Johnson, Patrick W.

Abstract Background We sought to evaluate key performance indicators related to an internally developed and deployed artificial intelligence (AI)-augmented kidney stone composition test system for potential improvements in test quality, efficiency, cost-effectiveness, and staff satisfaction. Methods We compared quality, efficiency, staff satisfaction, and financial data from the 6 months after the AI-augmented laboratory test system was deployed (test period) with data from the same 6-month period in the previous year (control period) to determine if AI-augmentation improved key performance indicators of this laboratory test. Results In the 6 months following the deployment (test period) of the AI-augmented kidney stone composition test system, 44 830 kidney stones were analyzed. Of these, 92% of kidney stones were eligible for AI-assisted interpretation. Out of these AI-eligible stones, 45% were able to be auto-released by the AI-augmented test system without human secondary review. Furthermore, the new AI-augmented kidney stone test system resulted in an apparent 40% reduction in incorrect laboratory results. Additionally, the new AI-augmented test system improved laboratory efficiency by 20%, improved staff satisfaction, and reduced the average analysis cost per kidney stone by $0.23. Conclusions The AI-augmented test system improved test quality, efficiency, cost-effectiveness and staff satisfaction related to this kidney stone composition test.

In the Spring of 2020, the United States of America (USA) deployed COVID-19 convalescent plasma (CCP) to treat hospitalized patients. Over 500,000 patients were treated with CCP during the first year of the pandemic. In this study, we estimated the number of actual inpatient lives saved by CCP treatment in the United States of America based on CCP weekly use, weekly national mortality data, and CCP mortality reduction data from meta-analyses of randomized controlled trials and real-world data. We also estimate the potential number of lives saved if CCP had been deployed for 100% of hospitalized patients or used in 15 to 75% of outpatients. Depending on the assumptions modeled in stratified analyses, we estimated that CCP saved between 16,476 and 66,296 lives. The CCP ideal use might have saved as many as 234,869 lives and prevented 1,136,133 hospitalizations. CCP deployment was a successful strategy for ameliorating the impact of the COVID-19 pandemic in the USA. This experience has important implications for convalescent plasma use in future infectious disease emergencies.

AbstractBackgroundLoss of function mutations in PINK1 and PRKN are the most common causes of early‐onset Parkinson disease (PD). The encoded ubiquitin (Ub) kinase PINK1 and the E3 Ub ligase PRKN together regulate the autophagic degradation of dysfunctional mitochondria, termed mitophagy. During this cytoprotective process, PINK1 and PRKN identify and jointly decorate damaged mitochondria with phosphorylated Ub (pS65‐Ub) that serves as the mitophagy tag. Accumulating evidence suggest a pathogenic role for impaired mitophagy in PD and related neurodegenerative conditions. This is in line with our previous finding of increased levels of the mitophagy marker pS65‐Ub in the hippocampus of postmortem Lewy body disease (LBD) brain.MethodWe performed a genome‐wide association study (GWAS) of hippocampal pS65‐Ub level to identify novel regulators of the PINK1‐PRKN‐directed mitophagy in LBD. In our two‐stage GWAS, we obtained 1,012 autopsy confirmed LBD samples (754 discovery stage, 258, replication stage) from Caucasian participants of European ancestry. Using an established, mostly automated workflow, hippocampal sections were immunostained for pS65‐Ub, scanned, and quantified with unbiased algorithms.ResultOur findings identified that APOE rs429358 (β: 0.50, 95% CI: 0.41 to 0.69, p = 8.67×10−25) was very strongly associated with pS65‐Ub levels in LBD brain. The APOE4 genotype is known to exacerbate Aβ and tau deposition. We did observe strong correlations of pS65‐Ub levels with both tau tangle and senile plaque density in the entire LBD cohort. Nevertheless, the increased pS65‐Ub levels in APOE4‐carrying LBD brains were also independent of Aβ and tau deposition in a subgroup (N = 175) with medium levels of these pathologies. To further explore APOE4 effects on mitophagy outside disease context, this observation was also confirmed in APOE‐targeted replacement mice and in induced pluripotent stem cell‐derived astrocytes.ConclusionOur findings nominate a novel mitophagy regulator in LBD brain and highlight a strong association of APOE4 with mitophagy alteration. Our results suggested that APOE4 may mediate mitophagy defects through two mechanisms, by aggravating Alzheimer’s‐type pathologies and also independent of them. With APOE4 being the strongest known risk factor for Alzheimer’s disease and dementia with Lewy bodies, our findings suggest a common mechanistic link underscoring the importance of mitochondrial quality control.

AbstractBackgroundPatients in the intensive care unit (ICU) often experience extended periods of immobility. Following hospital discharge, many face impaired mobility and never return to their baseline function. Although the benefits of physical and occupational rehabilitation are well established in non‐ICU patients, a paucity of work describes effective practices to alleviate ICU‐related declines in mobility.ObjectiveTo assess how rehabilitation with physical and occupational therapy (PT‐OT) during ICU stays affects patients' mobility, self‐care, and length of hospital stay.DesignRetrospective cohort study.SettingInpatient ICU.ParticipantsA total of 6628 adult patients who received physical rehabilitation across multiple sites (Arizona, Florida, Minnesota, and Wisconsin) of a single institution between January 2018 and December 2021.InterventionsNot applicable.Main Outcome MeasuresDescriptive statistics, linear regression models, and gradient boosting machine methods were used to determine the relationship between the amount of PT‐OT received and outcomes of hospital length of stay (LOS), Activity Measure for Post‐Acute Care Daily Activity and Basic Mobility scores.ResultsThe 6628 patients who met inclusion criteria received an average (median) of 23 (range: 1‐89) minutes of PT‐OT per day. Regression analyses showed each additional 10 minutes of PT‐OT per day was associated with a 1.0% (95% confidence interval [CI]: 0.41–1.66, p < .001) higher final Basic Mobility score, a 1.8% (95% CI: 1.30%–2.34%, p < .001) higher final Daily Activity score, and a 1.2‐day (95% CI: −1.28 to −1.09, p < .001) lower hospital LOS. One‐dimensional partial dependence plots revealed an exponential decrease in predicted LOS as minutes of PT‐OT received increased.ConclusionHigher rehabilitation minutes provided to patients in the ICU may reduce the LOS and improve patients' functional outcomes at discharge. The benefits of rehabilitation increased with increasing amounts of time of therapy received.

Abstract Background Cardiomyopathy is a leading cause of pregnancy-related mortality and represents the number one cause of death in the late postpartum period. Purpose The goal of this study was to prospectively evaluate the effectiveness of an artificial intelligence-based electrocardiogram (AI-ECG) and a point-of-care artificial intelligence-enhanced digital stethoscope for cardiomyopathy screening among pregnant and postpartum women. Methods We conducted a single-arm prospective study of pregnant and postpartum women (up to 12 months following delivery) enrolled at three sites between October 2021 and October 2022. Study participants completed a standard 12-lead ECG, ECG + phonocardiogram recordings with a digital stethoscope, a demographic questionnaire, and a transthoracic echocardiogram (TTE) within a 24-hour period. Diagnostic performance of the AI-ECG and digital stethoscope for cardiomyopathy detection, defined as left ventricular ejection fraction (LVEF) &lt; 45%, was evaluated using the area under the curve (AUC) and standard measures of diagnostic performance. Results We included 100 consecutive pregnant and postpartum women who provided informed consent and had at least one ECG recorded, completed the questionnaire, and had an echocardiogram performed. All participants self-identified as female, and 41% were recruited from a federally qualified health center. The median age of participants was 31 years (Q1: 27, Q3: 34). Thirty-eight percent identified as non-Hispanic White, 32% as non-Hispanic Black, 21% as Hispanic or Latino, 6% as Asian, and 3% as Other (1 Native Hawaiian and 2 multiracial). Five percent (5/100) had LVEF &lt;45%. The 12-lead AI-ECG model demonstrated close to perfect discrimination (accuracy 99%; AUC 1.00, sensitivity 100%) for detection of cardiomyopathy with 1 false positive screen (LVEF 49%), Figure 1A. The digital stethoscope (angled position) had an AUC of 0.99 (95% CI: 0.97, 1.00) for detection of LVEF &lt;45%. Sensitivity, specificity, positive predictive value, and negative predictive value for the digital stethoscope were 60%, 98%, 60% and 98%, respectively for detection of LVEF &lt;45% (Figure 1B & 1C). Conclusions In this small prospective study, we found that 5% of pregnant and postpartum women had cardiomyopathy, a potentially life-threatening condition, and that a rapid, inexpensive, ubiquitous, massively scalable point-of-care test - the ECG - showed promising results, identifying it with an AUC &gt; 0.98 with the application of artificial intelligence.Figure 1

We previously demonstrated that increased expression of the SERPINA5 gene is associated with hippocampal vulnerability in Alzheimer’s disease (AD) brains. SERPINA5 was further demonstrated to be a novel tau-binding partner that colocalizes within neurofibrillary tangles. Our goal was to determine whether genetic variants in the SERPINA5 gene contributed to clinicopathologic phenotypes in AD. To screen for SERPINA5 variants, we sequenced 103 autopsy-confirmed young-onset AD cases with a positive family history of cognitive decline. To further assess the frequency of a rare missense variant, SERPINA5 p.E228Q, we screened an additional 1114 neuropathologically diagnosed AD cases. To provide neuropathologic context in AD, we immunohistochemically evaluated SERPINA5 and tau in a SERPINA5 p.E228Q variant carrier and a matched noncarrier. In the initial SERPINA5 screen, we observed 1 individual with a rare missense variant (rs140138746) that resulted in an amino acid change (p.E228Q). In our AD validation cohort, we identified an additional 5 carriers of this variant, resulting in an allelic frequency of 0.0021. There was no significant difference between SERPINA5 p.E228Q carriers and noncarriers in terms of demographic or clinicopathologic characteristics. Although not significant, on average SERPINA5 p.E228Q carriers were 5 years younger at age of disease onset than noncarriers (median: 66 [60–73] vs 71 [63–77] years, P = .351). In addition, SERPINA5 p.E228Q carriers exhibited a longer disease duration than noncarriers that approached significance (median: 12 [10–15]) vs 9 [6–12] years, P = .079). More severe neuronal loss was observed in the locus coeruleus, hippocampus, and amygdala of the SERPINA5 p.E228Q carrier compared to noncarrier, although no significant difference in SERPINA5-immunopositive lesions was observed. Throughout the AD brain in either carrier or noncarrier, areas with early pretangle pathology or burnt-out ghost tangle accumulation did not reveal SERPINA5-immunopositive neurons. Mature tangles and newly formed ghost tangles appeared to correspond well with SERPINA5-immunopositive tangle-bearing neurons. SERPINA5 gene expression was previously associated with disease phenotype; however, our findings suggest that SERPINA5 genetic variants may not be a contributing factor to clinicopathologic differences in AD. SERPINA5-immunopositive neurons appear to undergo a pathologic process that corresponded with specific levels of tangle maturity.

Background: Mayo Clinic’s Care Hotel is a virtual hybrid care model which allows postoperative patients to recover in a comfortable environment after a low-risk procedure. Hospitals need to understand the key patient factors that promote acceptance of the Care Hotel if they are to benefit from this innovative care model. This study aims to identify factors that can predict whether a patient will stay at Care Hotel. Materials and methods: This retrospective chart review of 1065 patients was conducted between 23 July 2020, and 31 December 2021. Variables examined included patient age, sex, race, ethnicity, Charlson comorbidity index, distance patient travelled to hospital, length of surgery, day of the week of surgery, and surgical service. Associations of patient and surgery characteristics with the primary outcome of staying at the Care Hotel were assessed using unadjusted and multivariable logistic regression models. Results: Of the 1065 patients who met criteria for admission to the Care Hotel during the study period, 717 (67.3%) chose to stay at the Care Hotel while 328 (32.7%) choose to be admitted to the hospital. In multivariable analysis, there was a significant association between surgical service and staying at the Care Hotel (P<0.001). Specifically, there was a higher likelihood of staying at the Care Hotel for patients from Neurosurgery [odds rato (OR)=1.86, P=0.004], Otorhinolaryngology (OR=2.70, P<0.001), and General Surgery (OR=2.75, P=0.002). Additionally, there was a higher likelihood of staying at the Care Hotel with distance travelled over 110 miles [OR (per each doubling)=1.10, P=0.007]. Conclusion: When developing a post-surgical care model for patients following outpatient procedures, the referring surgical service is a primary factor to consider in order to ensure patient acceptance, along with patient distance. This study can assist other healthcare organizations considering this model, as it provides guidance on which factors are most indicative of acceptance.

Abstract Aims Current non-invasive screening methods for cardiac allograft rejection have shown limited discrimination and are yet to be broadly integrated into heart transplant care. Given electrocardiogram (ECG) changes have been reported with severe cardiac allograft rejection, this study aimed to develop a deep-learning model, a form of artificial intelligence, to detect allograft rejection using the 12-lead ECG (AI-ECG). Methods and results Heart transplant recipients were identified across three Mayo Clinic sites between 1998 and 2021. Twelve-lead digital ECG data and endomyocardial biopsy results were extracted from medical records. Allograft rejection was defined as moderate or severe acute cellular rejection (ACR) based on International Society for Heart and Lung Transplantation guidelines. The extracted data (7590 unique ECG-biopsy pairs, belonging to 1427 patients) was partitioned into training (80%), validation (10%), and test sets (10%) such that each patient was included in only one partition. Model performance metrics were based on the test set (n = 140 patients; 758 ECG-biopsy pairs). The AI-ECG detected ACR with an area under the receiver operating curve (AUC) of 0.84 [95% confidence interval (CI): 0.78–0.90] and 95% (19/20; 95% CI: 75–100%) sensitivity. A prospective proof-of-concept screening study (n = 56; 97 ECG-biopsy pairs) showed the AI-ECG detected ACR with AUC = 0.78 (95% CI: 0.61–0.96) and 100% (2/2; 95% CI: 16–100%) sensitivity. Conclusion An AI-ECG model is effective for detection of moderate-to-severe ACR in heart transplant recipients. Our findings could improve transplant care by providing a rapid, non-invasive, and potentially remote screening option for cardiac allograft function.

Abstract Background Screening for left ventricular (LV) systolic dysfunction (defined as ejection fraction ≤35%) based on data from a standard 12-lead electrocardiogram (ECG) has become well established when standard digital ECGs are available–8 independent leads sampled at least 250 hertz for 10 seconds. As the algorithm has been incorporated into various clinical scenarios and ancillary research projects, a limitation of the binary classification at 35% has become apparent. Purpose The objective of this study was to develop and validate a deep learning-based algorithm that would classify LVEF into three categories based on only the digital ECG input. Methods After IRB approval, native digital resting ECGs acquired between 1/1/2010 and 12/31/2021 on patients seen in Mayo Clinic in Jacksonville were extracted from the institutional electronic ECG database management system (MUSE, GE Healthcare). These ECGs were matched with transthoracic echocardiograms obtained up to four days prior or 30 days after the ECGs acquisition. A convolutional neural network consisting of 8 layers of convolutions, batch normalization and pooling was trained using Keras and Tensorflow with hyper-parameter optimization for L1 and L2 regularization, learning rate adjustments, and class weights to predict three classes of LVEF: ≤35%, 36–51%, and ≥52% based on clinical relevance. The primary measure of overall performance was the detection of LVEF ≤35%; however, the triad of model predictions was also considered in translating the model output to human interpretable findings. Results A total of 30,153 patients (60,169 ECG pairings; mean age 63 years; 48% male) were randomly split at the patient level into training (24,172 patients), validation (2,973 patients) and testing (3,008 patients). The trained model provided robust discrimination in the withheld testing data – AUROC of 0.941 (95% CI: 0.931 to 0.950). Using the optimal model threshold based on Youden's index from the validation data (0.186), sensitivity and specificity were estimated to be 87.9% (95% CI: 83.8% to 91.2%) and 86.3% (95% CI: 85.4% to 87.2%) in the testing data. In instances where discordant predictions were observed, the posterior distribution of model probabilities provide additional insights into the possible underlying value of LVEF (Figure 1). Conclusions The utilization of a multi-category deep learning classification model for the detection of reduced ejection fraction adds new dimensions to the use of AI technologies on digital ECGs. This work shows high discrimination can still be obtained when using three classes of LVEF. Funding Acknowledgement Type of funding sources: None.