Automated facial landmark measurement using machine learning: A feasibility study.

STATEMENT OF PROBLEM: Information regarding facial landmark measurement using machine learning (ML) techniques in prosthodontics is lacking. PURPOSE: The objective of this study was to evaluate and compare the reliability, validity, and accuracy of facial anthropological measurements using both manual and ML landmark detection techniques. MATERIAL AND METHODS: Two-dimensional (2D) frontal full-face photographs of 50 men and 50 women were made. The interpupillary width (IPW), interlateral canthus width (LCW), intermedial canthus width (MCW), interalar width (IAW), and intercommissural width (ICW) were measured on 2D digital images using manual and ML methods. The automated measurements were recorded using a programming language (Python), and a convolutional neural network (CNN) model was trained to detect human facial landmarks. The obtained data from the manual and ML methods were analyzed using intraclass correlation coefficients (ICCs), the paired sample t test, Bland-Altman plots, and the Pearson correlation analysis (α=.05). RESULTS: Intrarater and interrater reliability values were greater than 0.90, indicating excellent reliability. The mean difference between the manual and ML measurements of IPW, MCW, IAW, and ICW was 0.02 mm, while it was 0.01 mm for LCW. No statistically significant differences were found between the measurements obtained by the manual and ML methods (P>.05). Highly significant positive correlations (P<.001) were obtained between the results of the manual and ML methods: (r=0.996[IPW], r=0.977[LCW], r=0.944[MCW], r=0.965[IAW], and r=0.997[ICW]). CONCLUSIONS: In the field of prosthodontics, the use of ML methods provides a reliable alternative to manual digital techniques for carrying out facial anthropometric measurements.

In-silico approaches to assessing multiple high-level drug-drug and drug-disease adverse drug effects.

INTRODUCTION: Pharmacovigilance plays a pivotal role in monitoring adverse events (AEs) related to chemical substances in human/animal populations. With increasing spontaneous-reporting systems, researchers turned to in-silico approaches to efficiently analyze drug safety profiles. Here, we review in-silico methods employed for assessing multiple drug-drug/drug-disease AEs covered by comparative analyses and visualization strategies. AREAS COVERED: Disproportionality, involving multi-stage statistical methodologies and data processing, identifies safety signals among drug-AE pairs. By stratifying data based on disease indications/demographics, researchers address confounders and assess drug safety. Comparative analyses, including clustering techniques and visualization techniques, assess drug similarities, patterns, and trends, calculate correlations, and identify distinct toxicities. Furthermore, we conducted a thorough Scopus search on 'pharmacovigilance,' yielding 5,836 publications spanning 2003 to 2023. EXPERT OPINION: Pharmacovigilance relies on diverse data sources, presenting challenges in the integration of in-silico approaches and requiring compliance with regulations and AI adoption. Systematic use of statistical analyses enables identifications of potential risks with drugs. Frequentist and Bayesian methods are used in disproportionalities, each with its strengths and weaknesses. Integration of pharmacogenomics with pharmacovigilance enables personalized medicine, with AI further enhancing patient engagement. This multidisciplinary approach holds promise, improving drug efficacy and safety, and should be a core mission of One-Health studies.

Machine learning model to predict the width of maxillary central incisor from anthropological measurements.

PURPOSE: To improve smile esthetics, clinicians should comprehensively analyze the face and ensure that the sizes selected for the maxillary anterior teeth are compatible with the available anthropological measurements. The inter commissural (ICW), interalar (IAW), intermedial-canthus (MCW), interlateral-canthus (LCW), and interpupillary (IPW) widths are used to determine the width of maxillary central incisors (CW). The aim of this study was to develop an automated approach using machine learning (ML) algorithms to predict central incisor width in a young Turkish population using anthropological measurements. This automation can contribute to digital dentistry and clinical decision-making. METHODS: In the initial phase of this cross-sectional study, several ML regression models-including multiple linear regression (MLR), multi-layer-perceptron (MLP), decision-tree (DT), and random forest (RF) models-were validated to confirm the central width prediction accuracy. Datasets containing only male and female measurements, as well as combined were considered for ML model implementation, and the performance of each model was evaluated for an unbiased population dataset. RESULTS: Compared with the other algorithms, the RF algorithm showed improved performance for all cases, with an accuracy of 96%, which represents the percentage of correct predictions. The plot reveals the applicability of the RF model in predicting the CW from anthropological measurements irrespective of the candidate's sex. CONCLUSIONS: These results demonstrated the possibility of predicting central incisor widths based on anthropometric measurements using ML models. The accurate central incisor width prediction from these trials also indicates the applicability of the proposed model to be deployed for enhanced clinical decision-making.

Fretting-corrosion Apparatus with Low Magnitude Micro-motion (≤5 µm): Development and Preliminary Outcome.

Fretting-corrosion is one of the failure processes in many applications, including biomedical implants. For example, the modern design of hip implants with multiple components offers better flexibility and inventory storage. However, it will trigger the fretting at the implant interfaces with a small displacement amplitude (< 5 µm) and usually in a partial slip region. Although many studies have been reported on the fretting, they have high displacement amplitude and are in the gross slip region. It is imperative to have an apparatus to overcome such limitations, specifically for hip implant applications. Therefore, this study describes the development of a fretting-corrosion apparatus with low micro-motion (≤ 5 µm) that can simultaneously monitor the corrosion process. Initial experiments with Ti6Al4V-Ti6Al4V in 0.9% saline, Ti6Al4V-Ti6Al4V in bovine calf serum (BCS), and ZrO2-Ti6Al4V in BCS were conducted to validate the system. As a result, the fretting regime of all groups remained partially slip region throughout the 3600 cycles, and the possible failure mechanisms are proposed in this manuscript.

Advancements in Intraoperative Near-Infrared Fluorescence Imaging for Accurate Tumor Resection: A Promising Technique for Improved Surgical Outcomes and Patient Survival.

Clear surgical margins for solid tumor resection are essential for preventing cancer recurrence and improving overall patient survival. Complete resection of tumors is often limited by a surgeon's ability to accurately locate malignant tissues and differentiate them from healthy tissue. Therefore, techniques or imaging modalities are required that would ease the identification and resection of tumors by real-time intraoperative visualization of tumors. Although conventional imaging techniques such as positron emission tomography (PET), computed tomography (CT), magnetic resonance imaging (MRI), or radiography play an essential role in preoperative diagnostics, these cannot be utilized in intraoperative tumor detection due to their large size, high cost, long imaging time, and lack of cancer specificity. The inception of several imaging techniques has paved the way to intraoperative tumor margin detection with a high degree of sensitivity and specificity. Particularly, molecular imaging using near-infrared fluorescence (NIRF) based nanoprobes provides superior imaging quality due to high signal-to-noise ratio, deep penetration to tissues, and low autofluorescence, enabling accurate tumor resection and improved survival rates. In this review, we discuss the recent developments in imaging technologies, specifically focusing on NIRF nanoprobes that aid in highly specific intraoperative surgeries with real-time recognition of tumor margins.

Early Predicting Tribocorrosion Rate of Dental Implant Titanium Materials Using Random Forest Machine Learning Models.

Early detection and prediction of bio-tribocorrosion can avert unexpected damage that may lead to secondary revision surgery and associated risks of implantable devices. Therefore, this study sought to develop a state-of-the-art prediction technique leveraging machine learning(ML) models to classify and predict the possibility of mechanical degradation in dental implant materials. Key features considered in the study involving pure titanium and titanium-zirconium (zirconium = 5, 10, and 15 in wt%) alloys include corrosion potential, acoustic emission(AE) absolute energy, hardness, and weight-loss estimates. ML prototype models deployed confirms its suitability in tribocorrosion prediction with an accuracy above 90%. Proposed system can evolve as a continuous structural-health monitoring as well as a reliable predictive modeling technique for dental implant monitoring.

Development of machine learning algorithms to estimate maximum residue limits for veterinary medicines.

Establishing maximum-residue limits (MRLs) for veterinary medicine helps to protect the human food supply. Guidelines for establishing MRLs are outlined by regulatory authorities that drug sponsors follow in each country. During the drug approval process, residue limits are targeted for specific animal species and matrices. Therefore, MRLs are commonly not established for other species. This study demonstrates unestablished MRLs can be reliably predicted for under-represented food commodity groups using machine learning (ML). Classification methods with imbalanced data were used to analyze MRL data from multiple countries by implementing resampling techniques in different ML classifiers. Afterward, we developed and evaluated a data-mining method for predicting unestablished MRLs. Seven different ML classifiers such as support vector classifier, multi-layer perceptron (MLP), random forest, decision tree, k-neighbors, Gaussian NB, and AdaBoost have been selected in this baseline study. Among these, the neural network MLP classifier reliably scored the highest average-weighted F1 score (accuracy >99% with markers and ≈88% without markets) in predicting unestablished MRLs. This provides the first study to apply ML algorithms in regulatory food animal medicine. By predicting and estimating MRLs, we can potentially decrease the use and cost of live animals and the overall research burden of determining new MRLs.

A Review on Saliva-Based Health Diagnostics: Biomarker Selection and Future Directions.

The human body has a unique way of saying when something is wrong with it. The molecules in the body fluids can be helpful in the early detection of diseases by enabling health and preventing disease progression. These biomarkers enabling better healthcare are becoming an extensive area of research interest. Biosensors that detect these biomarkers are becoming the future, especially Point Of Care (POC) biosensors that remove the need to be physically present in the hospital. Detection of complex and systemic diseases using biosensors has a long way to go. Saliva-based biosensors are gaining attention among body fluids due to their non-invasive collection and ability to detect periodontal disease and identify systemic diseases. The possibility of saliva-based diagnostic biosensors has gained much publicity, with companies sending home kits for ancestry prediction. Saliva-based testing for covid 19 has revealed effective clinical use and relevance of the economic collection. Based on universal biomarkers, the detection of systemic diseases is a booming research arena. Lots of research on saliva-based biosensors is available, but it still poses challenges and limitations as POC devices. This review paper talks about the relevance of saliva and its usefulness as a biosensor. Also, it has recommendations that need to be considered to enable it as a possible diagnostic tool.

An Automated Customizable Live Web Crawler for Curation of Comparative Pharmacokinetic Data: An Intelligent Compilation of Research-Based Comprehensive Article Repository.

Data curation has significant research implications irrespective of application areas. As most curated studies rely on databases for data extraction, the availability of data resources is extremely important. Taking a perspective from pharmacology, extracted data contribute to improved drug treatment outcomes and well-being but with some challenges. Considering available pharmacology literature, it is necessary to review articles and other scientific documents carefully. A typical method of accessing articles on journal websites is through long-established searches. In addition to being labor-intensive, this conventional approach often leads to incomplete-content downloads. This paper presents a new methodology with user-friendly models to accept search keywords according to the investigators' research fields for metadata and full-text articles. To accomplish this, scientifically published records on the pharmacokinetics of drugs were extracted from several sources using our navigating tool called the Web Crawler for Pharmacokinetics (WCPK). The results of metadata extraction provided 74,867 publications for four drug classes. Full-text extractions performed with WCPK revealed that the system is highly competent, extracting over 97% of records. This model helps establish keyword-based article repositories, contributing to comprehensive databases for article curation projects. This paper also explains the procedures adopted to build the proposed customizable-live WCPK, from system design and development to deployment phases.

Advanced Electrochemical Reamer (EC-Reamer) for Root Canal Treatment.

OBJECTIVE: According to the American Association of Endodontists (AAE), 22 million endodontic procedures have been performed annually. Root canal treatment is needed to prevent infection and restore function when a tooth is severely infected or decayed. This procedure is the only way to preserve the natural tooth and avoid artificial replacement (implant, denture, etc.). The current study aims to develop an electrochemical reamer (EC-Reamer or EC-R) that can help to disinfect the canal system and thus improve the success rate of root canal treatment. METHODS: The COMSOL Multiphysics software was utilized to simulate the experimental setup and confirm the current flow in the electrolyte. The benchtop experimental approach follows a specific electrochemical protocol, (i) open circuit potential to monitor the electrochemical stabilization and (ii) potentiostatic scan at -9.0 V as the treatment stage. Identification of feasible reference electrode (RE) and insulation material for the exploratory benchtop studies considered platinum (Pt) and gold (Au) wire as the REs and hot melt adhesive (HMA) and liquid tape as the insulation materials. The antimicrobial effects of EC-R were analysed using Enterococcus faecalis (E. faecalis). One-way ANOVA with the Tukey post hoc test and a significance level of P<0.05 is used to compare the groups with an experimental duration of 60 seconds. RESULTS: The findings showed that magnitude and current fluctuations created by Pt wire are promising when compared to Au wire, while Pt-HMA pair is chosen considering Pt's good electrochemical inertness and HMA's easy handling, availability, and non-hazardous features. The use of potentiostatic duration of 1 s and 3 s resulted in >99.99% E. faecalis reduction. Duration at 5 s and above resulted in a total bacterial kill. Statistical analysis confirmed a significant difference among the groups tested with commercial and custom-built potentiostats. CONCLUSION: The outcome provided preliminary data for developing an EC-R prototype to enhance the antimicrobial effect during root canal treatment potentially. (EEJ-2022-01-04).

Artificial intelligence and machine learning as a viable solution for hip implant failure diagnosis-Review of literature and in vitro case study.

The digital health industry is experiencing fast-paced research which can provide digital care programs and technologies to enhance the competence of healthcare delivery. Orthopedic literature also confirms the applicability of artificial intelligence (AI) and machine learning (ML) models to medical diagnosis and clinical decision-making. However, implant monitoring after primary surgery often happens with a wellness visit or when a patient complains about it. Neglecting implant design and other technical errors in this scenario, unmonitored circumstances, and lack of post-surgery monitoring may ultimately lead to the implant system's failure and leave us with the only option of high-risk revision surgery. Preventive maintenance seems to be a good choice to identify the onset of an irreversible prosthesis failure. Considering all these aspects for hip implant monitoring, this paper explores existing studies linking ML models and intelligent systems for hip implant diagnosis. This paper explores the feasibility of an alternative continuous monitoring technique for post-surgery implant monitoring backed by an in vitro ML case study. Tribocorrosion and acoustic emission (AE) data are considered based on their efficacy in determining irreversible alteration of implant material to prevent total failures. This study also facilitates the relevance of developing an artificially intelligent implant monitoring methodology that can function with daily patient activities and how it can influence the digital orthopedic diagnosis. AI-based non-invasive hip implant monitoring system enabling point-of-care testing.

Total hip replacement monitoring: numerical models for the acoustic emission technique.

Any mechanical instability associated with total hip replacement (THR) excites elastic waves with different frequencies and propagates through the surrounding biological layers. Using the acoustic emission (AE) technique as a THR monitoring tool provides valuable information on structural degradations associated with these implants. However, several factors can compromise the reliability of the signals detected by AE sensors, such as attenuation of the detected signal due to the presence of biological layers in the human body between prosthesis (THR) and AE sensor. The main objective of this study is to develop a numerical model of THR that evaluates the impact of biological layer thicknesses on AE signal propagation. Adipose tissue thickness, which varies the most between patients, was modeled at two different thicknesses 40 mm and 70 mm, while the muscle and skin thicknesses were kept to a constant value. The proposed models were tested at different micromotions of 2 µm, 15-20 µm at modular junctions, and different frequencies of 10-60 kHz. Attenuation of signal is observed to be more with an increase in the selected boundary conditions along with an increase in distance the signals propagate through. Thereby, the numerical observations drawn on each interface helped to simulate the effect of tissue thicknesses and their impact on the attenuation of elastic wave propagation to the AE receiver sensor.

Dynamic microfluidic bioreactor-Hip simulator (DMBH) system for implant toxicity monitoring.

The generation of degradation products (DPs) like ions and organo-metallic particles from corroding metallic implants is an important healthcare concern. These DPs generate local and systemic toxicity. The impact on local toxicity is well documented, however, little is known about systemic toxicity. This is mainly due to the limited scope of the current microtiter plate-based (static) toxicity assay techniques. These methods do not mimic the systemic (dynamic) conditions. In this study, it is hypothesized that DPs incubated with cells in static conditions might provide improper systemic toxicity results, as there is no movement mimicking the blood circulation around cells. This study reports the development of a three-chambered prototype microfluidic system connected to the operational hip implant simulator to test the cellular response induced by the DPs. This setup is called a dynamic microfluidic bioreactor-hip simulator system. We hypothesize that a dynamic microfluidic system will provide a realistic toxicology response induced by DPs than a static cell culture plate. To prove the hypothesis, Neuro2a (N2a) cells were used as representative cells to study systemic neurotoxicity by the implant DPs. The microfluidic bioreactor system was validated by comparing the cell toxicity against the traditional static system and using COMSOL modeling for media flow with DPs. The hip implant simulator used in this study was a state-of-the-art sliding hip simulator developed in our lab. The results suggested that static toxicity was significantly more compared to dynamic microfluidic-based toxicity. The newly developed DMBH system tested for in situ systemic toxicity on N2a cells and demonstrated very minimum toxicity level (5.23%) compared to static systems (31.16%). Thus, the new DMBH system is an efficient tool for in situ implant metal systemic toxicity testing.

Prediction of tribocorrosion processes in titanium-based dental implants using acoustic emission technique: Initial outcome.

The use of dental implants is growing rapidly for the last few decades and Ti-based dental implants are a commonly used prosthetic structure in dentistry. Recently, the combined effect of corrosion and wear, called tribocorrosion, is considered as a major driving process in the early failure of dental implants. However, no previous study has reported the prediction of tribocorrosion processes in advance. Therefore, this study is a novel investigation on how the acoustic emission (AE) technique can predict tribocorrosion processes in commercially-pure titanium (cpTi) and titanium-zirconium (TiZr) alloys. In this study, tribocorrosion tests were performed under potentiostatic conditions and AE detection system associated with it captures AE data. Current evolution and friction coefficient data obtained from the potentiostatic evaluations were compared with AE absolute energy showcased the same data interpretation of tribocorrosion characteristics. Other AE data such as duration, count, and amplitude, matched more closely with other potentiostatic corrosion evaluations and delivered more promising results in the detection of tribocorrosion. Hence, AE can be consider as a tool for predicting tribocorrosion in dental implants. Experimental results also reveal Ti5Zr as one of the most appropriate dental implant materials while exposing Ti10Zr's lower effectiveness to withstand in the simulated oral environment.

Non-invasive early detection of failure modes in total hip replacements (THR) via acoustic emission (AE).

Total hip replacements (THR) are becoming an common orthopedic surgucal procedure in the United States (332 K/year in 2017) to relieve pain and improve the mobility of those that are affected by osteoarthritis, ankylosing spondylitis, or injury. However, complications like tribocorrosion, or material degradation due to friction and corrosion, may result in THR failure. Unfortunately, few strategies to non-invasively diagnose early-stage complications are reported in literature, leading to implant complications being detected after irreversible damage. Therefore, the main objective of this study proposes the utilization of acoustic emission (AE) to continuously monitor implant materials, CoCrMo and Ti6Al4V, and identify degradations formed during cycles of sleeping, standing, and walking by correlating them to potential and friction coefficient behavior. AE activity detected from the study correlates with the friction coefficient and open-circuit potential observed during recreated in-vitro standing, walking, and sleeping cycles. It was found that the absolute energy level obtained from AE increased as the friction coefficient increased, potential decreased, and wear volume loss increased. Through the results, higher friction coefficient and AE activity were observed in Ti6Al4V alloys while there was also a significant drop in potential, indicating increased tribocorrosion activity. Therefore, AE can be utilized to predict material degradations as a non-invasive method based on the severity of abnormality of the absolute energy and hits emitted. The correlation between potential, friction coefficient, and AE activity was further confirmed through profilometry which showed more material degradation in Ti6Al4V than CoCrMo. Through these evaluations, it was demonstrated that AE could be utilized to identify the deformations and failure modes of implant materials caused by tribocorrosion.

Activation of tyrosine hydroxylase by intermittent hypoxia: involvement of serine phosphorylation.

Regulation of tyrosine hydroxylase (TH) by intermittent hypoxia (IH) was investigated in rat pheochromocytoma 12 (PC-12) cells by exposing them to alternating cycles of hypoxia (1% O2, 15 s) and normoxia (21% O2, 3 min) for up to 60 cycles; controls were exposed to normoxia for a similar duration. IH exposure increased dopamine content and TH activity by approximately 42 and approximately 56%, respectively. Immunoblot analysis revealed that comparable levels of TH protein were expressed in normoxic and IH cells. Removal of TH-bound catecholamines and in vitro phosphorylation of TH in cell-free extracts by the catalytic subunit of protein kinase A (PKA) increased TH activity in normoxic but not in IH cells, suggesting possible induction of TH phosphorylation and removal of endogenous inhibition of TH by IH. To assess the role of serine phosphorylation in IH-induced TH activation, TH immunoprecipitates and extracts derived from normoxic and IH cells were probed with anti-phosphoserine and anti-phospho-TH (Ser-40) antibody, respectively. Compared with normoxic cells, total serine and Ser-40-specific phosphorylation of TH were increased in IH cells. IH-induced activation of TH and the increase in total serine and Ser-40-specific phosphorylation of TH were inhibited by Ca2+/calmodulin-dependent protein kinase (CaMK) and PKA-specific inhibitors but not by inhibitors of the extracellular signal-regulated protein kinase pathway, suggesting that IH activates TH in PC-12 cells via phosphorylation of serine residues including Ser-40, in part, by CaMK and PKA. Our results also suggest that IH-induced phosphorylation of TH facilitates the removal of endogenous inhibition of TH, leading to increased synthesis of dopamine.