Efficacy and safety of naldemedine treatment for opioid-induced constipation in gastrointestinal cancer: a retrospective analysis.

BACKGROUND: Gastrointestinal cancers are one of the most common cancer cases worldwide. Cancer treatment is multidisciplinary, which includes opioid pain management. Opioid analgesics cause opioid-induced constipation (OIC) with the onset of effect. Naldemedine, a peripheral opioid receptor antagonist, is an OIC-modifying agent, but no focused efficacy and safety analysis has been conducted for its use in gastrointestinal cancers. METHODS: We retrospectively evaluated patients with gastrointestinal cancer treated with naldemedine at ten institutions in Japan from June 2017 to August 2019. Patients with gastrointestinal cancer who initiated treatment with opioids during hospitalization and were treated with naldemedine for the first time were included in the study. The gastrointestinal cancer types included were esophageal, gastric, small bowel, and colorectal cancers. We assessed the defecation frequency before and after the initiation of naldemedine use. Responders were defined as patients who defecated three or more times/week, with an increase from the baseline of one or more bowel movements/week over seven days after starting naldemedine. RESULTS: Thirty-three patients were observed for one week before and after starting naldemedine. Twenty-one patients had an increase in defecation frequency of at least three times per week or at least once per week above the baseline. The response rate was 63.6% [95% confidence interval (CI): 46.6-77.9%]. The median number of bowel movements for a week before and after the initiation of naldemedine treatment was 3 (range, 0-13) and 7 (range, 1-39), respectively, in the overall population (n=33), with a significant increase in defecation frequency following naldemedine administration (Wilcoxon signed rank test, P<0.005). Diarrhea was the predominant gastrointestinal symptom, with 13 (39.4%) patients experiencing grade 1 and none experiencing grade 3 or grade 4 adverse events. The frequency of other grade 1 adverse events was low abdominal pain in two patients, nausea in two patients, and anorexia in one patient, without any grade 2-4 adverse events. CONCLUSIONS: The results of the study suggest that naldemedine is effective and safe in clinical practice for gastrointestinal cancer treatment.

Efficacy and Safety of Naldemedine for Patients with Cancer with Opioid-Induced Constipation in Clinical Practice: A Real-World Retrospective Study.

The efficacy and safety of naldemedine for opioid-induced constipation in patients with cancer has not been investigated in clinical practice. We conducted a multicenter, retrospective study to assess the effects of naldemedine among 10 Japanese institutions between June 2017 and August 2019. We evaluated the number of defecations 7 days before and after naldemedine administration. A total of 149 patients (89 male) with a median age of 72 years (range, 38−96) were included. The performance status was 0−1, 2, and ≥3 in 40, 38, and 71 patients, respectively. The median opioid dose in oral morphine equivalents was 30 mg/day (range: 7.5−800 mg). We observed 98 responders and 51 non-responders. The median number of defecations increased significantly in the 7 days following naldemedine administration from three to six (p < 0.0001). Multivariate analysis revealed that an opioid dose <30 mg/day [odds ratio, 2.08; 95% confidence interval, 1.01−4.32; p = 0.042] was significantly correlated with the effect of naldemedine. Diarrhea was the most common adverse event (38.2%) among all grades. The efficacy and safety of naldemedine in clinical practice are comparable to those of prospective studies, suggesting that it is effective in most patients.

Hippocampal calcification and its effects on cognitive function and symptoms in dementia.

BACKGROUND: Hippocampal calcification (HC), highly prevalent in older people, has not attracted attention until recently. Despite its potential effects on cognition and behaviour, and its possible impact on the diagnosis and severity of dementia, it has not been investigated. This study aimed to evaluate the prevalence of HC and its influence on cognition and behavioural symptoms in patients with dementia. METHODS: Data from consecutive patients who visited a medical centre for dementia, for the first time between April 2016 and September 2018, were extracted and analysed. These data included the patients' demographics, the presence of HC and hippocampal thickness as measured on computed tomography, the diagnosis of dementia and its type, cognitive function measured using the Mini-Mental State Examination and the Clock Drawing Test, and the chief complaints or symptoms prompting the visit. RESULTS: A high incidence of HC (85/267 patients) was observed. There was no significant difference in the ages of patients with and without HC. Patients with HC had higher cognitive function than those without HC at their first visit. This result was contrary to our expectations as it was not explained by the chief complaints recorded at the first visit. CONCLUSIONS: Our study showed a high prevalence of HC in older patients with dementia. Patients with HC had better cognitive function than did those without HC during their first hospital visit. This study suggests that HC may not affect the cognitive functions related to dementia. However, further research is needed to evaluate the long-term consequences of dementia with HC.

Three cases of parasomnias similar to sleep terrors occurring during sleep-wake transitions from REM sleep.

Sleep terrors are a non-rapid eye movement (NREM) sleep-related parasomnia characterized by abrupt terror with a frightening scream. However, it remains unknown whether sleep terrors occur only from NREM sleep. We evaluated 3 cases of a sleep terrors-like parasomnia that occurred exclusively during arousals from rapid eye movement (REM) sleep. These parasomnia events occurred at REM sleep-wake transitions, manifesting with screaming or crying, similar to sleep terrors, without alertness or clear orientation. The patients were all young-adult females without notable medical conditions. REM sleep behavior disorder and nocturnal frontal lobe epilepsy were not detected based on their video-polysomnographic findings. These 3 cases should be provisionally diagnosed as "Parasomnia, Unspecified" according to the International Classification of Sleep Disorders, third edition; however, the phenomenological diagnosis is proposed to be "Disorders of Arousal from REM Sleep." Our reported cases indicate that sleep terrors may also arise from REM sleep. CITATION: Futenma K, Inoue Y, Saso A, Takaesu Y, Yamashiro Y, Matsuura M. Three cases of parasomnias similar to sleep terrors occurring during sleep-wake transitions from REM sleep. J Clin Sleep Med. 2022;18(2):669-675.

Deep learning-assisted (automatic) diagnosis of glaucoma using a smartphone.

BACKGROUND/AIMS: To validate a deep learning algorithm to diagnose glaucoma from fundus photography obtained with a smartphone. METHODS: A training dataset consisting of 1364 colour fundus photographs with glaucomatous indications and 1768 colour fundus photographs without glaucomatous features was obtained using an ordinary fundus camera. The testing dataset consisted of 73 eyes of 73 patients with glaucoma and 89 eyes of 89 normative subjects. In the testing dataset, fundus photographs were acquired using an ordinary fundus camera and a smartphone. A deep learning algorithm was developed to diagnose glaucoma using a training dataset. The trained neural network was evaluated by prediction result of the diagnostic of glaucoma or normal over the test datasets, using images from both an ordinary fundus camera and a smartphone. Diagnostic accuracy was assessed using the area under the receiver operating characteristic curve (AROC). RESULTS: The AROC with a fundus camera was 98.9% and 84.2% with a smartphone. When validated only in eyes with advanced glaucoma (mean deviation value < -12 dB, N=26), the AROC with a fundus camera was 99.3% and 90.0% with a smartphone. There were significant differences between these AROC values using different cameras. CONCLUSION: The usefulness of a deep learning algorithm to automatically screen for glaucoma from smartphone-based fundus photographs was validated. The algorithm had a considerable high diagnostic ability, particularly in eyes with advanced glaucoma.

Validating the usefulness of sectorwise regression of visual field in the central 10°.

AIM: To evaluate the usefulness of the application of the clustering method to the trend analysis (sectorwise regression) in comparison with the pointwise linear regression (PLR). METHODS: This study included 153 eyes of 101 patients with open-angle glaucoma. With PLR, the total deviation (TD) values of the 10th visual field (VF) were predicted using the shorter VF sequences (from first 3 to 9) by extrapolating TD values against time in a pointwise manner. Then, 68 test points were stratified into 29 sectors. In each sector, the mean of TD values was calculated and allocated to all test points belonging to the sector. Subsequently, the TD values of the 10th VF were predicted by extrapolating the allocated TD value against time in a pointwise manner. Similar analyses were conducted to predict the 11th-16th VFs using the first 10 VFs. RESULTS: When predicting the 10th VF using the shorter sequences, the mean absolute error (MAE) values were significantly smaller in the sectorwise regression than in PLR. When predicting from the 11th and 16th VFs using the first 10 VFs, the MAE values were significantly larger in the sectorwise regression than in PLR when predicting the 11th VF; however, no significant difference was observed with other VF predictions. CONCLUSION: Accurate prediction was achieved using the sectorwise regression, in particular when a small number of VFs were used in the prediction. The accuracy of the sectorwise regression was not hampered in longer follow-up compared with PLR.

Comparing the usefulness of a new algorithm to measure visual field using the variational Bayes linear regression in glaucoma patients, in comparison to the Swedish interactive thresholding algorithm.

BACKGROUND/AIMS: We previously reported that the visual field (VF) prediction model using the variational Bayes linear regression (VBLR) is useful for accurately predicting VF progression in glaucoma (Invest Ophthalmol Vis Sci. 2014, 2018). We constructed a VF measurement algorithm using VBLR, and the purpose of this study was to investigate its usefulness. METHOD: 122 eyes of 73 patients with open-angle glaucoma were included in the current study. VF measurement was performed using the currently proposed VBLR programme with AP-7700 perimetry (KOWA). VF measurements were also conducted using the Swedish interactive thresholding algorithm (SITA) standard programme with Humphrey field analyser. VF measurements were performed using the 24-2 test grid. Visual sensitivities, test-retest reproducibility and measurement duration were compared between the two algorithms. RESULT: Mean mean deviation (MD) values with SITA standard were -7.9 and -8.7 dB (first and second measurements), whereas those with VBLR-VF were -8.2 and -8.0 dB, respectively. There were no significant differences across these values. The correlation coefficient of MD values between the 2 algorithms was 0.97 or 0.98. Test-retest reproducibility did not differ between the two algorithms. Mean measurement duration with SITA standard was 6 min and 02 s or 6 min and 00 s (first or second measurement), whereas a significantly shorter duration was associated with VBLR-VF (5 min and 23 s or 5 min and 30 s). CONCLUSION: VBLR-VF reduced test duration while maintaining the same accuracy as the SITA-standard.

Predicting 10-2 Visual Field From Optical Coherence Tomography in Glaucoma Using Deep Learning Corrected With 24-2/30-2 Visual Field.

Purpose: To investigate whether a correction based on a Humphrey field analyzer (HFA) 24-2/30-2 visual field (VF) can improve the prediction performance of a deep learning model to predict the HFA 10-2 VF test from macular optical coherence tomography (OCT) measurements. Methods: This is a multicenter, cross-sectional study. The training dataset comprised 493 eyes of 285 subjects (407, open-angle glaucoma [OAG]; 86, normative) who underwent HFA 10-2 testing and macular OCT. The independent testing dataset comprised 104 OAG eyes of 82 subjects who had undergone HFA 10-2 test, HFA 24-2/30-2 test, and macular OCT. A convolutional neural network (CNN) DL model was trained to predict threshold sensitivity (TH) values in HFA 10-2 from retinal thickness measured by macular OCT. The predicted TH values was modified by pattern-based regularization (PBR) and corrected with HFA 24-2/30-2. Absolute error (AE) of mean TH values and mean absolute error (MAE) of TH values were compared between the CNN-PBR alone model and the CNN-PBR corrected with HFA 24-2/30-2. Results: AE of mean TH values was lower in the CNN-PBR with HFA 24-2/30-2 correction than in the CNN-PBR alone (1.9dB vs. 2.6dB; P = 0.006). MAE of TH values was lower in the CNN-PBR with correction compared to the CNN-PBR alone (4.2dB vs. 5.3 dB; P < 0.001). The inferior temporal quadrant showed lower prediction errors compared with other quadrants. Conclusions: The performance of a DL model to predict 10-2 VF from macular OCT was improved by the correction with HFA 24-2/30-2. Translational Relevance: This model can reduce the burden of additional HFA 10-2 by making the best use of routinely performed HFA 24-2/30-2 and macular OCT.

Real-World Patient Characteristics and Treatment Patterns of Naldemedine for the Treatment of Opioid-Induced Constipation in Patients with Cancer: A Multicenter Retrospective Chart Review Study.

Background and Objectives: Naldemedine is a peripherally acting µ-opioid receptor antagonist that improves opioid-induced constipation. Although clinical trials have excluded patients with poor performance status (PS) and those started on naldemedine early after opioid initiation, clinical practice has used naldemedine for the same patients. Therefore, we investigated the treatment patterns of naldemedine in a real-world setting. Materials and Methods: This was a multicenter, retrospective chart review study of opioid-treated patients with cancer receiving naldemedine. Adverse events that occurred within 7 days of naldemedine initiation were evaluated in those who received one or more doses of the same. Effectiveness was assessed in patients who used naldemedine for more than 7 days. Results: A total of 296 patients satisfied the eligibility criteria, among whom 129 (43.6%) had a PS of ≥3 and 176 (59.5%) started naldemedine within 2 weeks of opioid initiation. Moreover, 203 (79.6%) patients had ≥3 bowel movements per week. Incidences of all grades of diarrhea and abdominal pain were 87 (29.4%) and 12 (4.1%), respectively. No patient had grade 4 or higher adverse events. Conclusions: Although nearly half of the patients receiving naldemedine in clinical practice belonged to populations that were not included in the clinical trials, our results suggested that naldemedine in clinical practice had the same efficacy and safety as that in clinical trials.

Spin glass behavior and magnetic boson peak in a structural glass of a magnetic ionic liquid.

Glassy magnetic behavior has been observed in a wide range of crystalline magnetic materials called spin glass. Here, we report spin glass behavior in a structural glass of a magnetic ionic liquid, C4mimFeCl4. Magnetization measurements demonstrate that an antiferromagnetic ordering occurs at TN = 2.3 K in the crystalline state, while a spin glass transition occurs at TSG = 0.4 K in the structural glass state. In addition, localized magnetic excitations were found in the spin glass state by inelastic neutron scattering, in contrast to spin-wave excitations in the ordered phase of the crystalline sample. The localized excitation was scaled by the Bose population factor below TSG and gradually disappeared above TSG. This feature is highly reminiscent of boson peaks commonly observed in structural glasses. We suggest the "magnetic" boson peak to be one of the inherent dynamics of a spin glass state.

Biomechanical Glaucoma Factor and Corneal Hysteresis in Treated Primary Open-Angle Glaucoma and Their Associations With Visual Field Progression.

Purpose: To investigate the relationship between biomechanical glaucoma factor (BGF) measured with Corvis ST and glaucomatous visual field (VF) progression, compared to corneal hysteresis (CH) measured with ocular response analyzer using a longitudinal dataset of primary open-angle glaucoma (POAG). The discriminative powers of BGF and CH were also compared using a cross-sectional dataset. Methods: The longitudinal dataset included 166 POAG eyes. The rate of VF change during the follow-up period was evaluated using the mean of 52 pointwise total deviations in the Humphrey 24-2 field test. Variables associated with the VF progression rate were identified from BGF, CH, age, baseline VF severity, and intraocular pressure during the VF follow-up period by identifying the optimal model. The cross-sectional dataset included 68 POAG eyes and 68 healthy eyes. Using this dataset, the area under the curve (AUC) values of the receiver-operating curve were compared between CH and BGF. Results: The optimal multivariate linear mixed model to describe the VF rate included age and CH, but not BGF. Between POAG and healthy eyes, CH was statistically different (P < 0.001), although this was not the case with BGF. The AUC values were 0.61 and 0.71 for BGF and CH, respectively (P = 0.027). Conclusions: CH, but not BGF, was associated with VF progression in POAG patients under treatment. BGF was not useful to discriminate POAG between treated and normal eyes.

Hepatectomy Followed by Adjuvant Chemotherapy with 3-Month Capecitabine Plus Oxaliplatin for Colorectal Cancer Liver Metastases.

LESSONS LEARNED: Three-month adjuvant capecitabine plus oxaliplatin in combination (CAPOX) appeared to reduce recurrence, with mild toxicity in postcurative resection of colorectal cancer liver metastases (CLM). Recurrence in patients who underwent the 3-month adjuvant CAPOX after resection of CLM was most commonly at extrahepatic sites. BACKGROUND: The role of neoadjuvant and adjuvant chemotherapy in the management of initially resectable colorectal cancer liver metastases (CLM) is still unclear. We evaluated the feasibility of 3-month adjuvant treatment with capecitabine plus oxaliplatin in combination (CAPOX) for postcurative resection of CLM. METHODS: Patients received one cycle of capecitabine followed by four cycles of CAPOX as adjuvant chemotherapy after curative resection of CLM. Oral capecitabine was given as 1,000 mg/m2 twice daily for 2 weeks in a 3-week cycle, and CAPOX consisted of oral capecitabine plus oxaliplatin 130 mg/m2 on day 1 in a 3-week cycle. Primary endpoint was the completion rate of adjuvant chemotherapy. Secondary endpoints included recurrence-free survival (RFS), overall survival (OS), dose intensity, and safety. RESULTS: Twenty-eight patients were enrolled. Median age was 69.5 years, 54% of patients had synchronous metastases, and 29% were bilobar. Mean number of lesions resected was two, and mean size of the largest lesion was 31 mm. Among patients, 20 (71.4%; 95% confidence interval, 53.6%-89.3%) completed the protocol treatment and met its primary endpoint. The most common grade 3 or higher toxicity was neutropenia (29%). Five-year recurrence-free survival and overall survival were 65.2% and 87.2%, respectively. CONCLUSION: Three-month adjuvant treatment with CAPOX is tolerable and might be a promising strategy for postcurative resection of CLM.

A Joint Multitask Learning Model for Cross-sectional and Longitudinal Predictions of Visual Field Using OCT.

Purpose: We constructed a multitask learning model (latent space linear regression and deep learning [LSLR-DL]) in which the 2 tasks of cross-sectional predictions (using OCT) of visual field (VF; central 10°) and longitudinal progression predictions of VF (30°) were performed jointly via sharing the deep learning (DL) component such that information from both tasks was used in an auxiliary manner (The Association for Computing Machinery's Special Interest Group on Knowledge Discovery and Data Mining [SIGKDD] 2021). The purpose of the current study was to investigate the prediction accuracy preparing an independent validation dataset. Design: Cohort study. Participants: Cross-sectional training and testing data sets included the VF (Humphrey Field Analyzer [HFA] 10-2 test) and an OCT measurement (obtained within 6 months) from 591 eyes of 351 healthy people or patients with open-angle glaucoma (OAG) and from 155 eyes of 131 patients with OAG, respectively. Longitudinal training and testing data sets included 7984 VF results (HFA 24-2 test) from 998 eyes of 592 patients with OAG and 1184 VF results (HFA 24-2 test) from 148 eyes of 84 patients with OAG, respectively. Each eye had 8 VF test results (HFA 24-2 test). The OCT sequences within the observation period were used. Methods: Root mean square error (RMSE) was used to evaluate the accuracy of LSLR-DL for the cross-sectional prediction of VF (HFA 10-2 test). For the longitudinal prediction, the final (eighth) VF test (HFA 24-2 test) was predicted using a shorter VF series and relevant OCT images, and the RMSE was calculated. For comparison, RMSE values were calculated by applying the DL component (cross-sectional prediction) and the ordinary pointwise linear regression (longitudinal prediction). Main Outcome Measures: Root mean square error in the cross-sectional and longitudinal predictions. Results: Using LSLR-DL, the mean RMSE in the cross-sectional prediction was 6.4 dB and was between 4.4 dB (VF tests 1 and 2) and 3.7 dB (VF tests 1-7) in the longitudinal prediction, indicating that LSLR-DL significantly outperformed other methods. Conclusions: The results of this study indicate that LSLR-DL is useful for both the cross-sectional prediction of VF (HFA 10-2 test) and the longitudinal progression prediction of VF (HFA 24-2 test).

Improving Visual Field Trend Analysis with OCT and Deeply Regularized Latent-Space Linear Regression.

PURPOSE: To investigate whether OCT measurements can improve visual field (VF) trend analyses in glaucoma patients using the deeply regularized latent-space linear regression (DLLR) model. DESIGN: Retrospective cohort study. PARTICIPANTS: Training and testing datasets included 7984 VF results from 998 eyes of 592 patients and 1184 VF results from 148 eyes of 84 patients with open-angle glaucoma, respectively. Each eye underwent a series of 8 VF tests with the Humphrey Field Analyzer OCT series obtained within the same observation period. METHODS: Using pointwise linear regression (PLR), the threshold values of a patient's eighth VF results were predicted using values from shorter VF series (first to second VF tests [VF1-2], first to third VF tests, . . . , to first to seventh VF tests [VF1-7]), and the root mean square error (RMSE) was calculated. With DLLR, OCT measurements (macular retinal nerve fiber layer thickness, the thickness of macular ganglion cell layer and inner plexiform layer, and the thickness of the outer segment and retinal pigment epithelium) that were obtained within the period of shorter VF series were incorporated into the model to predict the eighth VF. MAIN OUTCOME MEASURES: Prediction accuracy of VF trend analyses. RESULTS: The mean ± standard deviation RMSE resulting from PLR averaged 27.48 ± 16.14 dB for VF1-2 and 3.98 ± 2.25 dB for VF1-7. Significantly (P < 0.001) smaller RMSEs were obtained from DLLR: 4.57 ± 2.71 dB (VF1-2) and 3.65 ± 2.27 dB (VF1-7). CONCLUSIONS: It is useful to include OCT measurements when predicting future VF progression in glaucoma patients, especially with short VF series.

Deep learning model to predict visual field in central 10° from optical coherence tomography measurement in glaucoma.

BACKGROUND/AIM: To train and validate the prediction performance of the deep learning (DL) model to predict visual field (VF) in central 10° from spectral domain optical coherence tomography (SD-OCT). METHODS: This multicentre, cross-sectional study included paired Humphrey field analyser (HFA) 10-2 VF and SD-OCT measurements from 591 eyes of 347 patients with open-angle glaucoma (OAG) or normal subjects for the training data set. We trained a convolutional neural network (CNN) for predicting VF threshold (TH) sensitivity values from the thickness of the three macular layers: retinal nerve fibre layer, ganglion cell layer+inner plexiform layer and outer segment+retinal pigment epithelium. We implemented pattern-based regularisation on top of CNN to avoid overfitting. Using an external testing data set of 160 eyes of 131 patients with OAG, the prediction performance (absolute error (AE) and R2 between predicted and actual TH values) was calculated for (1) mean TH in whole VF and (2) each TH of 68 points. For comparison, we trained support vector machine (SVM) and multiple linear regression (MLR). RESULTS: AE of whole VF with CNN was 2.84±2.98 (mean±SD) dB, significantly smaller than those with SVM (5.65±5.12 dB) and MLR (6.96±5.38 dB) (all, p<0.001). Mean of point-wise mean AE with CNN was 5.47±3.05 dB, significantly smaller than those with SVM (7.96±4.63 dB) and MLR (11.71±4.15 dB) (all, p<0.001). R2 with CNN was 0.74 for the mean TH of whole VF, and 0.44±0.24 for the overall 68 points. CONCLUSION: DL model showed considerably accurate prediction of HFA 10-2 VF from SD-OCT.

Erratum: Lattice Dynamics Coupled to Charge and Spin Degrees of Freedom in the Molecular Dimer-Mott Insulator κ-(BEDT-TTF)_{2}Cu[N(CN)_{2}]Cl [Phys. Rev. Lett. 123, 027601 (2019)].

This corrects the article DOI: 10.1103/PhysRevLett.123.027601.

Relationship Between Macular Ganglion Cell Thickness and Ocular Elongation as Measured by Axial Length and Retinal Artery Position.

Purpose: We recently reported on the usefulness of retinal artery trajectory in estimating the magnitude of retinal stretch due to myopia. The purpose of the present study was to elucidate the relationship between the peripapillary retinal artery angle (PRAA) and thickness of the macular ganglion cell-inner plexiform layer (GCIPL). Methods: This r included 138 healthy eyes of 79 subjects older than 20 years of age without any known eye disease. GCIPL thickness was separated into eight sectors according to quadrant and eccentricity from the fovea. The PRAA was calculated as the angle between the superior and inferior retinal arteries. Relationships between whole GCIPL thickness (average and sectorial) and the values of PRAA and axial length (AL) were investigated using a linear mixed model. Results: Average GCIPL thickness in the whole scanned area decreased significantly with narrowing of the PRAA with and without adjusting for AL. Sectorized macular GCIPL thickness also decreased significantly, with narrowing of the PRAA in seven out of the eight with the adjustment of AL, the exception being the inferior peripheral temporal sector. Conclusions: Macular GCIPL thickness decreased significantly with narrowing of the PRAA on average and in seven out of eight sectors.

Effects of Study Population, Labeling and Training on Glaucoma Detection Using Deep Learning Algorithms.

Purpose: To compare performance of independently developed deep learning algorithms for detecting glaucoma from fundus photographs and to evaluate strategies for incorporating new data into models. Methods: Two fundus photograph datasets from the Diagnostic Innovations in Glaucoma Study/African Descent and Glaucoma Evaluation Study and Matsue Red Cross Hospital were used to independently develop deep learning algorithms for detection of glaucoma at the University of California, San Diego, and the University of Tokyo. We compared three versions of the University of California, San Diego, and University of Tokyo models: original (no retraining), sequential (retraining only on new data), and combined (training on combined data). Independent datasets were used to test the algorithms. Results: The original University of California, San Diego and University of Tokyo models performed similarly (area under the receiver operating characteristic curve = 0.96 and 0.97, respectively) for detection of glaucoma in the Matsue Red Cross Hospital dataset, but not the Diagnostic Innovations in Glaucoma Study/African Descent and Glaucoma Evaluation Study data (0.79 and 0.92; P < .001), respectively. Model performance was higher when classifying moderate-to-severe compared with mild disease (area under the receiver operating characteristic curve = 0.98 and 0.91; P < .001), respectively. Models trained with the combined strategy generally had better performance across all datasets than the original strategy. Conclusions: Deep learning glaucoma detection can achieve high accuracy across diverse datasets with appropriate training strategies. Because model performance was influenced by the severity of disease, labeling, training strategies, and population characteristics, reporting accuracy stratified by relevant covariates is important for cross study comparisons. Translational Relevance: High sensitivity and specificity of deep learning algorithms for moderate-to-severe glaucoma across diverse populations suggest a role for artificial intelligence in the detection of glaucoma in primary care.

Improving the Structure-Function Relationship in Glaucomatous Visual Fields by Using a Deep Learning-Based Noise Reduction Approach.

PURPOSE: To investigate whether processing visual field (VF) measurements using a variational autoencoder (VAE) improves the structure-function relationship in glaucoma. DESIGN: Cross-sectional study. PARTICIPANTS: The training data consisted of 82 433 VF measurements from 16 836 eyes. The testing dataset consisted of 117 eyes of 75 patients with open-angle glaucoma. METHODS: A VAE model to reconstruct the threshold of VF was developed using the training dataset. OCT and VF (Humphrey Field Analyzer 24-2, Swedish interactive threshold algorithm standard) measurements were carried out for all eyes in the testing dataset. Visual fields in the testing dataset then were reconstructed using the trained VAE. The structure-function relationship between the circumpapillary retinal nerve fiber layer (cpRNFL) thickness and VF sensitivity was investigated in each of twelve 30° segments of the optic disc (3 nasal sectors were merged). Similarly, the structure-function relationship was investigated using the VAE-reconstructed VF. MAIN OUTCOME MEASURES: Structure-function relationship. RESULTS: The corrected Akaike information criterion values with threshold were found to be smaller than the threshold reconstructed with the VAE (thresholdVAE) in 9 of 10 sectors. A significant relationship was found between threshold and cpRNFL thickness in 6 of 10 sectors, whereas it was significant in 9 of 10 sectors with thresholdVAE. CONCLUSIONS: Applying VAE to VF data results in an improved structure-function relationship.

The Relationship Between Corneal Hysteresis and Progression of Glaucoma After Trabeculectomy.

PURPOSE: The purpose of this study was to investigate the association of corneal hysteresis (CH) measured with Ocular Response Analyzer on the progression of glaucoma after trabeculectomy. MATERIALS AND METHODS: Twenty-four eyes of 19 patients with primary open-angle glaucoma underwent trabeculectomy. A series of visual fields (Humphery Field Analyzer 24-2 SITA-standard) were measured starting after 6 months after trabeculectomy (4.2±5.0 y, mean±SD). The mean total deviation (mTD) of the 52 test points were calculated. In addition, the mTD was divided into the following areas: central area (within central 10 degrees), superior area and inferior area: mTDcentre, mTDsuperior, and mTDinferior, respectively. The relationship between each area's progression rate of mTD and the 7 variables of baseline age, central corneal thickness, baseline mTD, mean intraocular pressure (IOP), SD of IOP divided by the mean IOP, the difference between baseline IOP obtained before the initiation of any treatment, mean IOP, and CH were analyzed using the linear mixed model, and the optimal model was selected using the model selection method with the second ordered Akaike Information Criterion. RESULTS: In the optimal model for mTD progression rate, only CH was selected with the coefficient of 0.11. The optimal model for the mTDcentre progression rate included mean IOP with the coefficient of -0.043 and CH with the coefficient of 0.12, and that for mTDinferior included only CH with the coefficient of 0.089. There was no variable selected in the optimal model for the mTDsuperior progression rate. CONCLUSION: CH is a useful measure in the management of glaucoma after trabeculectomy.