Applied Artificial Intelligence in Healthcare: A Review of Computer Vision Technology Application in Hospital Settings.

Computer vision (CV), a type of artificial intelligence (AI) that uses digital videos or a sequence of images to recognize content, has been used extensively across industries in recent years. However, in the healthcare industry, its applications are limited by factors like privacy, safety, and ethical concerns. Despite this, CV has the potential to improve patient monitoring, and system efficiencies, while reducing workload. In contrast to previous reviews, we focus on the end-user applications of CV. First, we briefly review and categorize CV applications in other industries (job enhancement, surveillance and monitoring, automation, and augmented reality). We then review the developments of CV in the hospital setting, outpatient, and community settings. The recent advances in monitoring delirium, pain and sedation, patient deterioration, mechanical ventilation, mobility, patient safety, surgical applications, quantification of workload in the hospital, and monitoring for patient events outside the hospital are highlighted. To identify opportunities for future applications, we also completed journey mapping at different system levels. Lastly, we discuss the privacy, safety, and ethical considerations associated with CV and outline processes in algorithm development and testing that limit CV expansion in healthcare. This comprehensive review highlights CV applications and ideas for its expanded use in healthcare.

Association Between Ethnicity and Mortality Outcomes in Patients with COVID-19: A Mayo Clinic VIRUS Registry Cohort Study.

Hispanic populations face significant disparities in health and healthcare. The COVID-19 pandemic highlighted and sometimes further exacerbated these disparities. We conducted a multisite, retrospective cohort study of 6494 hospitalized adult patients admitted between March 2020 and January 2022 with a diagnosis of COVID-19 from five sites including academic hospitals in MN, AZ, and FL and community hospitals in MN and WI. This is an ancillary project of the Viral Infection and Respiratory illness Universal Study (VIRUS) registry, supplemented by electronic health record data. We compared in-hospital mortality and length of stay outcomes between Hispanic and non-Hispanic populations admitted with COVID-19 using propensity matched scores to account for imbalances in demographic and clinical covariables. Among a total of 6494 patients, 512 (7.9%) patients were reported deceased and 5982 (92.1%) alive at discharge. We did not find a statistically significant difference between in-hospital mortality nor length of stay between the two groups.

Real Practice Assessment of Persistent Symptoms After Initiation of Levothyroxine.

OBJECTIVE: Levothyroxine (LT4) is the standard treatment for hypothyroidism. However, certain patients experience persistent symptoms even after achieving euthyroid status with LT4 therapy. We aimed to determine the frequency of persistent or new symptoms in patients with hypothyroidism after initiating LT4. METHODS: This retrospective study included patients with hypothyroidism who started on LT4 between January 2017 and December 2019 at Mayo Clinic in Rochester, Minnesota, USA. Five hundred patient charts were randomly selected for review. Patients with at least 1 documented follow-up encounter after LT4 initiation were evaluated for ≤3 follow-up visits regarding their biochemical status and symptoms. RESULTS: We included 356 patients, a majority of whom were female (66.6%), white (92.3%), and obese (71.9%), with an average age of 59.5 years. At the baseline visit, approximately one-half of the patients (177/356, 47.7%) reported hypothyroid symptoms, with fatigue being the most common symptom. During the follow-up periods, we observed that 17.8% (28/157), 17.9% (19/106), and 19.3% (11/57) of patients had normal thyroid stimulating hormone (TSH) values but persistent symptoms, while 12.3% (19/156), 19.9% (16/107), and 8.9% (5/56) had normal TSH values but new symptoms. Overall, during each respective follow-up period, 26.7% (42/157), 27.3% (29/106), and 28% (16/57) of patients experienced persistent or new symptoms alongside normal TSH values, with fatigue being the most constant symptom. CONCLUSION: Our findings indicate that approximately 1 in every 4 patients with hypothyroidism receiving LT4 therapy and achieving normal TSH levels experience persistent or new hypothyroid symptoms. The cause of these symptoms remains unclear, emphasizing the need for a better understanding of their underlying causes and the development of effective management strategies.

Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases: A Systematic Review.

Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying lung sounds. ML models require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, and data sources of existing models in the literature. Papers published from five major databases between 1990 and 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The review encompassed 62 studies utilizing ML models and public-access databases for lung sound classification. Artificial neural networks (ANN) and support vector machines (SVM) were frequently employed in the ML classifiers. The accuracy ranged from 49.43% to 100% for discriminating abnormal sound types and 69.40% to 99.62% for disease class classification. Seventeen public databases were identified, with the ICBHI 2017 database being the most used (66%). The majority of studies exhibited a high risk of bias and concerns related to patient selection and reference standards. Summarizing, ML models can effectively classify abnormal lung sounds using publicly available data sources. Nevertheless, inconsistent reporting and methodologies pose limitations to advancing the field, and therefore, public databases should adhere to standardized recording and labeling procedures.

Cerebellar infarction risk in a mild COVID-19 case.

Thrombotic events in SARS-COV-2 disease patients are frequent, especially in patients with comorbidities such as heart failure, hypertension, cancer, diabetes mellitus, kidney failure, vascular disease, and other pulmonary illnesses. In severe cases, in particular those of hospitalized patients with other comorbidities, the development of thrombotic events in spite of anticoagulation therapy has been observed. The main thrombotic events are pulmonary thromboembolism, cerebral ischemic stroke, and peripheral artery thrombosis. Despite the severity of SARS-COV-2 disease, some patients with the aforementioned comorbidities develop thrombotic events regardless of the severity of their SARS-COV-2 infection. In this setting, the cerebellum makes no exception as an uncommon, but still possible target for thrombotic events.

Understanding Protein Protocadherin-19 (PCDH19) Syndrome: A Literature Review of the Pathophysiology.

PCDH19 syndrome is a monogenic epilepsy related to the protein protocadherin-19 (PCDH19) gene, which encodes for a protein important for brain development. The protein also seems to regulate gamma-aminobutyric acid type A receptors (GABA(A)(R)). The disease presents with refractory epilepsy that is characterized by seizures occurring in clusters. Till now, the pathophysiology of the disease is mainly unknown, so we conducted a literature review to elucidate the pathophysiology of PCDH19-related epilepsy. We used two databases to investigate this literature review (Google Scholar and PubMed). We selected full-text papers that are published in the English language and published after the year 2000. We selected initially 64 papers and ended up with 29 to conduct this literature review. We found four main theories for the pathophysiology of PCDH19-related epilepsy: GABA(A)(R) dysregulation, blood-brain barrier (BBB) dysfunction, cellular interference, and the AKR1C1-3 gene product deficiency. GABA(A)(R) dysfunction and expression cause decreased effective inhibitory currents predisposing patients to epilepsy. BBB dysfunction allows the passage of methyl-D-aspartate (NMDA)-type glutamate receptor antibodies (abs-NR) through the BBB susceptible membrane. The cellular interference hypothesis establishes that the mutant and non-mutant cells interfere with each other's communication within the same tissue. Women are more susceptible to being affected by this hypothesis as men only have one copy of the x gene and interference is mediated by this gene, meaning that it cannot occur in them. Finally, downregulation and deficiency of the AKR1C3/AKR1C2 products lead to decreasing levels of allopregnanolone, which diminish the regulation of GABA(A)(R).