Automated Identification of Diabetic Retinopathy Using Deep Learning.

PURPOSE: Diabetic retinopathy (DR) is one of the leading causes of preventable blindness globally. Performing retinal screening examinations on all diabetic patients is an unmet need, and there are many undiagnosed and untreated cases of DR. The objective of this study was to develop robust diagnostic technology to automate DR screening. Referral of eyes with DR to an ophthalmologist for further evaluation and treatment would aid in reducing the rate of vision loss, enabling timely and accurate diagnoses. DESIGN: We developed and evaluated a data-driven deep learning algorithm as a novel diagnostic tool for automated DR detection. The algorithm processed color fundus images and classified them as healthy (no retinopathy) or having DR, identifying relevant cases for medical referral. METHODS: A total of 75 137 publicly available fundus images from diabetic patients were used to train and test an artificial intelligence model to differentiate healthy fundi from those with DR. A panel of retinal specialists determined the ground truth for our data set before experimentation. We also tested our model using the public MESSIDOR 2 and E-Ophtha databases for external validation. Information learned in our automated method was visualized readily through an automatically generated abnormality heatmap, highlighting subregions within each input fundus image for further clinical review. MAIN OUTCOME MEASURES: We used area under the receiver operating characteristic curve (AUC) as a metric to measure the precision-recall trade-off of our algorithm, reporting associated sensitivity and specificity metrics on the receiver operating characteristic curve. RESULTS: Our model achieved a 0.97 AUC with a 94% and 98% sensitivity and specificity, respectively, on 5-fold cross-validation using our local data set. Testing against the independent MESSIDOR 2 and E-Ophtha databases achieved a 0.94 and 0.95 AUC score, respectively. CONCLUSIONS: A fully data-driven artificial intelligence-based grading algorithm can be used to screen fundus photographs obtained from diabetic patients and to identify, with high reliability, which cases should be referred to an ophthalmologist for further evaluation and treatment. The implementation of such an algorithm on a global basis could reduce drastically the rate of vision loss attributed to DR.

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer.

Importance: Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective: Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. Design, Setting, and Participants: Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures: Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures: The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results: The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC). Conclusions and Relevance: In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

A retrospective analysis of ketamine intravenous therapy for depression in real-world care settings.

BACKGROUND: Outcomes of ketamine intravenous therapy (KIT) for depression in real-world care settings have been minimally evaluated. We set out to quantify treatment response to KIT in a large sample of patients from community-based practices. METHODS: We retrospectively analyzed 9016 depression patients who received KIT between 2016 and 2020 at one of 178 community practices across the United States. Depression symptoms were evaluated using the Patient Health Questionnaire-9 (PHQ-9). The induction phase of KIT was defined to be a series of 4-8 infusions administered over 7 to 28 days. RESULTS: Among the 537 patients who underwent induction and had sufficient data, 53.6% of patients showed a response (≥ 50% reduction in PHQ-9 score) at 14-31 days post-induction and 28.9% remitted (PHQ-9 score drop to < 5). The effect size was d = 1.5. Among patients with baseline suicidal ideation (SI), 73.0% exhibited a reduction in SI. A subset (8.4%) of patients experienced an increase in depressive symptoms after induction while 6.0% of patients reported increased SI. The response rate was uniform across 4 levels of baseline depression severity. However, more severe illness was weakly correlated with a greater drop in scores while remission status was weakly inversely correlated with depression severity. Kaplan-Meier analyses showed that a patient who responds to KIT induction has approximately 80% probability of sustaining response at 4 weeks and approximately 60% probability at 8 weeks, even without maintenance infusions. CONCLUSION: KIT can elicit a robust antidepressant response in community clinics; however, a small percentage of patients worsened.