Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Surgery Surgery

Artificial Intelligence for Automated Implant Identification in Knee Arthroplasty: A Multicenter External Validation Study Exceeding 3.5 Million Plain Radiographs.

In The Journal of arthroplasty ; h5-index 65.0

BACKGROUND : Surgical management of complications following knee arthroplasty demands accurate and timely identification of implant manufacturer and model. Automated image processing using deep machine learning has been previously developed and internally validated; however, external validation is essential prior to scaling clinical implementation for generalizability.

METHODS : We trained, validated, and externally tested a deep learning system to classify knee arthroplasty systems as one of the 9 models from four manufacturers derived from 4,724 original, retrospectively collected antero-posterior (AP) plain knee radiographs across three academic referral centers. From these radiographs, 3,568 were used for training, 412 for validation, and 744 for external testing. Augmentation was applied to the training set (n = 3,568,000) to increase model robustness. Performance was determined by area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. The training and testing sets were drawn from statistically different populations of implants (P < .001).

RESULTS : After 1,000 training epochs by the deep learning system, the system discriminated 9 implant models with a mean area under the receiver operating characteristic curve of 0.989, accuracy of 97.4%, sensitivity of 89.2%, and specificity of 99.0% in the external testing dataset of 744 AP radiographs. The software classified implants at a mean speed of 0.02 seconds per image.

CONCLUSION : An artificial intelligence-based software identifying knee arthroplasty implants 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 knee arthroplasty.

Karnuta Jaret M, Shaikh Hashim J F, Murphy Michael P, Brown Nicholas M, Pearle Andrew D, Nawabi Danyal H, Chen Antonia F, Ramkumar Prem N

2023-Mar-18

artificial intelligence, implant identification, knee arthroplasty, machine learning, revision arthroplasty

Public Health Public Health

Serum Immune Markers and Transition to Psychosis in Individuals at Clinical High Risk.

In Brain, behavior, and immunity

Individuals at clinical high risk (CHR) for psychosis have been found to have altered cytokine levels, but whether these changes are related to clinical outcomes remains unclear. We addressed this issue by measuring serum levels of 20 immune markers in 325 participants (n=269 CHR, n=56 healthy controls) using multiplex immunoassays, and then followed up the CHR sample to determine their clinical outcomes. Among 269 CHR individuals, 50 (18.6%) developed psychosis by two years. Univariate and machine learning techniques were used to compare levels of inflammatory markers in CHR subjects and healthy controls, and in CHR subjects who had (CHR-t), or had not (CHR-nt) transitioned to psychosis. An ANCOVA identified significant group differences (CHR-t, CHR-nt and controls) and post-hoc tests indicated that VEGF levels and the IL-10/IL-6 ratio were significantly higher in CHR-t than CHR-nt, after adjusting for multiple comparisons. Using a penalised logistic regression classifier, CHR participants were distinguished from controls with an area-under the curve (AUC) of 0.82, with IL-6 and IL-4 levels the most important discriminating features. Transition to psychosis was predicted with an AUC of 0.57, with higher VEGF level and IL-10/IL-6 ratio the most important discriminating features. These data suggest that alterations in the levels of peripheral immune markers are associated with the subsequent onset of psychosis. The association with increased VEGF levels could reflect altered blood-brain-barrier (BBB) permeability, while the link with an elevated IL-10/IL-6 ratio points to an imbalance between anti- and pro-inflammatory cytokines.

Mondelli Valeria, Blackman Graham, Kempton Matthew J, Pollak Thomas A, Iyegbe Conrad, Valmaggia Lucia R, Amminger Paul, Barrantes-Vidal Neus, Bressan Rodrigo, van der Gaag Mark, de Haan Lieuwe, Krebs Marie-Odile, Nordentoft Merete, Ruhrmann Stephan, Riecher-Rössler Anita, Rutten Bart P F, Sachs Gabriele, Koutsouleris Nikolaos, McGuire Philip

2023-Mar-18

VEGF, clinical high risk, cytokines, immune markers, inflammation, interlukin-6, psychosis, transition

General General

Identification of potentially contaminated areas of soil microplastic based on machine learning: A case study in Taihu Lake region, China.

In The Science of the total environment

Soil microplastic (MP) pollution has recently become increasingly aggravated, with severe consequences being generated. Understanding the spatial distribution characteristics of soil MPs is an important prerequisite for protecting and controlling soil pollution. However, determining the spatial distribution of soil MPs through a large number of soil field sampling and laboratory test analyses is unrealistic. In this study, we compared the accuracy and applicability of different machine learning models for predicting the spatial distribution of soil MPs. The support vector machine regression model with radial basis function (RBF) as kernel function (SVR-RBF) has a high prediction accuracy (R2 = 0.8934). Among the six ensemble models, random forest (R2 = 0.9007) could better explain the significance of source and sink factors affecting the occurrence of soil MPs. Soil texture, population density, and MPs point of interest (MPs-POI) were the main source-sink factors affecting the occurrence of soil MPs. Furthermore, the accumulation of MPs in soil was significantly affected by human activity. The spatial distribution map of soil MP pollution in the study area was drawn based on the bivariate local Moran's I model of soil MP pollution and the normalized difference vegetation index (NDVI) variation trend. A total of 48.74 km2 of soil was in an area of serious MP pollution, mainly concentrated in urban soil. This study provides a hybrid framework that includes spatial distribution prediction of MPs, source-sink analysis, and pollution risk area identification, providing scientific and systematic methods and techniques for pollution management in other soil environments.

Qiu Yifei, Zhou Shenglu, Zhang Chuchu, Qin Wendong, Lv Chengxiang, Zou Mengmeng

2023-Mar-18

Microplastic, Potential risk, Source–sink, Spatial correlation analysis

General General

Improving predictions of shale wettability using advanced machine learning techniques and nature-inspired methods: Implications for carbon capture utilization and storage.

In The Science of the total environment

The utilization of carbon capture utilization and storage (CCUS) in unconventional formations is a promising way for improving hydrocarbon production and combating climate change. Shale wettability plays a crucial factor for successful CCUS projects. In this study, multiple machine learning (ML) techniques, including multilayer perceptron (MLP) and radial basis function neural networks (RBFNN), were used to evaluate shale wettability based on five key features, including formation pressure, temperature, salinity, total organic carbon (TOC), and theta zero. The data were collected from 229 datasets of contact angle in three states of shale/oil/brine, shale/CO2/brine, and shale/CH4/brine systems. Five algorithms were used to tune MLP, while three optimization algorithms were used to optimize the RBFNN computing framework. The results indicate that the RBFNN-MVO model achieved the best predictive accuracy, with a root mean square error (RMSE) value of 0.113 and an R2 of 0.999993. The sensitivity analysis showed that theta zero, TOC, pressure, temperature, and salinity were the most sensitive features. This research demonstrates the effectiveness of RBFNN-MVO model in evaluating shale wettability for CCUS initiatives and cleaner production.

Zhang Hemeng, Thanh Hung Vo, Rahimi Mohammad, Al-Mudhafar Watheq J, Tangparitkul Suparit, Zhang Tao, Dai Zhenxue, Ashraf Umar

2023-Mar-18

Artificial intelligence, CO(2) capture, Carbon storage, Contact angle measurement, Deep learning, Wettability behavior

General General

Calving prediction with continuous measurement of subcutaneous tissue glucose concentration in pregnant cows.

In Theriogenology ; h5-index 37.0

To reduce losses of dams and calves due to unfortunate events, such as dystocia and freezing to death, identifying the onset of calving and providing necessary assistance are crucial. Prepartum increase in blood glucose concentration is a known indicator to detect labor in pregnant cows. However, some issues, including the need for frequent blood sampling and stress on cows, must be resolved before establishing a method for anticipating calving using changes in blood glucose concentrations. Herein, instead of measuring the blood glucose concentrations, subcutaneous tissue glucose concentration (tGLU) was measured in peripartum primiparous (n = 6) and multiparous (n = 8) cows at 15 min intervals using a wearable sensor. A transient increase in tGLU was observed in the peripartum period, with peak individual concentrations occurring between 2.8 h before and 3.5 h after calving. tGLU in primiparous cows was significantly higher than that in multiparous cows. To account for individual variations in basal tGLU, the maximum relative increase in the 3-h moving average of tGLU (Max MA) was used to predict calving. Cutoff points for Max MA were established by parity, with receiver operating characteristic analysis predicting calving within 24, 18, 12, and 6 h. Except for one multiparous cow that showed an increase in tGLU just before calving, all cows reached at least two cutoff points and calving was predicted successfully. The time interval between reaching the tGLU cutoff points that predicted calving within 12 h and actual calving was 12.3 ± 5.6 h. In conclusion, this study demonstrated the potential role of tGLU as a predictive indicator of calving in cows. Advancements in machine learning-based prediction algorithms and bovine-optimized sensors will help in increasing the accuracy of calving prediction using tGLU.

Wakatsuki Takuji, Nakamura Tsukasa, Ishii Ayumi, Konishi Kanta, Okubo Michiko, Souma Kousaku, Hirayama Hiroki

2023-Mar-13

Calving, Calving prediction systems, Cows, Dystocia, Subcutaneous tissue glucose concentration, Wearable sensors

General General

Step-adaptive sound guidance enhances locomotor-respiratory coupling in novice female runners: A proof-of-concept study.

In Frontiers in sports and active living

INTRODUCTION : Many runners struggle to find a rhythm during running. This may be because 20-40% of runners experience unexplained, unpleasant breathlessness at exercise onset. Locomotor-respiratory coupling (LRC), a synchronization phenomenon in which the breath is precisely timed with the steps, may provide metabolic or perceptual benefits to address these limitations. It can also be consciously performed. Hence, we developed a custom smartphone application to provide real-time LRC guidance based on individual step rate.

METHODS : Sixteen novice-intermediate female runners completed two control runs outdoors and indoors at a self-selected speed with auditory step rate feedback. Then, the runs were replicated with individualized breath guidance at specific LRC ratios. Hexoskin smart shirts were worn and analyzed with custom algorithms to estimate continuous LRC frequency and phase coupling.

RESULTS : LRC guidance led to a large significant increase in frequency coupling outdoor from 26.3 ± 10.7 (control) to 69.9 ± 20.0 % (LRC) "attached". There were similarly large differences in phase coupling between paired trials, and LRC adherence was stronger for the indoor treadmill runs versus outdoors. There was large inter-individual variability in running pace, preferred LRC ratio, and instruction adherence metrics.

DISCUSSION : Our approach demonstrates how personalized, step-adaptive sound guidance can be used to support this breathing strategy in novice runners. Subsequent investigations should evaluate the skill learning of LRC on a longer time basis to effectively clarify its risks and advantages.

Harbour Eric, van Rheden Vincent, Schwameder Hermann, Finkenzeller Thomas

2023

breathing strategies, breathing techniques, entrainment, locomotor-respiratory coupling, running, synchronization