Citations

Objective: To develop an artificial intelligence–based pipeline to assess and triage patient-submitted postoperative wound images. Background: The rise of outpatient surgeries, remote monitoring, and patient-submitted wound images via online portals has contributed to a growing administrative workload on clinicians. Early identification of surgical site infection (SSI) is essential for reducing postoperative morbidity. Methods: Patients ≥18 years old who underwent surgery at 9 affiliated Mayo Clinic hospitals (2019-2022) and were captured by the National Surgical Quality Improvement Program (NSQIP) were included. Eligibility required submission of one image via the patient portal within 30 days after surgery. Images were independently screened in duplicate to determine the presence of an incision. SSI outcomes were obtained from NSQIP. The developed model consisted of 2 stages: incision detection and SSI detection in images with incisions. Four pretrained architectures were evaluated using 10-fold cross-validation, with upsampling and data augmentation to mitigate class imbalance. An end-to-end pipeline, image quality assessment and sensitivity analysis stratified by race were also performed. Results: Among 6060 patients, the median age was 54 years (interquartile range: 40–65), 61.4% (n=3805) were female, and 92.5% (n=5731) identified as White. SSIs were confirmed in 6.2% (n=386) images. Vision Transformer outperformed all others, achieving an incision detection accuracy of 0.94 (area under the curve=0.98) and an SSI detection accuracy of 0.73 (area under the curve=0.81). In addition, it demonstrated strong performance in assessing image quality. Sensitivity analysis revealed comparable performance across racial subgroups. Conclusion: This artificial intelligence pipeline demonstrates promising performance in automating wound image assessment and SSI detection, reducing clinical workload and improving postoperative care.

Background: In the emergency setting, many diagnostic pathways incorporate change in high-sensitivity cardiac troponin (hs-cTn) concentrations (i.e., the delta) to classify patients as low-risk (rule-out) or high-risk (rule-in) for possible myocardial infarction (MI). However, the impact of analytical variation on the delta for correct classification is unknown, especially at concentrations below and around the 99th percentile. Our objective was to assess the impact of delta variation for correct risk classification across the European Society of Cardiology (ESC 0/1 h and 0/2 h), the High-STEACS, and the common change criteria (3C) pathways. Methods: A yearlong accuracy study for hs-cTnT was performed where laboratories across Canada tested three patient-based samples (level 1 target value = 6 ng/L, level 2 target value = 9 ng/L, level 3 target value = 12 ng/L) monthly across 41 different analyzers. The assigned low-delta between levels 1 and 2 was 3 ng/L (i.e., 9 − 6 = 3 ng/L) and the assigned high-delta between levels 1 and 3 was 6 ng/L (i.e., 12 − 6 = 6 ng/L). The low- and high-deltas for each analyzer were determined monthly from the measured values, with the difference calculated from the assigned deltas. The obtained deltas were then assessed via the different pathways on correct classification (i.e., percent correct with 95% confidence intervals, CI) and using non-parametric analyses. Results: The median (interquartile range) difference between the measured versus assigned low-delta (n = 436) and high-delta (n = 439) was −1 ng/L (−1 to 0). The correct classification differed among the pathways. The ESC 0/1 h pathway yielded the lowest percentage of correct classification at 35.3% (95% CI: 30.8 to 40.0) for the low-delta and 90.0% (95% CI: 86.8 to 92.6) for the high-delta. The 3C and ESC 0/2 h pathways yielded higher and equivalent estimates on correct classification: 95.2% (95% CI: 92.7 to 97.0) for the low-delta and 98.2% (95% CI: 96.4 to 99.2) for the high-delta. The High-STEACS pathway yielded 99.5% (95% CI: 98.4 to 99.9) of correct classifications for the high-delta but only 36.2% (95% CI: 31.7 to 40.9) for the low-delta. Conclusions: Analytical variation will impact risk classification for MI when using hs-cTn deltas alone per the pathways. The 3C and ESC 0/2 h pathways have <5% misclassification when using deltas for hs-cTnT in this dataset. Additional studies with different hs-cTnI assays at concentrations below and near the 99th percentile are warranted to confirm these findings.

Background Prompt diagnosis of acute central retinal artery occlusion (CRAO) is crucial for therapeutic management and stroke prevention. However, most stroke centers lack onsite ophthalmic expertise before considering fibrinolytic treatment. This study aimed to develop, train, and test a deep learning system to detect hyperacute CRAO on retinal fundus photographs within the critical 4.5‐hour treatment window and up to 24 hours after visual loss to aid in secondary stroke prevention. Methods Our retrospective, cross‐sectional study included 1322 color fundus photographs from 771 patients with acute visual loss due to CRAO, central retinal vein occlusion, nonarteritic anterior ischemic optic neuropathy, and healthy controls. Photographs were collected from 9 expert neuro‐ophthalmology centers in 6 countries, including 3 randomized clinical trials. Training included 1039 photographs (517 patients), followed by testing on 2 data sets: (1) hyperacute CRAO (54 photographs, 54 patients) and (2) CRAO within 24 hours after visual loss (110 photographs, 109 patients). Results The deep learning system achieved an area under the receiver operating characteristic curve of 0.96 (95% confidence interval (CI), 0.95–0.98), a sensitivity of 92.6% (95% CI, 87.0–98.0), and a specificity of 85.0% (95% CI, 81.8–92.8) for detecting CRAO at hyperacute stage, with similar results within 24 hours. The deep learning system outperformed stroke neurologists on a subset of hyperacute testing data set (120 photographs, 120 patients). Conclusions A deep learning system can accurately detect hyperacute CRAO on retinal photographs within a time window compatible with urgent fibrinolysis. If further validated, such systems could improve patient selection for fibrinolytic trials and optimize secondary stroke prevention. Registration URL: https://www.clinicaltrials.gov ; Unique identifier: NCT06390579.

ABSTRACT Purpose The natural history of biochemical recurrence (BCR) after radical prostatectomy (RP) remains understudied, with limited long‐term data from large cohorts inclusive of both salvage radiotherapy (SRT)‐treated and untreated patients. Herein, we sought to evaluate the outcomes of patients with BCR and the impact of SRT on disease progression. Materials and Methods Patients undergoing RP who developed BCR (PSA ≥ 0.20 ng/mL) were included. Patients with BCR treated with SRT were compared to untreated patients using risk‐set matching with time‐dependent propensity scores. The primary outcome was metastases, analyzed using Kaplan–Meier and Cox models. The number needed to treat (NNT) with SRT to prevent progression was derived at 5 and 15 years. Results Among 6881 patients with BCR, 2109 received SRT. At a median follow‐up of 10.2 years, 1147 patients developed metastases. The median PSA at the time of SRT was 0.50 ng/mL. After 1:1 propensity score matching (2109 patients per cohort), SRT significantly reduced the risk of metastases at 5 (12.7% vs. 19.3%, p < 0.0001) and 15 years (28.6% vs. 31.5%, p < 0.001). On multivariable analysis, SRT independently reduced metastasis risk (HR 0.75, 95% CI 0.63–0.90, p = 0.002), translating to NNT of 23 and 15 at 5 and 15 years, respectively. Interaction analyses between SRT and nodal status ( p = 0.04) showed greater metastasis risk reduction in pN+ (HR 0.41, 95% CI 0.22–0.77, p = 0.005) compared to pN− disease (HR 0.81, 95% CI 0.67–0.97, p = 0.02). Conclusions Most patients with BCR post‐RP do not progress to metastasis. For those who do progress, SRT inarguably improves the oncologic outcomes in the BCR setting. However, careful patient selection and shared decision making should be encouraged in order to limit overtreatment and side effects.

ABSTRACT Bipolar disorder’s (BD) clinical heterogeneity has an unresolved genetic basis. We meta-analyzed genome-wide association studies (GWAS) of 16 BD subphenotypes in 226,032 individuals from 57 cohorts (38,022 cases); 10 advanced to multivariate and multi-trait analyses. Four factors (compulsive, psychotic, dysregulated, internalizing) explained 82.8% of shared genetic variance. BD1 and BD2 loaded on distinct factors despite a high genetic correlation; 87.0% of common-factor loci were significant in neither subtype. Unipolar mania aligned with psychosis over internalizing, and was distinguishable from BD1, and rapid cycling showed heritable cross-domain liability. We identified 356 risk loci, 158 novel, including the first univariate-GWAS associations for psychosis, unipolar mania, rapid cycling and schizoaffective disorder—and 249 credible genes (89 high-confidence), 12 with approved-drug or clinical-phase annotations. Cell-type association showed a midbrain dopaminergic–GABAergic gradient along the psychotic factor. BD’s genetic architecture appears hierarchical—a general liability resolving into dimensions of course and comorbidity beyond diagnostic subtypes.

Context.— Complexity of ordering and transfusing blood is particularly evident in the pediatric population. Simplification, clarification, and standardization of blood orders can decrease complexity and improve patient safety. Objective.— To improve patient safety by optimizing electronic ordering of blood components in pediatrics through a collaborative process improvement initiative. Design.— A multidisciplinary working group, formed as part of a value stream analysis to improve transfusion safety at Children’s Healthcare of Atlanta (Atlanta, Georgia), focused on decreasing variability and providing clarity when ordering, preparing, and transfusing blood using the electronic health record. Through benchmarking with other pediatric institutions and a collaborative design process with multiple local stakeholders, an extensive redesign in the existing orders and order sets occurred. Metrics were collected to determine if a change was an improvement. Results.— Nurse and laboratory informaticists, a pathology informaticist, and a transfusion medicine specialist built the new orders based on the design. The new orders focused on the following changes: standardization, introduction of logic, naming conventions, clarifying definitions, adding calculations, improving transparency of history and laboratory data, removing aliquots, clarifying communication, and implementing additional modules to inform the provider of necessary information about the patient. Metrics included a decrease in the number of orders changed within an hour, decreased calls from the blood bank to the provider to clarify the order, and an absence of overtransfusions and transfusion-related serious safety events for a year following implementation. Conclusions.— This collaborative initiative, using standard process improvement tools, resulted in standardized blood orders improving transfusion safety.

Purpose To establish international expert consensus on surgical techniques, complications, and rehabilitation protocols for lateral extra‐articular procedures (LEAPs) performed adjunctively with anterior cruciate ligament reconstruction. Methods Fifty‐five knee surgeons from 17 countries on 5 continents completed a 3‐round modified Delphi process. In the final round, 16 statements on LEAP techniques and complications were scored on a 5‐point Likert scale; ≥75% “agree/strongly agree” constituted consensus. When appropriate, strength of recommendation was graded. Statements lacking support were revised until consensus or abandonment. Results Six statements achieved unanimous consensus (100%), 2 had strong consensus (90%‐99.9%), and 3 reached consensus (75%‐89.9%); 4 were removed. Key technical recommendations were as follows: (1) in iliotibial band procedures, the graft strip should pass beneath the lateral collateral ligament; (2) an anatomic technique is mandatory for anterolateral ligament reconstruction; and (3) no single LEAP is clinically superior to another. Unanimous agreement indicated that modern LEAPs do not increase lateral compartment osteoarthritis risk, carry a low complication rate, and do not necessitate changes to rehabilitation or return‐to‐play timelines. Conclusions Consensus defined core surgical principles and confirmed the safety of adding LEAPs to anterior cruciate ligament reconstruction. When an iliotibial band graft is used, it should be routed deep to the lateral collateral ligament and fixed between 0° and 60° of knee flexion under low tension. For anterolateral ligament reconstruction, femoral fixation should be in full extension at a posterior‐proximal point relative to the lateral epicondyle. Although no single LEAP proved superiority, adherence to these principles permits safe, effective surgery without altering standard rehabilitation or return‐to‐sport protocols and without increasing osteoarthritis risk. Level of Evidence Level V, expert opinion.

Purpose To define expert consensus on whether and how lateral extra‐articular procedures (LEAPs) should accompany anterior cruciate ligament (ACL) reconstruction to optimize outcomes in ACL‐deficient knees. Methods Fifty‐five knee surgeons from 17 countries on 5 continents completed a 3‐round modified Delphi process. Twenty‐one statements on patient selection for combined ACL reconstruction (ACLR) + LEAPs were graded on 5‐point Likert scales; ≥75% “agree/strongly agree” signified consensus. Strength of recommendation was ranked, and statements failing the threshold were revised or discarded after discussion. Results One statement achieved unanimous agreement (100%): it is strongly recommended to add a LEAP for active patients ≤25 years receiving hamstring‐autograft ACLR to reduce graft failure. Strong consensus (≥90%) supported LEAPs in primary ACLR when grade 3 pivot shift (97.9%), knee hyperextension (97.9%), skeletally immature status (79.5%), revision ACLR (91.5%), return to pivoting sports (93.2%), active patients ≤25 years using nonhamstring grafts (90.7%), grade 3 Lachman test (90%), and when multiple relative risk factors coexist (statement 36, 97.1%). Consensus (75%‐89.9%) favored LEAPs for chronic symptomatic ACL deficiency (86.1%), posterior tibial slope >12° (85.7%), and a history of contralateral ACL injury (88.9%). Eight statements did not reach consensus regarding small‐diameter autografts, female athletes, imaging signs of anterolateral injury (e.g., Segond fracture, lateral femoral‐notch sign), and concomitant meniscal procedures. One statement on LEAPs with primary ACL repair was withdrawn because the project focused on reconstruction. Conclusions International experts strongly recommend adding a LEAP in young active patients undergoing hamstring‐autograft ACLR and in cases of high‐grade rotational or anterior laxity, knee hyperextension, revision surgery, or returning to pivoting sports. Unresolved issues include small graft size, female athletes, imaging findings of rotational instability, and concurrent meniscal procedures, highlighting priorities for future research. Level of Evidence Level V, expert opinion.