Prognosis of the long-term functional outcome of traumatic brain injury is essential for personalized management of that injury. Nonetheless, accurate prediction remains unavailable. Although machine learning has shown promise in many fields, including medical diagnosis and prognosis, such models are rarely deployed in real-world settings due to a lack of transparency and trustworthiness. To address these drawbacks, we propose a machine learning-based framework that is explainable and aligns with clinical domain knowledge. To build such a framework, additional layers of statistical inference and human expert validation are added to the model, which ensures the predicted risk score’s trustworthiness. Using 831 patients with moderate or severe traumatic brain injury to build a model using the proposed framework, an area under the receiver operating characteristic curve (AUC) and accuracy of 0.8085 and 0.7488 were achieved, respectively, in determining which patients will experience poor functional outcomes. The performance of the machine learning classifier is not adversely affected by the imposition of statistical and domain knowledge “checks and balances”. Finally, through a case study, we demonstrate how the decision made by a model might be biased if it is not audited carefully.

There is a growing gap between studies describing the capabilities of artificial intelligence (AI) diagnostic systems using deep learning versus efforts to investigate how or when to integrate AI systems into a real-world clinical practice to support physicians and improve diagnosis. To address this gap, we investigate four potential strategies for AI model deployment and physician collaboration to determine their potential impact on diagnostic accuracy. As a case study, we examine an AI model trained to identify findings of the acute respiratory distress syndrome (ARDS) on chest X-ray images. While this model outperforms physicians at identifying findings of ARDS, there are several reasons why fully automated ARDS detection may not be optimal nor feasible in practice. Among several collaboration strategies tested, we find that if the AI model first reviews the chest X-ray and defers to a physician if it is uncertain, this strategy achieves a higher diagnostic accuracy (0.869, 95% CI 0.835–0.903) compared to a strategy where a physician reviews a chest X-ray first and defers to an AI model if uncertain (0.824, 95% CI 0.781–0.862), or strategies where the physician reviews the chest X-ray alone (0.808, 95% CI 0.767–0.85) or the AI model reviews the chest X-ray alone (0.847, 95% CI 0.806–0.887). If the AI model reviews a chest X-ray first, this allows the AI system to make decisions for up to 79% of cases, letting physicians focus on the most challenging subsets of chest X-rays.

Detection and severity assessment of subdural hematoma is a major step in the evaluation of traumatic brain injuries. This is a retrospective study of 110 computed tomography (CT) scans from patients admitted to the Michigan Medicine Neurological Intensive Care Unit or Emergency Department. A machine learning pipeline was developed to segment and assess the severity of subdural hematoma. First, the probability of each point belonging to the hematoma region was determined using a combination of hand-crafted and deep features. This probability provided the initial state of the segmentation. Next, a 3D post-processing model was applied to evolve the initial state and delineate the hematoma. The recall, precision, and Dice similarity coefficient of the proposed segmentation method were 78.61%, 76.12%, and 75.35%, respectively, for the entire population. The Dice similarity coefficient was 79.97% for clinically significant hematomas, which compared favorably to an inter-rater Dice similarity coefficient. In volume-based severity analysis, the proposed model yielded an F1, recall, and specificity of 98.22%, 98.81%, and 92.31%, respectively, in detecting moderate and severe subdural hematomas based on hematoma volume. These results show that the combination of classical image processing and deep learning can outperform deep learning only methods to achieve greater average performance and robustness. Such a system can aid critical care physicians in reducing time to intervention and thereby improve long-term patient outcomes.

Background: Both early detection and severity assessment of liver trauma are critical for optimal triage and management of trauma patients. Current trauma protocols utilize computed tomography (CT) assessment of injuries in a subjective and qualitative (v.s. quantitative) fashion, shortcomings which could both be addressed by automated computer-aided systems that are capable of generating real-time reproducible and quantitative information. This study outlines an end-to-end pipeline to calculate the percentage of the liver parenchyma disrupted by trauma, an important component of the American Association for the Surgery of Trauma (AAST) liver injury scale, the primary tool to assess liver trauma severity at CT.Methods: This framework comprises deep convolutional neural networks that first generate initial masks of both liver parenchyma (including normal and affected liver) and regions affected by trauma using three dimensional contrast-enhanced CT scans. Next, during the post-processing step, human domain knowledge about the location and intensity distribution of liver trauma is integrated into the model to avoid false positive regions. After generating the liver parenchyma and trauma masks, the corresponding volumes are calculated. Liver parenchymal disruption is then computed as the volume of the liver parenchyma that is disrupted by trauma.Results: The proposed model was trained and validated on an internal dataset from the University of Michigan Health System (UMHS) including 77 CT scans (34 with and 43 without liver parenchymal trauma). The Dice/recall/precision coefficients of the proposed segmentation models are 96.13/96.00/96.35% and 51.21/53.20/56.76%, respectively, in segmenting liver parenchyma and liver trauma regions. In volume-based severity analysis, the proposed model yields a linear regression relation of 0.95 in estimating the percentage of liver parenchyma disrupted by trauma. The model shows an accurate performance in avoiding false positives for patients without any liver parenchymal trauma. These results indicate that the model is generalizable on patients with pre-existing liver conditions, including fatty livers and congestive hepatopathy.Conclusion: The proposed algorithms are able to accurately segment the liver and the regions affected by trauma. This pipeline demonstrates an accurate performance in estimating the percentage of liver parenchyma that is affected by trauma. Such a system can aid critical care medical personnel by providing a reproducible quantitative assessment of liver trauma as an alternative to the sometimes subjective AAST grading system that is used currently.

We are bioinformatics trainees at the University of Michigan who started a local chapter of Girls Who Code to provide a fun and supportive environment for high school women to learn the power of coding. Our goal was to cover basic coding topics and data science concepts through live coding and hands-on practice. However, we could not find a resource that exactly met our needs. Therefore, over the past three years, we have developed a curriculum and instructional format using Jupyter notebooks to effectively teach introductory Python for data science. This method, inspired by The Carpentries organization, uses bite-sized lessons followed by independent practice time to reinforce coding concepts, and culminates in a data science capstone project using real-world data. We believe our open curriculum is a valuable resource to the wider education community and hope that educators will use and improve our lessons, practice problems, and teaching best practices. Anyone can contribute to our Open Educational Resources on GitHub.

To assess varicocele repair effect on semen parameters and improved candidacy for in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) or lesser involved treatment options depending on semen parameter response following varicocele repair in infertile men presenting with baseline semen analyses revealing cryptozoospermia. A retrospective chart review of the electronic health records was performed in men presenting for fertility evaluation with a palpable varicocele on physical examination and at least 2 consecutive semen analyses revealing cryptozoospermia who underwent subinguinal microsurgical varicocele repair. Of the 24 men with cryptozoospermia who underwent varicocele repair, 54% had improvement in semen parameters from cryptozoospermia preoperatively to semen parameters ranging from severely oligozoospermic to normozoospermic 3 to 6 months postoperatively. Statistical analyses did not demonstrate significant associations between patient age, follicle-stimulating hormone (FSH) level, or clinical grade of varicocele and semen parameter response following varicocele repair. Greater than half of the men with cryptozoospermia that underwent varicocele repair improved semen parameters to be optimized for IVF/ICSI or potentially lesser involved fertility treatments and obviated the need for surgical sperm retrieval. Neither patient age, serum FSH level, nor clinical grade of varicocele showed a statistically significant association with favorable versus unfavorable semen parameter response to varicocele repair in infertile men with preoperative cryptozoospermia.This data suggests varicocele repair may be offered to infertile, cryptozoospermic men with palpable varicoceles.