Enhancing prediction of supraspinatus/infraspinatus tendon complex injuries through integration of deep visual features and clinical information: a multicenter two-round assessment study.

OBJECTIVE: Develop and evaluate an ensemble clinical machine learning-deep learning (CML-DL) model integrating deep visual features and clinical data to improve the prediction of supraspinatus/infraspinatus tendon complex (SITC) injuries. METHODS: Patients with suspected SITC injuries were retrospectively recruited from two hospitals, with clinical data and shoulder x-ray radiographs collected. An ensemble CML-DL model was developed for diagnosing normal or insignificant rotator cuff abnormality (NIRCA) and significant rotator cuff tear (SRCT). All patients suspected with SRCT were confirmed by arthroscopy examination. The model's performance was evaluated using sensitivity, specificity, accuracy, and area under the curve (AUC) metrics, and a two-round assessment was conducted to authenticate its clinical applicability. RESULTS: A total of 974 patients were divided into three cohorts: the training cohort (n = 828), the internal validation cohort (n = 89), and the external validation cohort (n = 57). The CML-DL model, which integrates clinical and deep visual features, demonstrated superior performance compared to individual models of either type. The model's sensitivity, specificity, accuracy, and area under curve (95% confidence interval) were 0.880, 0.812, 0.836, and 0.902 (0.858-0.947), respectively. The CML-DL model exhibited higher sensitivity and specificity compared to or on par with the physicians in all validation cohorts. Furthermore, the assistance of the ensemble CML-DL model resulted in a significant improvement in sensitivity for junior physicians in all validation cohorts, without any reduction in specificity. CONCLUSIONS: The ensembled CML-DL model provides a solution to help physicians improve the diagnosis performance of SITC injury, especially for junior physicians with limited expertise. CRITICAL RELEVANCE STATEMENT: The ensembled clinical machine learning-deep learning (CML-DL) model integrating deep visual features and clinical data provides a superior performance in the diagnosis of supraspinatus/infraspinatus tendon complex (SITC) injuries, particularly for junior physicians with limited expertise. KEY POINTS: 1. Integrating clinical and deep visual features improves diagnosing SITC injuries. 2. Ensemble CML-DL model validated for clinical use in two-round assessment. 3. Ensemble model boosts sensitivity in SITC injury diagnosis for junior physicians.

Design and Analysis of a 6-DOF Magnetic Suspension Platform with an Improved Permanent Magnetic Array.

For ultra-precision, large stroke, and high start/stop acceleration, a novel 6-DOF magnetic suspension platform with a novel structure of the permanent array is proposed. The structure and the working principle of the novel platform are introduced. An accurate model of the novel structure was established to calculate the magnetic density distribution for obtaining the parameters and performance of the magnetic suspension platform. The analytical model's results were verified by the finite element method. The driving force model of the magnetic suspension platform was established based on the Lorentz force. Twelve laser displacement sensors were applied to perceive the posture and vibration acceleration of the platform. The hardware information and the measurement models were introduced and established based on the layout. Finally, the Lorentz force characteristics of the proposed platform were investigated and compared with the conventional magnetic platform by the finite element analysis. The results show that the average magnetic flux density is 0.54T, the horizontal current stiffness along the X-axis is 63.1N/A, the current stiffness along the Y-axis is 61.6N/A, and the average output torque is 7.2 N*cm of the novel platform, larger than those of the conventional ones.

Limited memory optimizes cooperation in social dilemma experiments.

Cooperation is one of the key collective behaviours of human society. Despite discoveries of several social mechanisms underpinning cooperation, relatively little is known about how our neural functions affect cooperative behaviours. Here, we study the effect of a main neural function, working-memory capacity, on cooperation in repeated Prisoner's Dilemma experiments. Our experimental paradigm overcomes the obstacles in measuring and changing subjects' working-memory capacity. We find that the optimal cooperation level occurs when subjects remember two previous rounds of information, and cooperation increases abruptly from no memory capacity to minimal memory capacity. The results can be explained by memory-based conditional cooperation of subjects. We propose evolutionary models based on replicator dynamics and Markov processes, respectively, which are in good agreement with experimental results of different memory capacities. Our experimental findings differ from previous hypotheses and predictions of existent models and theories, and suggest a neural basis and evolutionary roots of cooperation beyond cultural influences.

Locating multiple diffusion sources in time varying networks from sparse observations.

Data based source localization in complex networks has a broad range of applications. Despite recent progress, locating multiple diffusion sources in time varying networks remains to be an outstanding problem. Bridging structural observability and sparse signal reconstruction theories, we develop a general framework to locate diffusion sources in time varying networks based solely on sparse data from a small set of messenger nodes. A general finding is that large degree nodes produce more valuable information than small degree nodes, a result that contrasts that for static networks. Choosing large degree nodes as the messengers, we find that sparse observations from a few such nodes are often sufficient for any number of diffusion sources to be located for a variety of model and empirical networks. Counterintuitively, sources in more rapidly varying networks can be identified more readily with fewer required messenger nodes.

Equal status in Ultimatum Games promotes rational sharing.

Experiments on the Ultimatum Game (UG) repeatedly show that people's behaviour is far from rational. In UG experiments, a subject proposes how to divide a pot and the other can accept or reject the proposal, in which case both lose everything. While rational people would offer and accept the minimum possible amount, in experiments low offers are often rejected and offers are typically larger than the minimum, and even fair. Several theoretical works have proposed that these results may arise evolutionarily when subjects act in both roles and there is a fixed interaction structure in the population specifying who plays with whom. We report the first experiments on structured UG with subjects playing simultaneously both roles. We observe that acceptance levels of responders approach rationality and proposers accommodate their offers to their environment. More precisely, subjects keep low acceptance levels all the time, but as proposers they follow a best-response-like approach to choose their offers. We thus find that status equality promotes rational sharing while the influence of structure leads to fairer offers compared to well-mixed populations. Our results are far from what is observed in single-role UG experiments and largely different from available predictions based on evolutionary game theory.

Emergence of communities and diversity in social networks.

Communities are common in complex networks and play a significant role in the functioning of social, biological, economic, and technological systems. Despite widespread interest in detecting community structures in complex networks and exploring the effect of communities on collective dynamics, a deep understanding of the emergence and prevalence of communities in social networks is still lacking. Addressing this fundamental problem is of paramount importance in understanding, predicting, and controlling a variety of collective behaviors in society. An elusive question is how communities with common internal properties arise in social networks with great individual diversity. Here, we answer this question using the ultimatum game, which has been a paradigm for characterizing altruism and fairness. We experimentally show that stable local communities with different internal agreements emerge spontaneously and induce social diversity into networks, which is in sharp contrast to populations with random interactions. Diverse communities and social norms come from the interaction between responders with inherent heterogeneous demands and rational proposers via local connections, where the former eventually become the community leaders. This result indicates that networks are significant in the emergence and stabilization of communities and social diversity. Our experimental results also provide valuable information about strategies for developing network models and theories of evolutionary games and social dynamics.

Locating the source of diffusion in complex networks by time-reversal backward spreading.

Locating the source that triggers a dynamical process is a fundamental but challenging problem in complex networks, ranging from epidemic spreading in society and on the Internet to cancer metastasis in the human body. An accurate localization of the source is inherently limited by our ability to simultaneously access the information of all nodes in a large-scale complex network. This thus raises two critical questions: how do we locate the source from incomplete information and can we achieve full localization of sources at any possible location from a given set of observable nodes. Here we develop a time-reversal backward spreading algorithm to locate the source of a diffusion-like process efficiently and propose a general locatability condition. We test the algorithm by employing epidemic spreading and consensus dynamics as typical dynamical processes and apply it to the H1N1 pandemic in China. We find that the sources can be precisely located in arbitrary networks insofar as the locatability condition is assured. Our tools greatly improve our ability to locate the source of diffusion in complex networks based on limited accessibility of nodal information. Moreover, they have implications for controlling a variety of dynamical processes taking place on complex networks, such as inhibiting epidemics, slowing the spread of rumors, pollution control, and environmental protection.