Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs.

BACKGROUND: The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies. METHODS: We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. RESULTS: The training and testing sets were drawn from statistically different populations of implants (P < .001). After 1,000 training epochs by the deep learning system, the system discriminated 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image. CONCLUSION: An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.

Effectiveness of an Advanced Naloxone Training, Simulation, and Assessment of Second-Year Pharmacy Students.

Background: Opioid overdoses continue to be one of the most urgent public health priorities. In 2020, reported overdose deaths in the United States reached a high of over 93,000 cases. As the COVID-19 pandemic and opioid crisis continues to be addressed, life-saving agents must be more widely accessible to those with a high overdose risk. An essential step to increasing access is to train student pharmacists to dispense naloxone. Once licensed, the number of personnel authorized to dispense naloxone can increase. Objectives: To design a training program to educate second-year pharmacy (P2) students on furnishing naloxone under a state protocol. Methods: A multi-phased curriculum-based naloxone training program was delivered to P2 students and included lecture-based education, team-based learning (TBL) applications, case-based scenarios, and summative assessments to improve student knowledge and confidence in furnishing naloxone. Students were surveyed on their knowledge and confidence with naloxone prior to training, after the in-class training and TBL applications and after three assessments. Assessments included simulated patient counseling, case-based scenarios, and proper dispensing of naloxone in a community pharmacy simulation lab. Results: A total of 185 student pharmacists completed the naloxone training program and 68 completed all three surveys. Average scores for naloxone assessments were 83% for the APPS lab patient case, 90.5% for the prescription label typed for the naloxone product, and 88.5% for patient counseling. Statistically significant increases in knowledge-based quiz-like scores (42.1% after training vs. 7.2% after assessment) and in the proportion of students affirmatively answering survey questions after training and assessment was observed. Conclusion: Multi-phase curriculum-based naloxone training program improved pharmacy student knowledge and confidence in furnishing naloxone under a state BOP protocol.

Modulation of diabetic kidney disease markers by an antagonist of p75NTR in streptozotocin-treated mice.

Two therapeutic agents targeting p75NTR pathways have been recently developed to alleviate retinopathy and bladder dysfunction in diabetes mellitus (DM), namely the small molecule p75NTR antagonist THX-B and a monoclonal antibody (mAb) that neutralizes the receptor ligand proNGF. We herein explore these two components in the context of diabetic kidney disease (DKD). Streptozotocin-injected mice were treated for 4 weeks with THX-B or anti-proNGF mAb. Kidneys were taken for quantification of microRNAs and mRNAs by RT-qPCR and for detection of proteins by immunohistochemistry, immunoblotting and ELISA. Blood was sampled to measure plasma levels of urea, creatinine, and albumin. DM led to increases in plasma concentrations of urea and creatinine and decreases in plasma albumin. Receptor p75NTR was expressed in kidneys and its expression was decreased by DM. All these changes were reversed by THX-B treatment while the effect of mAb was less pronounced. MicroRNAs tightly linked to DKD (miR-21-5p, miR-214-3p and miR-342-3p) were highly expressed in diabetic kidneys compared to healthy ones. Also, miR-146a, a marker of kidney inflammation, and mRNA levels of Fn-1 and Nphs, two markers of fibrosis and inflammation, were elevated in DM. Treatments with THX-B or mAb partially or completely reduced the expression of the aforementioned microRNAs and mRNAs. P75NTR antagonism and proNGF mAb might constitute new therapeutic tools to treat or slow down the progression of kidney disease in DM, along with other diabetic related complications. The translational potential of these strategies is currently being investigated.

The Challenges of Upper Extremity Intramuscular Hemangioma: A Case Study and Systematic Review.

BACKGROUND: Intramuscular hemangiomas are rare, benign vascular tumors, constituting 0.8 percent of all hemangiomas. Upper extremity intramuscular hemangiomas pose diagnostic and therapeutic challenges because of their rarity, invasive nature, and potential for neurovascular involvement. The authors report a comprehensive systematic review of upper extremity intramuscular hemangioma management and a challenging case report. METHODS: A systematic review was performed using Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Electronic databases were used to identify articles describing upper extremity intramuscular hemangiomas through 2019. Patient demographics, clinical presentation, management, complications, and outcomes were reviewed. Based on operative timing, cases were categorized as either "primary" (excision performed at initial diagnosis) or "secondary" (excision performed after failure of conservative treatment). RESULTS: Eighteen articles encompassing 25 patients were included in the authors' systematic review. Of those, 18 underwent primary excision and seven underwent secondary excision. The majority involved the forearm or antecubital region. Complete excision, evaluated by gross examination or pathology, was reported in all primary cases and 71 percent of secondary cases. Primary excisions demonstrated smaller size of mass (19.4 cm 2 versus 165.3 cm 2 ) and superior reported functional outcomes (100 percent versus 33 percent). Complications were reported in 5 percent of the primary excisions compared to 71 percent of the secondary excisions, where one complication was a fatal hematoma. CONCLUSIONS: The literature concerning upper extremity intramuscular hemangioma is limited to mostly case reports and several case series with the potential risk of bias. With careful dissection and microsurgical technique, wide local excision followed by complete reconstruction can be successfully performed at initial diagnosis for upper extremity intramuscular hemangiomas. At early stages, smaller lesion size significantly reduces the risk of functional impairment and complications.

Sports Medicine and Artificial Intelligence: A Primer.

Artificial intelligence (AI) represents the fourth industrial revolution and the next frontier in medicine poised to transform the field of orthopaedics and sports medicine, though widespread understanding of the fundamental principles and adoption of applications remain nascent. Recent research efforts into implementation of AI in the field of orthopaedic surgery and sports medicine have demonstrated great promise in predicting athlete injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting the patient experience. Not unlike the recent emphasis thrust upon physicians to understand the business of medicine, the future practice of sports medicine specialists will require a fundamental working knowledge of the strengths, limitations, and applications of AI-based tools. With appreciation, caution, and experience applying AI to sports medicine, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. In this Current Concepts review, we discuss the definitions, strengths, limitations, and applications of AI from the current literature as it relates to orthopaedic sports medicine.

Cost-effectiveness of Multidisciplinary Care in Plastic Surgery: A Systematic Review.

BACKGROUND: Multidisciplinary care has been previously shown to improve outcomes for patients and providers alike, fostering interprofessional collaboration and communication. Many studies have demonstrated the beneficial health care outcomes of interdisciplinary care. However, there has been minimal focus on the cost-effectiveness of such care, particularly in the realm of plastic surgery. This is the first systematic review to examine cost savings attributable to plastic surgery involvement in multidisciplinary care. METHODS: A comprehensive literature review of articles published on cost outcomes associated with multidisciplinary teams including a plastic surgeon was performed. Included articles reported on cost outcomes directly or indirectly attributable to a collaborative intervention. Explicitly reported cost savings were totaled on a per-patient basis. Each article was also reviewed to determine whether the authors ultimately recommended the team-based intervention described. RESULTS: A total of 604 articles were identified in the initial query, of which 8 met the inclusion criteria. Three studies reported explicit cost savings from multidisciplinary care, with cost savings ranging from $707 to $26,098 per patient, and 5 studies reported changes in secondary factors such as complication rates and length of stay. All studies ultimately recommended multidisciplinary care, regardless of whether cost savings were achieved. CONCLUSIONS: This systematic review of the cost-effectiveness of multidisciplinary plastic surgery care examined both primary cost savings and associated quality outcomes, such as length of stay, complication rate, and resource consumption. Our findings indicate that the inclusion of plastic surgery in team-based care provides both direct and indirect cost savings to all involved parties.

Employment as a Plastic Surgeon: A Review of Trends and Demand Across the Field.

ABSTRACT: Intrinsic to the field of plastic surgery, constant changes in health care policy, consumer demands, and medical technology necessitate periodic evaluation of trends in employment over time. In this article, we review the existing literature to report the current state of plastic surgery employment in the United States with regards to compensation, practice patterns, subspecialty trends, contract negotiation, representation of women in the field of plastic surgery, burnout and job satisfaction, and retirement. Understanding how the plastic surgery job market is changing not only serves as a valuable tool for the individual plastic surgeon regarding the navigation of his or her own career but also offers insight into the future of the field as a whole.

Cytocompatibility, membrane disruption, and siRNA delivery using environmentally responsive cationic nanogels.

Advances in the formulation of nucleic acid-based therapeutics have rendered them a promising avenue for treating diverse ailments. Nonetheless, clinical translation of these therapies is hindered by a lack of strategies to ensure the delivery of these nucleic acids in a safe, efficacious manner with the required spatial and temporal control. To this aim, environmentally responsive hydrogels are of interest due to their ability to provide the desired characteristics of a protective carrier for siRNA delivery. Previous work in our laboratory has demonstrated the ability to synthesize nanoparticle formulations with targeted pKa, swelling, and surface PEG density. Here, a library of nanoparticle formulations was assessed on their in vitro toxicity, hemolytic capacity, siRNA loading, and gene-silencing efficacy. Successful candidates exhibited the lowest degrees of cytotoxicity, pH-dependent membrane disruption potential, the highest siRNA loading, and the highest transfection efficacies.

Insights from a vertebrate model organism on the molecular mechanisms of whole-body dehydration tolerance.

Studies on the molecular mechanisms of dehydration tolerance have been largely limited to plants and invertebrates. Currently, research in whole body dehydration of complex animals is limited to cognitive and behavioral effects in humans, leaving the molecular mechanisms of vertebrate dehydration relatively unexplored. The present review summarizes studies to date on the African clawed frog (Xenopus laevis) and examines whole-body dehydration on physiological, cellular and molecular levels. This aquatic frog is exposed to seasonal droughts in its native habitat and can endure a loss of over 30% of its total body water. When coping with dehydration, osmoregulatory processes prioritize water retention in skeletal tissues and vital organs over plasma volume. Although systemic blood circulation is maintained in the vital organs and even elevated in the brain during dehydration, it is done so at the expense of reduced circulation to the skeletal muscles. Increased hemoglobin affinity for oxygen helps to counteract impaired blood circulation and metabolic enzymes show altered kinetic and regulatory parameters that support the use of anaerobic glycolysis. Recent studies with X. laevis also show that pro-survival pathways such as antioxidant defenses and heat shock proteins are activated in an organ-specific manner during dehydration. These pathways are tightly coordinated at the post-transcriptional level by non-coding RNAs, and at the post-translational level by reversible protein phosphorylation. Paired with ongoing research on the X. laevis genome, the African clawed frog is poised to be an ideal animal model with which to investigate the molecular adaptations for dehydration tolerance much more deeply.

Multidisciplinary care in surgery: Are team-based interventions cost-effective?

BACKGROUND: Multidisciplinary care has been shown to improve outcomes for patients, and interprofessional collaboration has been demonstrated to be beneficial for providers. In the field of surgery, although a large number of multidisciplinary care teams have been described, no study to date has examined whether or not these team-based interventions are generally cost-effective. This is the first systematic review to examine cost savings attributable to multidisciplinary care across all surgical fields. METHODS: A comprehensive literature review of articles published on cost outcomes associated with multidisciplinary surgical teams was performed. Selected articles reported on cost outcomes directly attributable to a collaborative intervention. Cost savings were totaled on a per-patient basis. Each article was also reviewed to determine whether the authors ultimately recommended the team-based intervention described. RESULTS: A total of 1421 articles were identified in the initial query, of which 43 met inclusion criteria. Thirty-nine studies (91%) reported multidisciplinary care to be cost effective, with an average cost savings among all studies of $5815 per patient. No significant differences in the amount of savings achieved were found between different intervention subtypes. All studies ultimately recommended (40) or gave mixed reviews (3) of multidisciplinary care, regardless of whether cost savings were achieved. CONCLUSION: Multidisciplinary surgical care is beneficial not only in terms of patient and provider outcomes, but also in reference to its cost-effectiveness. Well-designed multidisciplinary teams tend to optimize perioperative care for all involved parties. Efforts to improve surgical care should employ multidisciplinary teams to promote both quality and cost-effective care.

Cost-effectiveness of surgical comanagement: A systematic review.

OBJECTIVE: To determine the impact of surgical comanagement programs on healthcare system costs. BACKGROUND: With increasing emphasis on multidisciplinary care, surgical comanagement programs are increasing in popularity. However, the overall cost-effectiveness of these programs has yet to be evaluated. METHODS: Pubmed, Scopus, and Cochrane were systematically searched for studies that reported on cost outcomes after implementation of a surgical comanagement program. Data points extracted included study design details, cost outcomes, complication rates, duration of hospital stay, hospital volume changes, patient satisfaction, mortality, and overall multidisciplinary care recommendation. RESULTS: A total of 8 studies were included. Five of the 8 studies reported cost savings, with an average savings of $4132 per patient. Three of the 8 studies reported increases in costs, with an average increase of $11,128 per patient. Seven of the 8 studies reported decreases in length-of-stay, with an average decrease of 1.29 days. CONCLUSIONS: Surgical comanagement programs have had mixed results on overall hospital costs, but cost saving interventions do not sacrifice the quality of patient care delivered.

Clinical and Research Medical Applications of Artificial Intelligence.

Artificial intelligence (AI), including machine learning (ML), has transformed numerous industries through newfound efficiencies and supportive decision-making. With the exponential growth of computing power and large datasets, AI has transitioned from theory to reality in teaching machines to automate tasks without human supervision. AI-based computational algorithms analyze "training sets" using pattern recognition and learning from inputted data to classify and predict outputs that otherwise could not be effectively analyzed with human processing or standard statistical methods. Though widespread understanding of the fundamental principles and adoption of applications have yet to be achieved, recent applications and research efforts implementing AI have demonstrated great promise in predicting future injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting telehealth. With appreciation, caution, and experience applying AI, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. The purpose of this review is to discuss the pearls, pitfalls, and applications associated with AI.

Artificial Intelligence to Identify Arthroplasty Implants From Radiographs of the Hip.

BACKGROUND: The surgical management of complications surrounding patients who have undergone hip arthroplasty necessitates accurate identification of the femoral implant manufacturer and model. Failure to do so risks delays in care, increased morbidity, and further economic burden. Because few arthroplasty experts can confidently classify implants using plain radiographs, automated image processing using deep learning for implant identification may offer an opportunity to improve the value of care rendered. METHODS: We trained, validated, and externally tested a deep-learning system to classify total hip arthroplasty and hip resurfacing arthroplasty femoral implants as one of 18 different manufacturer models from 1972 retrospectively collected anterior-posterior (AP) plain radiographs from 4 sites in one quaternary referral health system. From these radiographs, 1559 were used for training, 207 for validation, and 206 for external testing. Performance was evaluated by calculating the area under the receiver-operating characteristic curve, sensitivity, specificity, and accuracy, as compared with a reference standard of implant model from operative reports with implant serial numbers. RESULTS: The training and validation data sets from 1715 patients and 1766 AP radiographs included 18 different femoral components across four leading implant manufacturers and 10 fellowship-trained arthroplasty surgeons. After 1000 training epochs by the deep-learning system, the system discriminated 18 implant models with an area under the receiver-operating characteristic curve of 0.999, accuracy of 99.6%, sensitivity of 94.3%, and specificity of 99.8% in the external-testing data set of 206 AP radiographs. CONCLUSIONS: A deep-learning system using AP plain radiographs accurately differentiated among 18 hip arthroplasty models from four industry leading manufacturers.

Artificial Intelligence to Identify Arthroplasty Implants From Radiographs of the Knee.

BACKGROUND: Revisions and reoperations for patients who have undergone total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA), and distal femoral replacement (DFR) necessitates accurate identification of implant manufacturer and model. Failure risks delays in care, increased morbidity, and further financial burden. Deep learning permits automated image processing to mitigate the challenges behind expeditious, cost-effective preoperative planning. Our aim was to investigate whether a deep-learning algorithm could accurately identify the manufacturer and model of arthroplasty implants about the knee from plain radiographs. METHODS: We trained, validated, and externally tested a deep-learning algorithm to classify knee arthroplasty implants from one of 9 different implant models from retrospectively collected anterior-posterior (AP) plain radiographs from four sites in one quaternary referral health system. The performance was evaluated by calculating the area under the receiver-operating characteristic curve (AUC), sensitivity, specificity, and accuracy when compared with a reference standard of implant model from operative reports. RESULTS: The training and validation data sets were comprised of 682 radiographs across 424 patients and included a wide range of TKAs from the four leading implant manufacturers. After 1000 training epochs by the deep-learning algorithm, the model discriminated nine implant models with an AUC of 0.99, accuracy 99%, sensitivity of 95%, and specificity of 99% in the external-testing data set of 74 radiographs. CONCLUSIONS: A deep learning algorithm using plain radiographs differentiated between 9 unique knee arthroplasty implants from four manufacturers with near-perfect accuracy. The iterative capability of the algorithm allows for scalable expansion of implant discriminations and represents an opportunity in delivering cost-effective care for revision arthroplasty.

Machine Learning Outperforms Regression Analysis to Predict Next-Season Major League Baseball Player Injuries: Epidemiology and Validation of 13,982 Player-Years From Performance and Injury Profile Trends, 2000-2017.

BACKGROUND: Machine learning (ML) allows for the development of a predictive algorithm capable of imbibing historical data on a Major League Baseball (MLB) player to accurately project the player's future availability. PURPOSE: To determine the validity of an ML model in predicting the next-season injury risk and anatomic injury location for both position players and pitchers in the MLB. STUDY DESIGN: Descriptive epidemiology study. METHODS: Using 4 online baseball databases, we compiled MLB player data, including age, performance metrics, and injury history. A total of 84 ML algorithms were developed. The output of each algorithm reported whether the player would sustain an injury the following season as well as the injury's anatomic site. The area under the receiver operating characteristic curve (AUC) primarily determined validation. RESULTS: Player data were generated from 1931 position players and 1245 pitchers, with a mean follow-up of 4.40 years (13,982 player-years) between the years of 2000 and 2017. Injured players spent a total of 108,656 days on the disabled list, with a mean of 34.21 total days per player. The mean AUC for predicting next-season injuries was 0.76 among position players and 0.65 among pitchers using the top 3 ensemble classification. Back injuries had the highest AUC among both position players and pitchers, at 0.73. Advanced ML models outperformed logistic regression in 13 of 14 cases. CONCLUSION: Advanced ML models generally outperformed logistic regression and demonstrated fair capability in predicting publicly reportable next-season injuries, including the anatomic region for position players, although not for pitchers.

Machine Learning Outperforms Logistic Regression Analysis to Predict Next-Season NHL Player Injury: An Analysis of 2322 Players From 2007 to 2017.

BACKGROUND: The opportunity to quantitatively predict next-season injury risk in the National Hockey League (NHL) has become a reality with the advent of advanced computational processors and machine learning (ML) architecture. Unlike static regression analyses that provide a momentary prediction, ML algorithms are dynamic in that they are readily capable of imbibing historical data to build a framework that improves with additive data. PURPOSE: To (1) characterize the epidemiology of publicly reported NHL injuries from 2007 to 2017, (2) determine the validity of a machine learning model in predicting next-season injury risk for both goalies and position players, and (3) compare the performance of modern ML algorithms versus logistic regression (LR) analyses. STUDY DESIGN: Descriptive epidemiology study. METHODS: Professional NHL player data were compiled for the years 2007 to 2017 from 2 publicly reported databases in the absence of an official NHL-approved database. Attributes acquired from each NHL player from each professional year included age, 85 performance metrics, and injury history. A total of 5 ML algorithms were created for both position player and goalie data: random forest, K Nearest Neighbors, Naïve Bayes, XGBoost, and Top 3 Ensemble. LR was also performed for both position player and goalie data. Area under the receiver operating characteristic curve (AUC) primarily determined validation. RESULTS: Player data were generated from 2109 position players and 213 goalies. For models predicting next-season injury risk for position players, XGBoost performed the best with an AUC of 0.948, compared with an AUC of 0.937 for LR (P < .0001). For models predicting next-season injury risk for goalies, XGBoost had the highest AUC with 0.956, compared with an AUC of 0.947 for LR (P < .0001). CONCLUSION: Advanced ML models such as XGBoost outperformed LR and demonstrated good to excellent capability of predicting whether a publicly reportable injury is likely to occur the next season.

Comparing Independent and Integrated Plastic Surgery Residency Models: A Review of the Literature.

There are currently 2 approved residency training models in the United States conferring eligibility for the American Board of Plastic Surgery examination-the integrated pathway and the independent pathway. While both pathways allow for board certification, there has been much debate regarding the effectiveness of one training model over the other. In this article, we review the existing literature to compare these pathways with regard to quality of trainees, proficiency of graduates, and practice or career outcomes. Ongoing studies are strongly encouraged to continue to identify areas of improvement for both types of training programs.

The regulation of Akt and FoxO transcription factors during dehydration in the African clawed frog (Xenopus laevis).

The African clawed frog (Xenopus laevis) naturally tolerates severe dehydration using biochemical adaptation, one of which is the elevation of antioxidant defenses during whole-body dehydration. The present study investigated the role and regulation of a pathway known to regulate oxidative stress response, the Akt-FoxO signaling pathway, in clawed frog skeletal muscle, responding to medium (15%) and high (30%) dehydration. Protein levels of total and phosphorylated Akt, FoxO1, and FoxO3 were assessed via immunoblotting, in addition to the levels of the E3 ubiquitin ligase known to be associated with muscle atrophy, MAFbx. Akt activity/phosphorylation in addition to its total protein levels were decreased in the skeletal muscle during dehydration, and this corresponded with decreases in the relative phosphorylation of FoxO1 and FoxO3 as well on several residues. Akt is an inhibitor of FoxO1 and FoxO3 activity via phosphorylation, suggesting that FoxO activities were increased during dehydration stress. Furthermore, MAFbx showed decreased protein expression during high dehydration as well, suggesting that the clawed frog may exhibit some natural resistance to skeletal muscle atrophy during severe dehydration conditions. In addition to identifying that the suppression of Akt could lead to an activation of FoxO transcription factors in X. laevis during dehydration, these investigations suggest that X. laevis dehydration may implicate FoxO1 and FoxO3 in controlling skeletal muscle atrophy in X. laevis exposed to dehydration. This study implicates the Akt signaling pathway, its regulation of FoxO transcription factors, and FoxO-controlled targets, in stress adaptation against dehydration.