Steady Floquet-Andreev states in graphene Josephson junctions.

Engineering quantum states through light-matter interaction has created a paradigm in condensed-matter physics. A representative example is the Floquet-Bloch state, which is generated by time-periodically driving the Bloch wavefunctions in crystals. Previous attempts to realize such states in condensed-matter systems have been limited by the transient nature of the Floquet states produced by optical pulses1-3, which masks the universal properties of non-equilibrium physics. Here we report the generation of steady Floquet-Andreev states in graphene Josephson junctions by continuous microwave application and direct measurement of their spectra by superconducting tunnelling spectroscopy. We present quantitative analysis of the spectral characteristics of the Floquet-Andreev states while varying the phase difference of the superconductors, the temperature, the microwave frequency and the power. The oscillations of the Floquet-Andreev-state spectrum with phase difference agreed with our theoretical calculations. Moreover, we confirmed the steady nature of the Floquet-Andreev states by establishing a sum rule of tunnelling conductance4, and analysed the spectral density of Floquet states depending on Floquet interaction strength. This study provides a basis for understanding and engineering non-equilibrium quantum states in nanodevices.

FDA, CDC, and NIH Co-sponsored Public Workshop Summary-Development Considerations of Antimicrobial Drugs for the Treatment of Gonorrhea.

There is an unmet need for developing drugs for the treatment of gonorrhea, due to rapidly evolving resistance of Neisseria gonorrhoeae against antimicrobial drugs used for empiric therapy, an increase in globally reported multidrug resistant cases, and the limited available therapeutic options. Furthermore, few drugs are under development. Development of antimicrobials is hampered by challenges in clinical trial design, limitations of available diagnostics, changes in and varying standards of care, lack of robust animal models, and clinically relevant pharmacodynamic targets. On April 23, 2021, the U.S. Food and Drug Administration; Centers for Disease Control and Prevention; and National Institute of Allergy and Infectious Diseases, National Institutes of Health co-sponsored a workshop with stakeholders from academia, industry, and regulatory agencies to discuss the challenges and strategies, including potential collaborations and incentives, to facilitate the development of drugs for the treatment of gonorrhea. This article provides a summary of the workshop.

N121T and N121S substitutions on the SARS-CoV-2 spike protein impact on serum neutralization.

The N121 site on the spike protein of SARS-CoV-2 is associated with heme and its metabolite, biliverdin, which can affect antibody binding. Both N121T and N121S substitutions have been observed in natural conditions and in a hamster model of dual infection with SARS-CoV-2 and Influenza A virus. Serum pseudotype neutralization assays against HIV-1 particles carrying wild-type, N121T, and N121S spikes with immune mouse and human sera revealed that N121T and N121S mutations had a greater impact on serum neutralization than biliverdin treatment. Although N121T and N121S substitutions are not currently major SARS-CoV-2 variants of concern, this study could provide fundamental information to prepare for potential future mutations at the N121 site of SARS-CoV-2.

Deep-Learning Automation of Preoperative Radiographic Parameters Associated With Early Periprosthetic Femur Fracture After Total Hip Arthroplasty.

BACKGROUND: The radiographic assessment of bone morphology impacts implant selection and fixation type in total hip arthroplasty (THA) and is important to minimize the risk of periprosthetic femur fracture (PFF). We utilized a deep-learning algorithm to automate femoral radiographic parameters and determined which automated parameters were associated with early PFF. METHODS: Radiographs from a publicly available database and from patients undergoing primary cementless THA at a high-volume institution (2016 to 2020) were obtained. A U-Net algorithm was trained to segment femoral landmarks for bone morphology parameter automation. Automated parameters were compared against that of a fellowship-trained surgeon and compared in an independent cohort of 100 patients who underwent THA (50 with early PFF and 50 controls matched by femoral component, age, sex, body mass index, and surgical approach). RESULTS: On the independent cohort, the algorithm generated 1,710 unique measurements for 95 images (5% lesser trochanter identification failure) in 22 minutes. Medullary canal width, femoral cortex width, canal flare index, morphological cortical index, canal bone ratio, and canal calcar ratio had good-to-excellent correlation with surgeon measurements (Pearson's correlation coefficient: 0.76 to 0.96). Canal calcar ratios (0.43 ± 0.08 versus 0.40 ± 0.07) and canal bone ratios (0.39 ± 0.06 versus 0.36 ± 0.06) were higher (P < .05) in the PFF cohort when comparing the automated parameters. CONCLUSIONS: Deep-learning automated parameters demonstrated differences in patients who had and did not have early PFF after cementless primary THA. This algorithm has the potential to complement and improve patient-specific PFF risk-prediction tools.

Explainable Deep-Learning-Based Gait Analysis of Hip-Knee Cyclogram for the Prediction of Adolescent Idiopathic Scoliosis Progression.

Accurate prediction of scoliotic curve progression is crucial for guiding treatment decisions in adolescent idiopathic scoliosis (AIS). Traditional methods of assessing the likelihood of AIS progression are limited by variability and rely on static measurements. This study developed and validated machine learning models for classifying progressive and non-progressive scoliotic curves based on gait analysis using wearable inertial sensors. Gait data from 38 AIS patients were collected using seven inertial measurement unit (IMU) sensors, and hip-knee (HK) cyclograms representing inter-joint coordination were generated. Various machine learning algorithms, including support vector machine (SVM), random forest (RF), and novel deep convolutional neural network (DCNN) models utilizing multi-plane HK cyclograms, were developed and evaluated using 10-fold cross-validation. The DCNN model incorporating multi-plane HK cyclograms and clinical factors achieved an accuracy of 92% in predicting curve progression, outperforming SVM (55% accuracy) and RF (52% accuracy) models using handcrafted gait features. Gradient-based class activation mapping revealed that the DCNN model focused on the swing phase of the gait cycle to make predictions. This study demonstrates the potential of deep learning techniques, and DCNNs in particular, in accurately classifying scoliotic curve progression using gait data from wearable IMU sensors.

Proton Intercalation into an Open-Tunnel Bronze Phase with Near-Zero Volume Change.

Managing safety and supply-chain risks associated with lithium-ion batteries (LIBs) is an urgent task for sustainable development. Aqueous proton batteries are attractive alternatives to LIBs because using water and protons addresses these two risks. However, most host materials undergo large volume changes upon H+ intercalation, which induces intraparticle cracking to accelerates parasitic reactions. Herein, we report that Mo3Nb2O14 bronze exhibits reversible H+ intercalation (200 mAh g-1) with a Coulombic efficiency of 99.7% owing to near-zero volume change and solid-solution-type phase transition. Combination of experimental and theoretical analyses clarifies that rotation and shrinkage of open tunnels, which consist of flexible corner-sharing Mo/NbOn polyhedra, relieve local structural distortions upon H+ intercalation to suppress intraparticle cracking. The prototype full cell of an aqueous proton battery with a Mo3Nb2O14 anode operates stably over 1000 charge/discharge cycles. This study reveals the importance of implementing distortion-relieving voids in host materials to reduce volume change upon charge/discharge.

Animal pharmacokinetics/pharmacodynamics (PK/PD) infection models for clinical development of antibacterial drugs: lessons from selected cases.

In the wake of emerging antimicrobial resistance, antibacterial drug development has become more critical. At the same time, development of antibacterial drugs targeting specific pathogens or resistance phenotypes that may have low prevalence presents challenges because it is difficult to conduct large, randomized controlled trials for such drugs. Animal models have increasingly supported clinical development of antibacterials; however, more work is needed to optimize the design and application of these animal models to ensure clear and actionable translation to further human investigation. This review discusses recent case studies of animal infection models used to support antibacterial drug development in order to illuminate considerations for future development of novel antibacterial drugs.

Magnetic-bead-based DNA-capture-assisted real-time polymerase chain reaction and recombinase polymerase amplification for the detection of African swine fever virus.

African swine fever (ASF) is a deadly disease in swine caused by African swine fever virus (ASFV). The global spread of ASFV has resulted in significant economic losses worldwide. Improved early detection has been the most important first line of defense for preventing ASF outbreaks and for activating control measures. Despite the availability of rapid amplification methods, nucleic acid extraction from specimens still needs to be performed in a laboratory. To facilitate this step, we exploited the strong affinity of biotin-streptavidin binding by functionalizing streptavidin-coated magnetic beads with biotinylated oligonucleotide capture probes to efficiently capture genotype II ASFV DNA directly from crude clinical samples. The captured DNA is suitable for detection using real-time quantitative PCR (qPCR) and recombinase polymerase amplification (RPA). In this study, ASFV DNA was efficiently captured from swine feces, serum, and tissue samples. Both DNA-capture-assisted qPCR and RPA-based detection methods have a limit of detection (LOD) of 102 copies/µl, which is comparable to those of commercially available kits. In addition, an RPA-SYBR Green I method was developed for the immediate visual detection of ASFV DNA, which is time-saving and efficient for resource-limited field settings. In summary, a rapid, versatile, sequence-specific DNA capture method was developed to efficiently capture ASFV DNA from swine clinical samples and subsequent detection by qPCR and RPA, which has the potential to be used for robust screening and surveillance of ASFV and in point-of-care (POC) diagnostics.

Evidence for the circulation of genotype 4 Eurasian avian-like lineage swine H1N1 influenza A viruses on Korean swine farms, obtained using a newly developed one-step multiplex RT-qPCR assay.

Genotype 4 (G4) Eurasian avian-like lineage swine H1N1 influenza A viruses, which are reassortants containing sequences from the pandemic 2009 H1N1 virus lineage, triple-reassortant-lineage internal genes, and EA-lineage external genes, have been reported in China since 2013. These have been predominant in pig populations since 2016 and have exhibited pandemic potential. In this study, we developed a one-step multiplex RT-qPCR assay targeting the M, HA1, and PB2 genes to detect G4 and related EA H1N1 viruses, with detection limits of 1.5 × 101 copies/µL and 1.15 × 10-2 ng/µL for the purified PCR products and RNA templates, respectively. The specificity of the detection method was confirmed using various influenza virus subtypes. When the one-step multiplex RT-qPCR assay was applied to swine respiratory samples collected between 2020 and 2022 in Korea, a virus related to G4 EA H1N1 strains was detected. Phylogenetic analysis based on portions of all eight genome segments showed that the positive sample contained HA, NA, PB2, NS, and NP genes closely related to those of G4 EA H1N1 viruses, confirming the ability of our assay to accurately detect G4 EA H1N1 viruses in the field.

EwaldSolidSolution: A High-Throughput Application to Quickly Sample Stable Site Arrangements for Ionic Solid Solutions.

Data-driven materials design of ionic solid solutions often requires sampling (meta)stable site arrangements among the massive number of possibilities, which has been hampered by the lack of relevant methods. Herein, we develop a quick high-throughput sampling application for site arrangements of ionic solid solutions. Given the Ewald Coulombic energies for an initial site arrangement, EwaldSolidSolution updates the modified parts of the energy with varying sites only, which can be exhaustively estimated by using massively parallel processing. Given two representative examples of solid electrolytes, Li10GeP2S12 and Na3Zr2Si2PO12, EwaldSolidSolution successfully calculates the Ewald Coulombic energies of 211,266,225 (235,702,467) site arrangements for Li10GeP2S12 (Na3Zr2Si2PO12) with 216 (160) ion sites per unit cell in 1223.2 (1187.9) seconds: 0.0057898 (0.0050397) milliseconds per site arrangement. The computational cost is enormously saved in comparison with an existing application, which estimates the energy of a site arrangement on the second timescale. The positive correlations between the Ewald Coulombic energies and those estimated by density functional theory calculations show that (meta)stable samples are easily revealed by our computationally inexpensive algorithm. We also reveal that the different-valence nearest-neighbor pairs are distinctively formed in the low-energy site arrangements. EwaldSolidSolution will boost the materials design of ionic solid solutions by attracting broad interest.

Radiographic findings involved in knee osteoarthritis progression are associated with pain symptom frequency and baseline disease severity: a population-level analysis using deep learning.

PURPOSE: To (1) develop a deep-learning (DL) algorithm capable of producing limb-length and knee-alignment measurements, and (2) determine the association between limb-length discrepancy (LLD), coronal-plane alignment, osteoarthritis (OA) severity, and patient-reported knee pain. METHODS: A multicenter, prospective patient cohort from the Osteoarthritis Initiative between 2004 and 2015 with full-limb standing radiographs at 12 month follow-up was included. A convolutional neural network was developed to automate measurements of the hip-knee-ankle (HKA) angle, femur, and tibia lengths, and LLD. At 12 month follow-up, patients reported their frequency of knee pain since enrollment and current level of knee pain. RESULTS: A total of 1011 patients (2022 knees, 52.3% female) with an average age of 61.2 ± 9.0 years were included. The algorithm performed 12,312 measurements in 5.4 h. ICC values of HKA and LLD ranged between 0.87 and 1.00 when compared against trained radiologist measurements. Knees producing pain most days of the month were significantly more varus (mean HKA:- 3.9° ± 2.8°) or valgus (mean HKA:2.8° ± 2.3°) compared to knees that did not produce any pain (p < 0.05). In varus knees, those producing pain on most days were part of the shorter limb compared to nonpainful knees (p < 0.05). Baseline Kellgren-Lawrence grade was significantly associated with HKA magnitude, LLD, and pain frequency at 12 month follow-up (p < 0.05 all). CONCLUSION: A higher frequency of knee pain was associated with more severe coronal plane deformity, with valgus deviation being one degree less than varus on average, suggesting that the knee tolerates less valgus deformation before symptoms become more consistent. Knee pain frequency was also associated with greater LLD and baseline KL grade, suggesting an association between radiographically apparent joint degeneration and pain frequency. LEVEL OF EVIDENCE: IV case series.

A practical guide to the development and deployment of deep learning models for the orthopedic surgeon: part II.

Deep learning has the potential to be one of the most transformative technologies to impact orthopedic surgery. Substantial innovation in this area has occurred over the past 5 years, but clinically meaningful advancements remain limited by a disconnect between clinical and technical experts. That is, it is likely that few orthopedic surgeons possess both the clinical knowledge necessary to identify orthopedic problems, and the technical knowledge needed to implement deep learning-based solutions. To maximize the utilization of rapidly advancing technologies derived from deep learning models, orthopedic surgeons should understand the steps needed to design, organize, implement, and evaluate a deep learning project and its workflow. Equipping surgeons with this knowledge is the objective of this three-part editorial review. Part I described the processes involved in defining the problem, team building, data acquisition, curation, labeling, and establishing the ground truth. Building on that, this review (Part II) provides guidance on pre-processing and augmenting the data, making use of open-source libraries/toolkits, and selecting the required hardware to implement the pipeline. Special considerations regarding model training and evaluation unique to deep learning models relative to "shallow" machine learning models are also reviewed. Finally, guidance pertaining to the clinical deployment of deep learning models in the real world is provided. As in Part I, the focus is on applications of deep learning for computer vision and imaging.

Artificial intelligence for automated identification of total shoulder arthroplasty implants.

BACKGROUND: Accurate and rapid identification of implant manufacturer and model is critical in the evaluation and management of patients requiring revision total shoulder arthroplasty (TSA). Failure to correctly identify implant designs in these circumstances may lead to delay in care, unexpected intraoperative challenges, increased morbidity, and excess health care costs. Deep learning (DL) permits automated image processing and holds the potential to mitigate such challenges while improving the value of care rendered. The purpose of this study was to develop an automated DL algorithm to identify shoulder arthroplasty implants from plain radiographs. METHODS: A total of 3060 postoperative images from patients who underwent TSA between 2011 and 2021 performed by 26 fellowship-trained surgeons at 2 independent tertiary academic hospitals in the Pacific Northwest and Mid-Atlantic Northeast were included. A DL algorithm was trained using transfer learning and data augmentation to classify 22 different reverse TSA and anatomic TSA prostheses from 8 implant manufacturers. Images were split into training and testing cohorts (2448 training and 612 testing images). Optimized model performance was assessed using standardized metrics including the multiclass area under the receiver operating characteristic curve (AUROC) and compared with a reference standard of implant data from operative reports. RESULTS: The algorithm classified implants at a mean speed of 0.079 seconds (±0.002 seconds) per image. The optimized model discriminated between 8 manufacturers (22 unique implants) with AUROCs of 0.994-1.000, accuracy of 97.1%, and sensitivities between 0.80 and 1.00 on the independent testing set. In the subset of single-institution implant predictions, a DL model identified 6 specific implants with AUROCs of 0.999-1.000, accuracy of 99.4%, and sensitivity >0.97 for all implants. Saliency maps revealed key differentiating features across implant manufacturers and designs recognized by the algorithm for classification. CONCLUSION: A DL model demonstrated excellent accuracy in identifying 22 unique TSA implants from 8 manufacturers. This algorithm may provide a clinically meaningful adjunct in assisting with preoperative planning for the failed TSA and allows for scalable expansion with additional radiographic data and validation efforts.

Geographic Variation in Knee Phenotypes Based on the Coronal Plane Alignment of the Knee Classification: A Systematic Review.

BACKGROUND: The extent of geographic variation in knee phenotypes remains unclear. The Coronal Plane Alignment of the Knee (CPAK) Classification proposes 9 coronal plane phenotypes based on constitutional limb alignment and joint line obliquity. This systematic review aims to examine differences in the distributions of CPAK types across geographic regions. METHODS: A systematic review of the literature was performed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Studies reporting distributions of knee phenotypes according to the CPAK classification for healthy and/or arthritic knees were included. RESULTS: There were 7 studies included, accounting for 5,964 knees in 3,917 subjects. Among healthy knees (n = 1,214), CPAK type II was the most common type in Belgium (39.2%), Taiwan (39.3%), and India (25.6%). Among arthritic knees (n = 2,804), CPAK type I was the most common in France (33.4%), India (58.8%), and Japan (53.8%), whereas CPAK type II was the most common in Australia (32.8%). The proportion of CPAK type I and II knees varied significantly across geographic regions among healthy (P < .01) and arthritic knees (P < .01). CONCLUSION: Significant variation in CPAK distributions exists between countries. Further work is needed to delineate racial and sexual differences in CPAK types, which were not explored in this article. A better understanding of population-level variability in knee phenotypes may enable orthopaedic surgeons to offer a more personalized approach to knee arthroplasty.

Deep Learning Phenotype Automation and Cohort Analyses of 1,946 Knees Using the Coronal Plane Alignment of the Knee Classification.

BACKGROUND: The Coronal Plane Alignment of the Knee (CPAK) classification allows for knee phenotyping which can be used in preoperative planning prior to total knee arthroplasty. We used deep learning (DL) to automate knee phenotyping and analyzed CPAK distributions in a large patient cohort. METHODS: Patients who had full-limb radiographs from a large arthritis database were retrospectively included. A DL algorithm was developed to automate CPAK knee alignment parameters including the lateral distal femoral, medial proximal tibia, hip-knee-ankle, and joint line obliquity angles. The algorithm was validated against a fellowship-trained arthroplasty surgeon. After applying the algorithm in a large patient cohort (n = 1,946 knees), the distribution of CPAK was compared across patient sex and baseline Kellgren-Lawrence (KL) scores. RESULTS: There was no significant difference in the CPAK angles (n = 140, P = .66-.98, inter-class correlation coefficient = 0.89-0.91) or phenotype classifications made by the algorithm and surgeon (P = .96). The deep learning algorithm measured the entire cohort (n = 1,946 knees, mean age 61 years [range, 46 to 80 years], 51% women) in < 5 hours. Women had more valgus CPAK phenotypes than men (P < .05). Patients who had higher KL grades at baseline (2 to 4) were more varus using the CPAK classification compared to lower KL grades (0 to 1) (P < .05). CONCLUSION: We applied an accurate, automated DL algorithm on a large patient cohort to determine knee phenotypes, helping to validate and strengthen the CPAK classification system. Analyses revealed that sex-specific and major bone loss adjustments may need to be accounted for when using this system.

Complication Rate After Primary Total Hip Arthroplasty Using the Posterior Approach and Enabling Technology: A Consecutive Series of 2,888 Hips.

BACKGROUND: Total hip arthroplasty (THA) is a safe and effective procedure; however, complications such as dislocation, fracture, and infection still occur. It is still unclear whether the dislocation rate via the posterior approach (PA) is better, equal, or worse than the direct anterior approach. Our aim was to report the primary THA dislocation rate via the PA using enabling technology in a large consecutive series of patients. METHODS: A retrospective cohort of 2,888 primary THAs were reviewed at a single, high-volume, academic institution from January 2018 to September 2021. All patients underwent a THA by 4 fellowship-trained orthopaedic surgeons through the PA with enabling technology. Overall dislocation and readmission rates within 90 days and up to 3 years were analyzed. RESULTS: Of the 2,888 procedures, a total of 39 patients had complications related to the surgery during the 3-year follow-up period. There were 10 patients (0.35%) who experienced a dislocation, with half undergoing surgical revision. Of the 39 patients who experienced complications, 37 (1.3%) were readmitted and 2 underwent revision during their hospital stay. Postoperative periprosthetic fractures were the most common cause for readmission and reoperation at a rate of 0.52% and 0.52%, respectively. CONCLUSION: The dislocation rate of 0.35% is one of the lowest reported rates via the PA at a mean follow up of 2.1 years and is comparable to previously published rates using alternate approaches. Using contemporary THA with enabling technology, the PA is a reliable approach with respect to dislocation and complication rates after primary THA.

Leg-Length Discrepancy Variability on Standard Anteroposterior Pelvis Radiographs: An Analysis Using Deep Learning Measurements.

BACKGROUND: Leg-length discrepancy (LLD) is a critical factor in component selection and placement for total hip arthroplasty. However, LLD radiographic measurements are subject to variation based on the femoral/pelvic landmarks chosen. This study leveraged deep learning (DL) to automate LLD measurements on pelvis radiographs and compared LLD based on several anatomically distinct landmarks. METHODS: Patients who had baseline anteroposterior pelvis radiographs from the Osteoarthritis Initiative were included. A DL algorithm was created to identify LLD-relevant landmarks (ie, teardrop (TD), obturator foramen, ischial tuberosity, greater and lesser trochanters) and measure LLD accurately using six landmark combinations. The algorithm was then applied to automate LLD measurements in the entire cohort of patients. Interclass correlation coefficients (ICC) were calculated to assess agreement between different LLD methods. RESULTS: The DL algorithm measurements were first validated in an independent cohort for all six LLD methods (ICC = 0.73-0.98). Images from 3,689 patients (22,134 LLD measurements) were measured in 133 minutes. When using the TD and lesser trochanter landmarks as the standard LLD method, only measuring LLD using the TD and greater trochanter conferred acceptable agreement (ICC = 0.72). When comparing all six LLD methods for agreement, no combination had an ICC>0.90. Only two (13%) combinations had an ICC>0.75 and eight (53%) combinations had a poor ICC (<0.50). CONCLUSION: We leveraged DL to automate LLD measurements in a large patient cohort and found considerable variation in LLD based on the pelvic/femoral landmark selection. This emphasizes the need for the standardization of landmarks for both research and surgical planning.

Standardized Fixation Zones and Cone Assessments for Revision Total Knee Arthroplasty Using Deep Learning.

BACKGROUND: Achieving adequate implant fixation is critical to optimize survivorship and postoperative outcomes after revision total knee arthroplasty (rTKA). Three anatomical zones (ie, epiphysis, metaphysis, and diaphysis) have been proposed to assess fixation, but are not well-defined. The purpose of the study was to develop a deep learning workflow capable of automatically delineating rTKA zones and cone placements in a standardized way on postoperative radiographs. METHODS: A total of 235 patients who underwent rTKA were randomly partitioned (6:2:2 training, validation, and testing split), and a U-Net segmentation workflow was developed to delineate rTKA fixation zones and assess revision cone placement on anteroposterior radiographs. Algorithm performance for zone delineation and cone placement were compared against ground truths from a fellowship-trained arthroplasty surgeon using the dice segmentation coefficient and accuracy metrics. RESULTS: On the testing cohort, the algorithm defined zones in 98% of images (8 seconds/image) using anatomical landmarks. The dice segmentation coefficient between the model and surgeon was 0.89 ± 0.08 (interquartile range [IQR]:0.88-0.94) for femoral zones, 0.91 ± 0.08 (IQR: 0.91-0.95) for tibial zones, and 0.90 ± 0.05 (IQR:0.88-0.94) for all zones. Cone identification and zonal cone placement accuracy were 98% and 96%, respectively, for the femur and 96% and 89%, respectively, for the tibia. CONCLUSION: A deep learning algorithm was developed to automatically delineate revision zones and cone placements on postoperative rTKA radiographs in an objective, standardized manner. The performance of the algorithm was validated against a trained surgeon, suggesting that the algorithm demonstrated excellent predictive capabilities in accordance with relevant anatomical landmarks used by arthroplasty surgeons in practice.

An Interpretable Machine Learning Model for Predicting 10-Year Total Hip Arthroplasty Risk.

BACKGROUND: As the demand for total hip arthroplasty (THA) rises, a predictive model for THA risk may aid patients and clinicians in augmenting shared decision-making. We aimed to develop and validate a model predicting THA within 10 years in patients using demographic, clinical, and deep learning (DL)-automated radiographic measurements. METHODS: Patients enrolled in the osteoarthritis initiative were included. DL algorithms measuring osteoarthritis- and dysplasia-relevant parameters on baseline pelvis radiographs were developed. Demographic, clinical, and radiographic measurement variables were then used to train generalized additive models to predict THA within 10 years from baseline. A total of 4,796 patients were included [9,592 hips; 58% female; 230 THAs (2.4%)]. Model performance using 1) baseline demographic and clinical variables 2) radiographic variables, and 3) all variables was compared. RESULTS: Using 110 demographic and clinical variables, the model had a baseline area under the receiver operating curve (AUROC) of 0.68 and area under the precision recall curve (AUPRC) of 0.08. Using 26 DL-automated hip measurements, the AUROC was 0.77 and AUPRC was 0.22. Combining all variables, the model improved to an AUROC of 0.81 and AUPRC of 0.28. Three of the top five predictive features in the combined model were radiographic variables, including minimum joint space, along with hip pain and analgesic use. Partial dependency plots revealed predictive discontinuities for radiographic measurements consistent with literature thresholds of osteoarthritis progression and hip dysplasia. CONCLUSION: A machine learning model predicting 10-year THA performed more accurately with DL radiographic measurements. The model weighted predictive variables in concordance with clinical THA pathology assessments.