL-DGS Formula for Intraocular Lens Power Calculation in Post–Myopic Laser Refractive Corneal Surgery Eyes

PurposeTo investigate the accuracy of the PEARL-DGS formula for intraocular lens (IOL) power calculation in post-myopic laser refractive corneal surgery eyes. DesignRetrospective case series MethodsA total of 139 eyes of 139 patients (mean axial length: 27.4 ± 2.1 mm), who had prior myopic laser refractive corneal surgery and subsequent cataract surgery using Tecnis ZCB00 from March 2018 to February 2023 were included. Refractive outcomes of five formulas (Barrett True K, Haigis-L, Hoffer-QST, PEARL-DGS, and Shammas-PL) were evaluated. Prediction error was defined as the difference between the measured and predicted postoperative refractive spherical equivalent using the IOL power actually implanted. Mean prediction error (MPE), median absolute prediction error (MedAE), mean absolute prediction error were calculated. ResultsWithout constant optimization, the PEARL-DGS resulted in a MPE of +0.05 ± 0.65 D, while the other formulas resulted in myopic shifts. The MedAEs of the formulas were 0.39, 0.53, 0.65, 0.85, and 1.11 D for the PEARL-DGS, Hoffer-QST, Barrett True K, Shammas-PL, and Haigis-L, respectively, in order of magnitude (P < 0.05). With constant optimization, there were no statistically significant differences in the MedAEs among the five formulas (P = 0.388). ConclusionsIn comparison to other IOL formulas, the PEARL-DGS resulted in better refractive outcomes after cataract surgery in post-myopic laser refractive corneal surgery eyes without constant optimization. We suggest that PEARL-DGS be considered as the first choice for IOL power calculation in these eyes when the clinicians do not have their optimized constants.

Contactless estimation of apple fruit respiration rate using machine learning models based on laser speckle imaging

This article presents the application of the laser speckle imaging method, a nondestructive and contactless method monitoring the gas exchange rate of intact apples. Red and infrared lasers in a typical setup for laser speckle imaging were used. A new parameter, speckle pattern relaxation time, has been proposed to evaluate speckle dynamics. Machine learning methods were used to develop a set of predictive models calibrated and validated against the respiration rate of two apple fruit cultivars measured with the flush system. The model with the highest performance used three variables: the speckle pattern relaxation time (τRED or τIR), fruit mass, and categorical variables describing apple varieties. This model provided satisfactorily low values of mean absolute prediction errors of 6.04%. Data from laser light scattering measurements combined with modern machine learning algorithms provided a nondestructive and fast method for estimating the apple fruit respiration rate. The developed solution has the potential for a wide range of industrial applications, especially in fruit storage, where the fruit respiration rate indicates optimal storage conditions.

Accuracy of Different Lens Power Calculation Formulas in Patients With Mature Cataracts.

Introduction To compare the prediction accuracy of lens power calculation formulas in patients undergoing mature cataract surgery. Methods A total of 90 operations involving the Alcon SA60AT IOL implant (Alcon, Geneva, Switzerland) were analyzed in terms of mean refractive prediction error (PE) and mean absolute prediction error (MAE) using backward calculation in a retrospective design. Results A negative PE was observed in SRK/T, Holladay 1, Holladay 2, Hoffer Q, Haigis, and Emmetropia Verifying Optical (EVO) formulas. In contrast, positive PEs were observed in Barrett Universal II (BAUII), Kane, and Radial Basis Function (RBF) formulas. Negative PE was observed with all formulas, except BAUII, in patients with a shallow anterior chamber depth (ACD). While the SRK/T, Holladay 1, BAU, Kane, and RBF formulas demonstrated positive PE, the Holladay 2, Hoffer Q, Haigis, and EVO formulas indicated negative PE. In patients with deep ACD, positive PE was observed in all formulas, barring Holladay 2 and EVO. No significant differences were identified between the formulas concerning MAE and percentages of 0.25 diopter (D), 0.50 D, 0.75 D, and 1.0 D across all study groups. Conclusion Although the new generation formulas provide very good results, achieving the best with a single formula is still impossible.