From Bench-to-Bedside: How Artificial Intelligence is Changing Thyroid Nodule Diagnostics, a Systematic Review.

CONTEXT: Use of artificial intelligence (AI) to predict clinical outcomes in thyroid nodule diagnostics has grown exponentially over the past decade. The greatest challenge is in understanding the best model to apply to one's own patient population, and how to operationalize such a model in practice. EVIDENCE ACQUISITION: A literature search of PubMed and IEEE Xplore was conducted for English-language publications between January 1, 2015 and January 1, 2023, studying diagnostic tests on suspected thyroid nodules that used AI. We excluded articles without prospective or external validation, nonprimary literature, duplicates, focused on nonnodular thyroid conditions, not using AI, and those incidentally using AI in support of an experimental diagnostic outside standard clinical practice. Quality was graded by Oxford level of evidence. EVIDENCE SYNTHESIS: A total of 61 studies were identified; all performed external validation, 16 studies were prospective, and 33 compared a model to physician prediction of ground truth. Statistical validation was reported in 50 papers. A diagnostic pipeline was abstracted, yielding 5 high-level outcomes: (1) nodule localization, (2) ultrasound (US) risk score, (3) molecular status, (4) malignancy, and (5) long-term prognosis. Seven prospective studies validated a single commercial AI; strengths included automating nodule feature assessment from US and assisting the physician in predicting malignancy risk, while weaknesses included automated margin prediction and interobserver variability. CONCLUSION: Models predominantly used US images to predict malignancy. Of 4 Food and Drug Administration-approved products, only S-Detect was extensively validated. Implementing an AI model locally requires data sanitization and revalidation to ensure appropriate clinical performance.

A multitask approach for automated detection and segmentation of thyroid nodules in ultrasound images.

An increase in the incidence and diagnosis of thyroid nodules and thyroid cancer underscores the need for a better approach to nodule detection and risk stratification in ultrasound (US) images that can reduce healthcare costs, patient discomfort, and unnecessary invasive procedures. However, variability in ultrasound technique and interpretation makes the diagnostic process partially subjective. Therefore, an automated approach that detects and segments nodules could improve performance on downstream tasks, such as risk stratification. Ultrasound studies were acquired from 280 patients at UCLA Health, totaling 9888 images, and annotated by collaborating radiologists. Current deep learning architectures for segmentation are typically semi-automated because they are evaluated solely on images known to have nodules and do not assess ability to identify suspicious images. However, the proposed multitask approach both detects suspicious images and segments potential nodules; this allows for a clinically translatable model that aptly parallels the workflow for thyroid nodule assessment. The multitask approach is centered on an anomaly detection (AD) module that can be integrated with any UNet architecture variant to improve image-level nodule detection. Of the evaluated multitask models, a UNet with a ImageNet pretrained encoder and AD achieved the highest F1 score of 0.839 and image-wide Dice similarity coefficient of 0.808 on the hold-out test set. Furthermore, models were evaluated on two external validations datasets to demonstrate generalizability and robustness to data variability. Ultimately, the proposed architecture is an automated multitask method that expands on previous methods by successfully both detecting and segmenting nodules in ultrasound.

A Multitask Approach for Automated Detection and Segmentation of Thyroid Nodules in Ultrasound Images.

An increase in the incidence and diagnosis of thyroid nodules and thyroid cancer underscores the need for a better approach to nodule detection and risk stratification in ultrasound (US) images that can reduce healthcare costs, patient discomfort, and unnecessary invasive procedures. However, variability in ultrasound technique and interpretation makes the diagnostic process partially subjective. Therefore, an automated approach that detects and segments nodules could improve performance on downstream tasks, such as risk stratification.Current deep learning architectures for segmentation are typically semi-automated because they are evaluated solely on images known to have nodules and do not assess ability to identify suspicious images. However, the proposed multitask approach both detects suspicious images and segments potential nodules; this allows for a clinically translatable model that aptly parallels the workflow for thyroid nodule assessment. The multitask approach is centered on an anomaly detection (AD) module that can be integrated with any U-Net architecture variant to improve image-level nodule detection. Ultrasound studies were acquired from 280 patients at UCLA Health, totaling 9,888 images, and annotated by collaborating radiologists. Of the evaluated models, a multi-scale UNet (MSUNet) with AD achieved the highest F1 score of 0.829 and image-wide Dice similarity coefficient of 0.782 on our hold-out test set. Furthermore, models were evaluated on two external validations datasets to demonstrate generalizability and robustness to data variability. Ultimately, the proposed architecture is an automated multitask method that expands on previous methods by successfully both detecting and segmenting nodules in ultrasound.

Patient-level thyroid cancer classification using attention multiple instance learning on fused multi-scale ultrasound image features.

For patients with thyroid nodules, the ability to detect and diagnose a malignant nodule is the key to creating an appropriate treatment plan. However, assessments of ultrasound images do not accurately represent malignancy, and often require a biopsy to confirm the diagnosis. Deep learning techniques can classify thyroid nodules from ultrasound images, but current methods depend on manually annotated nodule segmentations. Furthermore, the heterogeneity in the level of magnification across ultrasound images presents a significant obstacle to existing methods. We developed a multi-scale, attention-based multiple-instance learning model which fuses both global and local features of different ultrasound frames to achieve patient-level malignancy classification. Our model demonstrates improved performance with an AUROC of 0.785 (p<0.05) and AUPRC of 0.539, significantly surpassing the baseline model trained on clinical features with an AUROC of 0.667 and AUPRC of 0.444. Improved classification performance better triages the need for biopsy.

A machine learning approach to predicting risk of myelodysplastic syndrome.

BACKGROUND: Early myelodysplastic syndrome (MDS) diagnosis can allow physicians to provide early treatment, which may delay advancement of MDS and improve quality of life. However, MDS often goes unrecognized and is difficult to distinguish from other disorders. We developed a machine learning algorithm for the prediction of MDS one year prior to clinical diagnosis of the disease. METHODS: Retrospective analysis was performed on 790,470 patients over the age of 45 seen in the United States between 2007 and 2020. A gradient boosted decision tree model (XGB) was built to predict MDS diagnosis using vital signs, lab results, and demographics from the prior two years of patient data. The XGB model was compared to logistic regression (LR) and artificial neural network (ANN) models. The models did not use blast percentage and cytogenetics information as inputs. Predictions were made one year prior to MDS diagnosis as determined by International Classification of Diseases (ICD) codes, 9th and 10th revisions. Performance was assessed with regard to area under the receiver operating characteristic curve (AUROC). RESULTS: On a hold-out test set, the XGB model achieved an AUROC value of 0.87 for prediction of MDS one year prior to diagnosis, with a sensitivity of 0.79 and specificity of 0.80. The XGB model was compared against LR and ANN models, which achieved an AUROC of 0.838 and 0.832, respectively. CONCLUSIONS: Machine learning may allow for early MDS diagnosis MDS and more appropriate treatment administration.

Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data.

BACKGROUND: Acute heart failure (AHF) is associated with significant morbidity and mortality. Effective patient risk stratification is essential to guiding hospitalization decisions and the clinical management of AHF. Clinical decision support systems can be used to improve predictions of mortality made in emergency care settings for the purpose of AHF risk stratification. In this study, several models for the prediction of seven-day mortality among AHF patients were developed by applying machine learning techniques to retrospective patient data from 236,275 total emergency department (ED) encounters, 1881 of which were considered positive for AHF and were used for model training and testing. The models used varying subsets of age, sex, vital signs, and laboratory values. Model performance was compared to the Emergency Heart Failure Mortality Risk Grade (EHMRG) model, a commonly used system for prediction of seven-day mortality in the ED with similar (or, in some cases, more extensive) inputs. Model performance was assessed in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. RESULTS: When trained and tested on a large academic dataset, the best-performing model and EHMRG demonstrated test set AUROCs of 0.84 and 0.78, respectively, for prediction of seven-day mortality. Given only measurements of respiratory rate, temperature, mean arterial pressure, and FiO2, one model produced a test set AUROC of 0.83. Neither a logistic regression comparator nor a simple decision tree outperformed EHMRG. CONCLUSIONS: A model using only the measurements of four clinical variables outperforms EHMRG in the prediction of seven-day mortality in AHF. With these inputs, the model could not be replaced by logistic regression or reduced to a simple decision tree without significant performance loss. In ED settings, this minimal-input risk stratification tool may assist clinicians in making critical decisions about patient disposition by providing early and accurate insights into individual patient's risk profiles.