Machine Learning for RNA Design: LEARNA.

Machine learning algorithms, and in particular deep learning approaches, have recently garnered attention in the field of molecular biology due to remarkable results. In this chapter, we describe machine learning approaches specifically developed for the design of RNAs, with a focus on the learna_tools Python package, a collection of automated deep reinforcement learning algorithms for secondary structure-based RNA design. We explain the basic concepts of reinforcement learning and its extension, automated reinforcement learning, and outline how these concepts can be successfully applied to the design of RNAs. The chapter is structured to guide through the usage of the different programs with explicit examples, highlighting particular applications of the individual tools.

Our Experience with Labyrinthine Fistula: Prospective Hearing Outcomes.

Introduction: Chronic otitis media with cholesteatoma is a locally destructive middle ear infection with bone erosive properties which can lead to fistula if erodes labyrinth. Materials and Methods: A prospective observational study was conducted at tertiary health care centre with a total of 12 patients who presented with complaints of otorrhoea, hearing loss and vertigo. Such patients were evaluated clinic audiologically and radiologically as a pre op assessment. Post-surgery audiological assessment was done. Results: Hearing preservation was seen in 91.7% patients and none of the patients had iatrogenic sensorineural hearing loss. Conclusion: Complete removal of the cholesteatoma is beneficial and does not lead to any iatrogenic SNHL when performed meticulously. A newer way of diagnosing membranous labyrinthine breach utilizing Magnetic Resonance Imaging T2 Diffusion Weighted (MRI- T2 DW) sequence can be implemented.

Energy-aware bio-inspired spiking reinforcement learning system architecture for real-time autonomous edge applications.

Mobile, low-cost, and energy-aware operation of Artificial Intelligence (AI) computations in smart circuits and autonomous robots will play an important role in the next industrial leap in intelligent automation and assistive devices. Neuromorphic hardware with spiking neural network (SNN) architecture utilizes insights from biological phenomena to offer encouraging solutions. Previous studies have proposed reinforcement learning (RL) models for SNN responses in the rat hippocampus to an environment where rewards depend on the context. The scale of these models matches the scope and capacity of small embedded systems in the framework of Internet-of-Bodies (IoB), autonomous sensor nodes, and other edge applications. Addressing energy-efficient artificial learning problems in such systems enables smart micro-systems with edge intelligence. A novel bio-inspired RL system architecture is presented in this work, leading to significant energy consumption benefits without foregoing real-time autonomous processing and accuracy requirements of the context-dependent task. The hardware architecture successfully models features analogous to synaptic tagging, changes in the exploration schemes, synapse saturation, and spatially localized task-based activation observed in the brain. The design has been synthesized, simulated, and tested on Intel MAX10 Field-Programmable Gate Array (FPGA). The problem-based bio-inspired approach to SNN edge architectural design results in 25X reduction in average power compared to the state-of-the-art for a test with real-time context learning and 30 trials. Furthermore, 940x lower energy consumption is achieved due to improvement in the execution time.

Effectiveness of a Digital Health Intervention Leveraging Reinforcement Learning: Results From the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) Randomized Clinical Trial.

BACKGROUND: Digital and mobile health interventions using personalization via reinforcement learning algorithms have the potential to reach large number of people to support physical activity and help manage diabetes and depression in daily life. OBJECTIVE: The Diabetes and Mental Health Adaptive Notification and Tracking Evaluation (DIAMANTE) study tested whether a digital physical activity intervention using personalized text messaging via reinforcement learning algorithms could increase step counts in a diverse, multilingual sample of people with diabetes and depression symptoms. METHODS: From January 2020 to June 2022, participants were recruited from 4 San Francisco, California-based public primary care clinics and through web-based platforms to participate in the 24-week randomized controlled trial. Eligibility criteria included English or Spanish language preference and a documented diagnosis of diabetes and elevated depression symptoms. The trial had 3 arms: a Control group receiving a weekly mood monitoring message, a Random messaging group receiving randomly selected feedback and motivational text messages daily, and an Adaptive messaging group receiving text messages selected by a reinforcement learning algorithm daily. Randomization was performed with a 1:1:1 allocation. The primary outcome, changes in daily step counts, was passively collected via a mobile app. The primary analysis assessed changes in daily step count using a linear mixed-effects model. An a priori subanalysis compared the primary step count outcome within recruitment samples. RESULTS: In total, 168 participants were analyzed, including those with 24% (40/168) Spanish language preference and 37.5% (63/168) from clinic-based recruitment. The results of the linear mixed-effects model indicated that participants in the Adaptive arm cumulatively gained an average of 3.6 steps each day (95% CI 2.45-4.78; P<.001) over the 24-week intervention (average of 608 total steps), whereas both the Control and Random arm participants had significantly decreased rates of change. Postintervention estimates suggest that participants in the Adaptive messaging arm showed a significant step count increase of 19% (606/3197; P<.001), in contrast to 1.6% (59/3698) and 3.9% (136/3480) step count increase in the Random and Control arms, respectively. Intervention effectiveness differences were observed between participants recruited from the San Francisco clinics and those recruited via web-based platforms, with the significant step count trend persisting across both samples for participants in the Adaptive group. CONCLUSIONS: Our study supports the use of reinforcement learning algorithms for personalizing text messaging interventions to increase physical activity in a diverse sample of people with diabetes and depression. It is the first to test this approach in a large, diverse, and multilingual sample. TRIAL REGISTRATION: ClinicalTrials.gov NCT03490253; https://clinicaltrials.gov/study/NCT03490253. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1136/bmjopen-2019-034723.

Development of silk microfiber-reinforced bioink for muscle tissue engineering and in situ printing by a handheld 3D printer.

Volumetric muscle loss (VML) presents a significant challenge in tissue engineering due to the irreparable nature of extensive muscle injuries. In this study, we propose a novel approach for VML treatment using a bioink composed of silk microfiber-reinforced silk fibroin (SF) hydrogel. The engineered scaffolds are predesigned to provide structural support and fiber alignment to promote tissue regeneration in situ. We also validated our custom-made handheld 3D printer performance and showcased its potential applications for in situ printing using robotics. The fiber contents of SF and gelatin ink were varied from 1 to 5 %. Silk fibroin microfibers reinforced ink offered increased viscosity of the gel, which enhanced the shape fidelity and mechanical strength of the bulk scaffold. The fiber-reinforced bioink also demonstrated better cell-biomaterial interaction upon printing. The handheld 3D printer enabled the precise and on-demand fabrication of scaffolds directly at the defect site, for personalized and minimally invasive treatment. This innovative approach holds promise for addressing the challenges associated with VML treatment and advancing the field of regenerative medicine.

Synchronous and efficient removal of carbon, nitrogen, and phosphorus from actual rural sewage by composite wetlands enhanced with functional fillers.

A composite wetland (CECW) was constructed by introducing P-adsorption filler (EPAF) and activated sludge into traditional wetlands for treating actual sewage. The results showed that EPAF improved P removal through physico-chemical adsorption, and it could be stably regenerated after adsorption saturation without potential risks. Meanwhile, zeolite promoted NH4+-N reduction in sewage by cation exchange. In addition, simultaneous biological removal of carbon, nitrogen, and phosphorus was achieved through nitrification, denitrification, anammox, and aerobic P-accumulation processes induced by Nitrobacter, Proteus Hauser, Candidatus Paracaedibacter, and Brevundimonas. Under the coupling of filler interception/adsorption, microbial assimilation/transformation, flocculation, and plant uptake, CECW obtained the removal rates of 93.22 %, 85.75 %, 91.80 %, 95.38 %, 97.07 %, and 78.05 % for turbidity, TN, NH4+-N, TP, PO43--P, and TCOD, which met the Class 1A standard (GB18918-2002). Therefore, the experiment systematically investigated the effects and mechanism of CECW in treating actual sewage, which could provide reference for rural sewage treatment and sludge utilization.

An algorithmic account for how humans efficiently learn, transfer, and compose hierarchically structured decision policies.

Learning structures that effectively abstract decision policies is key to the flexibility of human intelligence. Previous work has shown that humans use hierarchically structured policies to efficiently navigate complex and dynamic environments. However, the computational processes that support the learning and construction of such policies remain insufficiently understood. To address this question, we tested 1026 human participants, who made over 1 million choices combined, in a decision-making task where they could learn, transfer, and recompose multiple sets of hierarchical policies. We propose a novel algorithmic account for the learning processes underlying observed human behavior. We show that humans rely on compressed policies over states in early learning, which gradually unfold into hierarchical representations via meta-learning and Bayesian inference. Our modeling evidence suggests that these hierarchical policies are structured in a temporally backward, rather than forward, fashion. Taken together, these algorithmic architectures characterize how the interplay between reinforcement learning, policy compression, meta-learning, and working memory supports structured decision-making and compositionality in a resource-rational way.

Demystifying unsupervised learning: how it helps and hurts.

Humans and machines rarely have access to explicit external feedback or supervision, yet manage to learn. Most modern machine learning systems succeed because they benefit from unsupervised data. Humans are also expected to benefit and yet, mysteriously, empirical results are mixed. Does unsupervised learning help humans or not? Here, we argue that the mixed results are not conflicting answers to this question, but reflect that humans self-reinforce their predictions in the absence of supervision, which can help or hurt depending on whether predictions and task align. We use this framework to synthesize empirical results across various domains to clarify when unsupervised learning will help or hurt. This provides new insights into the fundamentals of learning with implications for instruction and lifelong learning.

Acquiring musculoskeletal skills with curriculum-based reinforcement learning.

Efficient musculoskeletal simulators and powerful learning algorithms provide computational tools to tackle the grand challenge of understanding biological motor control. Our winning solution for the inaugural NeurIPS MyoChallenge leverages an approach mirroring human skill learning. Using a novel curriculum learning approach, we trained a recurrent neural network to control a realistic model of the human hand with 39 muscles to rotate two Baoding balls in the palm of the hand. In agreement with data from human subjects, the policy uncovers a small number of kinematic synergies, even though it is not explicitly biased toward low-dimensional solutions. However, selectively inactivating parts of the control signal, we found that more dimensions contribute to the task performance than suggested by traditional synergy analysis. Overall, our work illustrates the emerging possibilities at the interface of musculoskeletal physics engines, reinforcement learning, and neuroscience to advance our understanding of biological motor control.

Autonomous countertraction for secure field of view in laparoscopic surgery using deep reinforcement learning.

PURPOSE: Countertraction is a vital technique in laparoscopic surgery, stretching the tissue surface for incision and dissection. Due to the technical challenges and frequency of countertraction, autonomous countertraction has the potential to significantly reduce surgeons' workload. Despite several methods proposed for automation, achieving optimal tissue visibility and tension for incision remains unrealized. Therefore, we propose a method for autonomous countertraction that enhances tissue surface planarity and visibility. METHODS: We constructed a neural network that integrates a point cloud convolutional neural network (CNN) with a deep reinforcement learning (RL) model. This network continuously controls the forceps position based on the surface shape observed by a camera and the forceps position. RL is conducted in a physical simulation environment, with verification experiments performed in both simulation and phantom environments. The evaluation was performed based on plane error, representing the average distance between the tissue surface and its least-squares plane, and angle error, indicating the angle between the tissue surface vector and the camera's optical axis vector. RESULTS: The plane error decreased under all conditions both simulation and phantom environments, with 93.3% of case showing a reduction in angle error. In simulations, the plane error decreased from 3.6 ± 1.5 mm to 1.1 ± 1.8 mm , and the angle error from 29 ± 19 ∘ to 14 ± 13 ∘ . In the phantom environment, the plane error decreased from 0.96 ± 0.24 mm to 0.39 ± 0.23 mm , and the angle error from 32 ± 29 ∘ to 17 ± 20 ∘ . CONCLUSION: The proposed neural network was validated in both simulation and phantom experimental settings, confirming that traction control improved tissue planarity and visibility. These results demonstrate the feasibility of automating countertraction using the proposed model.

Utility-Driven End-to-End Network Slicing for Diverse IoT Users in MEC: A Multi-Agent Deep Reinforcement Learning Approach.

Mobile Edge Computing (MEC) is crucial for reducing latency by bringing computational resources closer to the network edge, thereby enhancing the quality of services (QoS). However, the broad deployment of cloudlets poses challenges in efficient network slicing, particularly when traffic distribution is uneven. Therefore, these challenges include managing diverse resource requirements across widely distributed cloudlets, minimizing resource conflicts and delays, and maintaining service quality amid fluctuating request rates. Addressing this requires intelligent strategies to predict request types (common or urgent), assess resource needs, and allocate resources efficiently. Emerging technologies like edge computing and 5G with network slicing can handle delay-sensitive IoT requests rapidly, but a robust mechanism for real-time resource and utility optimization remains necessary. To address these challenges, we designed an end-to-end network slicing approach that predicts common and urgent user requests through T distribution. We formulated our problem as a multi-agent Markov decision process (MDP) and introduced a multi-agent soft actor-critic (MAgSAC) algorithm. This algorithm prevents the wastage of scarce resources by intelligently activating and deactivating virtual network function (VNF) instances, thereby balancing the allocation process. Our approach aims to optimize overall utility, balancing trade-offs between revenue, energy consumption costs, and latency. We evaluated our method, MAgSAC, through simulations, comparing it with the following six benchmark schemes: MAA3C, SACT, DDPG, S2Vec, Random, and Greedy. The results demonstrate that our approach, MAgSAC, optimizes utility by 30%, minimizes energy consumption costs by 12.4%, and reduces execution time by 21.7% compared to the closest related multi-agent approach named MAA3C.

Ventral frontostriatal circuitry mediates the computation of reinforcement from symbolic gains and losses.

Reinforcement learning (RL), particularly in primates, is often driven by symbolic outcomes. However, it is usually studied with primary reinforcers. To examine the neural mechanisms underlying learning from symbolic outcomes, we trained monkeys on a task in which they learned to choose options that led to gains of tokens and avoid choosing options that led to losses of tokens. We then recorded simultaneously from the orbitofrontal cortex (OFC), ventral striatum (VS), amygdala (AMY), and mediodorsal thalamus (MDt). We found that the OFC played a dominant role in coding token outcomes and token prediction errors. The other areas contributed complementary functions, with the VS coding appetitive outcomes and the AMY coding the salience of outcomes. The MDt coded actions and relayed information about tokens between the OFC and VS. Thus, the OFC leads the processing of symbolic RL in the ventral frontostriatal circuitry.

Using recurrent neural network to estimate irreducible stochasticity in human choice behavior.

Theoretical computational models are widely used to describe latent cognitive processes. However, these models do not equally explain data across participants, with some individuals showing a bigger predictive gap than others. In the current study, we examined the use of theory-independent models, specifically recurrent neural networks (RNNs), to classify the source of a predictive gap in the observed data of a single individual. This approach aims to identify whether the low predictability of behavioral data is mainly due to noisy decision-making or misspecification of the theoretical model. First, we used computer simulation in the context of reinforcement learning to demonstrate that RNNs can be used to identify model misspecification in simulated agents with varying degrees of behavioral noise. Specifically, both prediction performance and the number of RNN training epochs (i.e., the point of early stopping) can be used to estimate the amount of stochasticity in the data. Second, we applied our approach to an empirical dataset where the actions of low IQ participants, compared with high IQ participants, showed lower predictability by a well-known theoretical model (i.e., Daw's hybrid model for the two-step task). Both the predictive gap and the point of early stopping of the RNN suggested that model misspecification is similar across individuals. This led us to a provisional conclusion that low IQ subjects are mostly noisier compared to their high IQ peers, rather than being more misspecified by the theoretical model. We discuss the implications and limitations of this approach, considering the growing literature in both theoretical and data-driven computational modeling in decision-making science.

Development and systematic review of connection techniques for RC Precast structural elements: Beam and Column Connection.

Precast reinforcement concrete (RC) structures have attracted increasing attention in the global construction industry. They offer advantages such as reduced construction time, improved quality, and sustainability. However, their seismic performance and construction pose unique challenges. This study comprehensively reviewed and systematically analyzed the nodal connection techniques of RC precast structures. Using a data-driven approach combining quantitative and qualitative analyses, relevant literature was collected from the Web of Science database based on specific search criteria. Historical and recent trends in the scientific landscape were visualized, and citation networks were analyzed. In addition, the study reviewed different types of beam-column connections, which is a significant research focus. The results indicate that although various types of nodal connections demonstrate good seismic performance in experiments, they still face challenges of complexity and long-term maintenance in actual construction.

HMM for discovering decision-making dynamics using reinforcement learning experiments.

Major depressive disorder (MDD), a leading cause of years of life lived with disability, presents challenges in diagnosis and treatment due to its complex and heterogeneous nature. Emerging evidence indicates that reward processing abnormalities may serve as a behavioral marker for MDD. To measure reward processing, patients perform computer-based behavioral tasks that involve making choices or responding to stimulants that are associated with different outcomes, such as gains or losses in the laboratory. Reinforcement learning (RL) models are fitted to extract parameters that measure various aspects of reward processing (e.g. reward sensitivity) to characterize how patients make decisions in behavioral tasks. Recent findings suggest the inadequacy of characterizing reward learning solely based on a single RL model; instead, there may be a switching of decision-making processes between multiple strategies. An important scientific question is how the dynamics of strategies in decision-making affect the reward learning ability of individuals with MDD. Motivated by the probabilistic reward task within the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study, we propose a novel RL-HMM (hidden Markov model) framework for analyzing reward-based decision-making. Our model accommodates decision-making strategy switching between two distinct approaches under an HMM: subjects making decisions based on the RL model or opting for random choices. We account for continuous RL state space and allow time-varying transition probabilities in the HMM. We introduce a computationally efficient Expectation-maximization (EM) algorithm for parameter estimation and use a nonparametric bootstrap for inference. Extensive simulation studies validate the finite-sample performance of our method. We apply our approach to the EMBARC study to show that MDD patients are less engaged in RL compared to the healthy controls, and engagement is associated with brain activities in the negative affect circuitry during an emotional conflict task.

Preparation of novel hierarchical catalysts by simultaneous generation of ß-zeolite and mesoporous silica for catalytic cracking.

The gel skeletal reinforcement (GSR) method was applied at the preparation stage of ß-zeolite to prepare a novel hierarchical catalyst. A solution of hexamethyldisiloxane (HMDS) and acetic anhydride, a GSR reagent, was added to the mixture of colloidal silica, sodium aluminate, tetraethylammonium hydroxide, sodium hydroxide and water, and successive aging and hydrothermal treatment gave microporous ß-zeolite surrounded by mesoporous silica like core-shell structure. Its properties were characterized by XRD, nitrogen adsorption and desorption, NH3-TPD, TEM, and TG-DTA measurements, and further characteristics of the catalysts produced were clarified by the catalytic cracking of n-dodecane. The hierarchical structure of microporous zeolite and mesoporous silica was shown from GSR-2.9HS-H-Beta to GSR-3.2HS-H-Beta, where the molar ratio of HMDS and silica source of ß-zeolite was 2.9~3.2:100. It was found that in the catalytic cracking of n-dodecane, the relative activity (the conversion per the amount of zeolite crystals) increased with the increase in mesopore volume and surface area. The result indicated that the introduction of mesopores was effective even in catalytic cracking of small molecule of n-dodecane.

Six-year analysis of 30-day post-operative leaks for primary sleeve gastrectomy: a MBSAQIP database study.

BACKGROUND: Sleeve gastrectomy is the most performed bariatric surgery. Post-operative gastric sleeve leaks, although rare, are dreaded complications. This study aims to perform an updated investigation of the factors associated with sleeve leaks. METHODS: This retrospective cohort study analyzed 692,554 cases from the MBSAQIP database (2016-2021) with CPT code 43,775 for primary sleeve gastrectomy. We excluded emergency operations, conversions/revisions, endoscopic interventions, patient with prior foregut surgery, and open operations. Multivariate logistic regression analysis (STATA version 15) was performed to identify factors associated with sleeve gastrectomy leaks. RESULTS: Out of 692,554 patients, 600,910 (86.77%) patients underwent laparoscopic sleeve gastrectomy, and 91,644 (13.23%) patients underwent robotic sleeve gastrectomy. 1179 (0.17%) developed leaks within 30 days; 177(0.19%) were in the robotic group and 1002 (0.17%) in the laparoscopic group with no significant difference in leak rates between two groups on multivariate analysis. Black patients had lower odds of having leaks as compared to white patients (Odds Ratio (OR): 0.68 (0.56-0.82); p < 0.01). Hispanic patients had lower odds of having leak as compared to non-Hispanics. Factors associated with higher leak odds (p < 0.05) included hypertension, GERD, smoking, immunosuppression, increased operating time, and albumin < 3.5 g/dl. Higher odds of leaks were observed in years 2016-2019 vs 2020-2021 (OR: 1.44 (1.25-1.65), p < 0.01). Higher odds of leak in operations with general surgeons compared to bariatric surgeons was found (OR: 1.46 (1.04-2.02), p = 0.02); observed only on robotic group on subgroup analysis (OR: 2.2 (1.2-4.2), p = 0.02). Staple line reinforcement, oversewing, and performance of leak test showed no differences in leak rate. Bougie size and distance from pylorus were not associated with changes in leak rate. CONCLUSION: This study provides updated insights into the factors associated with sleeve leaks, reinforcing information gained from prior studies. A higher association of leak among general surgeons could represent a learning curve for new robotic general surgeons. The overall decreasing trend for gastric sleeve leak is encouraging and may be a sign of improved techniques.

PelviNet: A Collaborative Multi-agent Convolutional Network for Enhanced Pelvic Image Registration.

PelviNet introduces a groundbreaking multi-agent convolutional network architecture tailored for enhancing pelvic image registration. This innovative framework leverages shared convolutional layers, enabling synchronized learning among agents and ensuring an exhaustive analysis of intricate 3D pelvic structures. The architecture combines max pooling, parametric ReLU activations, and agent-specific layers to optimize both individual and collective decision-making processes. A communication mechanism efficiently aggregates outputs from these shared layers, enabling agents to make well-informed decisions by harnessing combined intelligence. PelviNet's evaluation centers on both quantitative accuracy metrics and visual representations to elucidate agents' performance in pinpointing optimal landmarks. Empirical results demonstrate PelviNet's superiority over traditional methods, achieving an average image-wise error of 2.8 mm, a subject-wise error of 3.2 mm, and a mean Euclidean distance error of 3.0 mm. These quantitative results highlight the model's efficiency and precision in landmark identification, crucial for medical contexts such as radiation therapy, where exact landmark identification significantly influences treatment outcomes. By reliably identifying critical structures, PelviNet advances pelvic image analysis and offers potential enhancements for broader medical imaging applications, marking a significant step forward in computational healthcare.

Exploring the suitability of cannabis use with next-day responsibilities: A behavioral-economic and qualitative study.

Cannabis demand is sensitive to next-day responsibilities, such as job interviews; however, it is unclear how demand is affected by non-work-related responsibilities and how reported compatibility of cannabis use (i.e., how suitable one perceives cannabis use to be in a situation) influences demand. This study examined the effects of a range of responsibilities on cannabis demand in a crowdsourced sample of adults who smoked cannabis at least monthly (n = 177; 78% White; 47% women; mean age = 36.52). Participants completed hypothetical marijuana purchase tasks asking how much cannabis they would consume at escalating prices in the context of no responsibilities and next-day responsibilities spanning work, leisure, and caregiving. Cannabis demand was significantly reduced in all responsibility conditions (ps < .008; ds .28-.94), with the largest reductions for the job interview and caring-for-kids conditions. Higher ratings of suitability of cannabis use in each situation were correlated with higher demand. Finally, a qualitative thematic analysis characterized why cannabis use was considered suitable or unsuitable with each responsibility. These results suggest that demand is sensitive to next-day responsibilities. However, these effects are not uniform, and future research is needed to examine these individual differences and the timing of upcoming responsibilities.

Intraoperative Acetabular Fractures in Primary Total Hip Arthroplasty Management and Functional Outcomes.

PURPOSE: Intraoperative acetabular fracture (IAF) is a non-common complication of primary total hip arthroplasty (THA). Despite the prevalence of intraoperative periprosthetic fractures are increasing, little has been written about this type of fracture. The main objective is to analyze possible risk factors, treatment options and functional outcomes associated with IAF. METHODS: Between 2006 and 2020, 4 senior arthroplasty surgeons performed 5540 uncemented primary THA. We reviewed our Total Joint Registry and found 18 cases with an IAF. We analyzed demographic factors, medical history, preoperative diagnose, acetabular cups designs, anatomic location of the fracture, treatment, associated complications and functional outcomes. The minimum duration of follow-up was 12 months. RESULTS: The prevalence of an IAF was 0,3%. All the acetabular cups were hemispherical modular. The most frequent acetabular cup associated with an IAF was the CSF Plus (JRI). In two cases the acetabular components were judged to be stable and no additional treatment was done. In the other sixteen patients, various surgical procedures were carried out. Almost 30% of patients that sustained an IAF had some complication during their follow up. Moreover, poor functionality outcomes were obtained (12.1 ± 4.1). in the final follow up accordance to Postel Merle d'Aubingé score. CONCLUSION: Although IAF is a rare complication of THA, maintaining a high index of suspicion is important as they can be difficult to identify. Still with an adequate early treatment they have poor functionality and high risk of associated complications.