Clinical Utility of an Artificial Intelligence Radiomics-based Tool for Risk Stratification of Pulmonary Nodules.

BACKGROUND: Clinical utility data on pulmonary nodule (PN) risk stratification biomarkers are lacking. We aimed to determine the incremental predictive value and clinical utility of using an artificial intelligence (AI) radiomics-based computer-aided diagnosis (CAD) tool in addition to routine clinical information to risk stratify PNs among real-world patients. METHODS: We performed a retrospective cohort study of patients with PNs who underwent lung biopsy. We collected clinical data and used a commercially available AI radiomics-based CAD tool to calculate a Lung Cancer Prediction (LCP) score. We developed logistic regression models to evaluate a well-validated clinical risk prediction model (the Mayo Clinic model) with and without the LCP score (Mayo vs Mayo + LCP) using area under the curve (AUC), risk stratification table, and standardized net benefit analyses. RESULTS: Among the 134 patients undergoing PN biopsy, cancer prevalence was 61%. Addition of the radiomics-based LCP score to the Mayo model was associated with increased predictive accuracy (likelihood ratio test, P = .012). The AUCs for the Mayo and Mayo + LCP models were 0.58 (95% CI, 0.48-0.69) and 0.65 (95% CI, 0.56-0.75), respectively. At the 65% risk threshold, the Mayo + LCP model was associated with increased sensitivity (56% vs 38%; P = .019), similar false positive rate (33% vs 35%; P = .8), and increased standardized net benefit (18% vs -3.3%) compared to the Mayo model. CONCLUSIONS: Use of a commercially available AI radiomics-based CAD tool as a supplement to clinical information improved PN cancer risk prediction and may result in clinically meaningful changes in risk stratification.

Automated monitoring of tooth wear progression using AI on intraoral scans.

OBJECTIVES: This study aimed to develop and evaluate a fully automated method for visualizing and measuring tooth wear progression using pairs of intraoral scans (IOSs) in comparison with a manual protocol. METHODS: Eight patients with severe tooth wear progression were retrospectively included, with IOSs taken at baseline and 1-year, 3-year, and 5-year follow-ups. For alignment, the automated method segmented the arch into separate teeth in the IOSs. Tooth pair registration selected tooth surfaces that were likely unaffected by tooth wear and performed point set registration on the selected surfaces. Maximum tooth profile losses from baseline to each follow-up were determined based on signed distances using the manual 3D Wear Analysis (3DWA) protocol and the automated method. The automated method was evaluated against the 3DWA protocol by comparing tooth segmentations with the Dice-Sørensen coefficient (DSC) and intersection over union (IoU). The tooth profile loss measurements were compared with regression and Bland-Altman plots. Additionally, the relationship between the time interval and the measurement differences between the two methods was shown. RESULTS: The automated method completed within two minutes. It was very effective for tooth instance segmentation (826 teeth, DSC = 0.947, IoU = 0.907), and a correlation of 0.932 was observed for agreement on tooth profile loss measurements (516 tooth pairs, mean difference = 0.021mm, 95% confidence interval = [-0.085, 0.138]). The variability in measurement differences increased for larger time intervals. CONCLUSIONS: The proposed automated method for monitoring tooth wear progression was faster and not clinically significantly different in accuracy compared to a manual protocol for full-arch IOSs. CLINICAL SIGNIFICANCE: General practitioners and patients can benefit from the visualization of tooth wear, allowing quantifiable and standardized decisions concerning therapy requirements of worn teeth. The proposed method for tooth wear monitoring decreased the time required to less than two minutes compared with the manual approach, which took at least two hours.

Oral mucosal lesions triage via YOLOv7 models.

BACKGROUND/PURPOSE: The global incidence of lip and oral cavity cancer continues to rise, necessitating improved early detection methods. This study leverages the capabilities of computer vision and deep learning to enhance the early detection and classification of oral mucosal lesions. METHODS: A dataset initially consisting of 6903 white-light macroscopic images collected from 2006 to 2013 was expanded to over 50,000 images to train the YOLOv7 deep learning model. Lesions were categorized into three referral grades: benign (green), potentially malignant (yellow), and malignant (red), facilitating efficient triage. RESULTS: The YOLOv7 models, particularly the YOLOv7-E6, demonstrated high precision and recall across all lesion categories. The YOLOv7-D6 model excelled at identifying malignant lesions with notable precision, recall, and F1 scores. Enhancements, including the integration of coordinate attention in the YOLOv7-D6-CA model, significantly improved the accuracy of lesion classification. CONCLUSION: The study underscores the robust comparison of various YOLOv7 model configurations in the classification to triage oral lesions. The overall results highlight the potential of deep learning models to contribute to the early detection of oral cancers, offering valuable tools for both clinical settings and remote screening applications.

The role of information systems in emergency department decision-making-a literature review.

OBJECTIVES: Healthcare providers employ heuristic and analytical decision-making to navigate the high-stakes environment of the emergency department (ED). Despite the increasing integration of information systems (ISs), research on their efficacy is conflicting. Drawing on related fields, we investigate how timing and mode of delivery influence IS effectiveness. Our objective is to reconcile previous contradictory findings, shedding light on optimal IS design in the ED. MATERIALS AND METHODS: We conducted a systematic review following PRISMA across PubMed, Scopus, and Web of Science. We coded the ISs' timing as heuristic or analytical, their mode of delivery as active for automatic alerts and passive when requiring user-initiated information retrieval, and their effect on process, economic, and clinical outcomes. RESULTS: Our analysis included 83 studies. During early heuristic decision-making, most active interventions were ineffective, while passive interventions generally improved outcomes. In the analytical phase, the effects were reversed. Passive interventions that facilitate information extraction consistently improved outcomes. DISCUSSION: Our findings suggest that the effectiveness of active interventions negatively correlates with the amount of information received during delivery. During early heuristic decision-making, when information overload is high, physicians are unresponsive to alerts and proactively consult passive resources. In the later analytical phases, physicians show increased receptivity to alerts due to decreased diagnostic uncertainty and information quantity. Interventions that limit information lead to positive outcomes, supporting our interpretation. CONCLUSION: We synthesize our findings into an integrated model that reveals the underlying reasons for conflicting findings from previous reviews and can guide practitioners in designing ISs in the ED.

Diagnostic Utility of Artificial Intelligence-assisted Transperineal Biopsy Planning in Prostate Cancer Suspected Men: A Prospective Cohort Study.

BACKGROUND AND OBJECTIVE: Accurate magnetic resonance imaging (MRI) reporting is essential for transperineal prostate biopsy (TPB) planning. Although approved computer-aided diagnosis (CAD) tools may assist urologists in this task, evidence of improved clinically significant prostate cancer (csPCa) detection is lacking. Therefore, we aimed to document the diagnostic utility of using Prostate Imaging Reporting and Data System (PI-RADS) and CAD for biopsy planning compared with PI-RADS alone. METHODS: A total of 262 consecutive men scheduled for TPB at our referral centre were analysed. Reported PI-RADS lesions and an US Food and Drug Administration-cleared CAD tool were used for TPB planning. PI-RADS and CAD lesions were targeted on TPB, while four (interquartile range: 2-5) systematic biopsies were taken. The outcomes were the (1) proportion of csPCa (grade group ≥2) and (2) number of targeted lesions and false-positive rate. Performance was tested using free-response receiver operating characteristic curves and the exact Fisher-Yates test. KEY FINDINGS AND LIMITATIONS: Overall, csPCa was detected in 56% (146/262) of men, with sensitivity of 92% and 97% (p = 0.007) for PI-RADS- and CAD-directed TPB, respectively. In 4% (10/262), csPCa was detected solely by CAD-directed biopsies; in 8% (22/262), additional csPCa lesions were detected. However, the number of targeted lesions increased by 54% (518 vs 336) and the false-positive rate doubled (0.66 vs 1.39; p = 0.009). Limitations include biopsies only for men at clinical/radiological suspicion and no multidisciplinary review of MRI before biopsy. CONCLUSIONS AND CLINICAL IMPLICATIONS: The tested CAD tool for TPB planning improves csPCa detection at the cost of an increased number of lesions sampled and false positives. This may enable more personalised biopsy planning depending on urological and patient preferences. PATIENT SUMMARY: The computer-aided diagnosis tool tested for transperineal prostate biopsy planning improves the detection of clinically significant prostate cancer at the cost of an increased number of lesions sampled and false positives. This may enable more personalised biopsy planning depending on urological and patient preferences.

Clinical decision support systems (CDSS) in assistance to COVID-19 diagnosis: A scoping review on types and evaluation methods.

Background and Aims: Due to the COVID-19 pandemic, a precise and reliable diagnosis of this disease is critical. The use of clinical decision support systems (CDSS) can help facilitate the diagnosis of COVID-19. This scoping review aimed to investigate the role of CDSS in diagnosing COVID-19. Methods: We searched four databases (Web of Science, PubMed, Scopus, and Embase) using three groups of keywords related to CDSS, COVID-19, and diagnosis. To collect data from studies, we utilized a data extraction form that consisted of eight fields. Three researchers selected relevant articles and extracted data using a data collection form. To resolve any disagreements, we consulted with a fourth researcher. Results: A search of the databases retrieved 2199 articles, of which 68 were included in this review after removing duplicates and irrelevant articles. The studies used nonknowledge-based CDSS (n = 52) and knowledge-based CDSS (n = 16). Convolutional Neural Networks (CNN) (n = 33) and Support Vector Machine (SVM) (n = 8) were employed to design the CDSS in most of the studies. Accuracy (n = 43) and sensitivity (n = 35) were the most common metrics for evaluating CDSS. Conclusion: CDSS for COVID-19 diagnosis have been developed mainly through machine learning (ML) methods. The greater use of these techniques can be due to their availability of public data sets about chest imaging. Although these studies indicate high accuracy for CDSS based on ML, their novelty and data set biases raise questions about replacing these systems as clinician assistants in decision-making. Further studies are needed to improve and compare the robustness and reliability of nonknowledge-based and knowledge-based CDSS in COVID-19 diagnosis.

Integrating factors associated with complex wound healing into a mobile application: Findings from a cohort study.

Complex, chronic or hard-to-heal wounds are a prevalent health problem worldwide, with significant physical, psychological and social consequences. This study aims to identify factors associated with the healing process of these wounds and develop a mobile application for wound care that incorporates these factors. A prospective multicentre cohort study was conducted in nine health units in Portugal, involving data collection through a mobile application by nurses from April to October 2022. The study followed 46 patients with 57 wounds for up to 5 weeks, conducting six evaluations. Healing time was the main outcome measure, analysed using the Mann-Whitney test and three Cox regression models to calculate risk ratios. The study sample comprised various wound types, with pressure ulcers being the most common (61.4%), followed by venous leg ulcers (17.5%) and diabetic foot ulcers (8.8%). Factors that were found to impair the wound healing process included chronic kidney disease (U = 13.50; p = 0.046), obesity (U = 18.0; p = 0.021), non-adherence to treatment (U = 1.0; p = 0.029) and interference of the wound with daily routines (U = 11.0; p = 0.028). Risk factors for delayed healing over time were identified as bone involvement (RR 3.91; p < 0.001), presence of odour (RR 3.36; p = 0.007), presence of neuropathy (RR 2.49; p = 0.002), use of anti-inflammatory drugs (RR 2.45; p = 0.011), stalled wound (RR 2.26; p = 0.022), greater width (RR 2.03; p = 0.002), greater depth (RR 1.72; p = 0.036) and a high score on the healing scale (RR 1.21; p = 0.001). Integrating the identified risk factors for delayed healing into the assessment of patients and incorporating them into a mobile application can enhance decision-making in wound care.

Negativity and Positivity in the ICU: Exploratory Development of Automated Sentiment Capture in the Electronic Health Record.

OBJECTIVES: To develop proof-of-concept algorithms using alternative approaches to capture provider sentiment in ICU notes. DESIGN: Retrospective observational cohort study. SETTING: The Multiparameter Intelligent Monitoring of Intensive Care III (MIMIC-III) and the University of California, San Francisco (UCSF) deidentified notes databases. PATIENTS: Adult (≥18 yr old) patients admitted to the ICU. MEASUREMENTS AND MAIN RESULTS: We developed two sentiment models: 1) a keywords-based approach using a consensus-based clinical sentiment lexicon comprised of 72 positive and 103 negative phrases, including negations and 2) a Decoding-enhanced Bidirectional Encoder Representations from Transformers with disentangled attention-v3-based deep learning model (keywords-independent) trained on clinical sentiment labels. We applied the models to 198,944 notes across 52,997 ICU admissions in the MIMIC-III database. Analyses were replicated on an external sample of patients admitted to a UCSF ICU from 2018 to 2019. We also labeled sentiment in 1,493 note fragments and compared the predictive accuracy of our tools to three popular sentiment classifiers. Clinical sentiment terms were found in 99% of patient visits across 88% of notes. Our two sentiment tools were substantially more predictive (Spearman correlations of 0.62-0.84, p values < 0.00001) of labeled sentiment compared with general language algorithms (0.28-0.46). CONCLUSION: Our exploratory healthcare-specific sentiment models can more accurately detect positivity and negativity in clinical notes compared with general sentiment tools not designed for clinical usage.

Evaluating the predictive ability of natural language processing in identifying tertiary/quaternary cases in prioritization workflows for interhospital transfer.

Objectives: Tertiary and quaternary (TQ) care refers to complex cases requiring highly specialized health services. Our study aimed to compare the ability of a natural language processing (NLP) model to an existing human workflow in predictively identifying TQ cases for transfer requests to an academic health center. Materials and methods: Data on interhospital transfers were queried from the electronic health record for the 6-month period from July 1, 2020 to December 31, 2020. The NLP model was allowed to generate predictions on the same cases as the human predictive workflow during the study period. These predictions were then retrospectively compared to the true TQ outcomes. Results: There were 1895 transfer cases labeled by both the human predictive workflow and the NLP model, all of which had retrospective confirmation of the true TQ label. The NLP model receiver operating characteristic curve had an area under the curve of 0.91. Using a model probability threshold of ≥0.3 to be considered TQ positive, accuracy was 81.5% for the NLP model versus 80.3% for the human predictions (P = .198) while sensitivity was 83.6% versus 67.7% (P<.001). Discussion: The NLP model was as accurate as the human workflow but significantly more sensitive. This translated to 15.9% more TQ cases identified by the NLP model. Conclusion: Integrating an NLP model into existing workflows as automated decision support could translate to more TQ cases identified at the onset of the transfer process.

Using the TI.VA algorithm to titrate the depth of general anaesthesia: a first-in-humans study.

Background: The dose of anaesthetic and opioid drugs must be continuously adjusted after the induction of general anaesthesia to maintain an adequate depth of anaesthesia. The TI.VA algorithm is a multiple-input/multiple-output algorithm designed to optimise the balance between anaesthetic and opioid concentrations during general anaesthesia. It applies vector analysis to a two-dimensional matrix to quantify any inadequacy of the depth of anaesthesia at any given moment and determine any drug dose adjustments required to achieve an adequate depth of anaesthesia. This study aimed to capture preliminary data on the performance and safety of the TI.VA algorithm during total i.v. anaesthesia in patients. Methods: This prospective study enrolled nine patients with breast cancer scheduled to undergo surgery. General anaesthesia was induced under manual control using propofol and remifentanil. Anaesthesia was guided using the TI.VA algorithm from skin incision until surgical resection was completed. The quality of anaesthesia was assessed through an analysis of performance errors. A bispectral index global score (GSBIS) <50 was considered an acceptable target for algorithm performance. Results: All nine procedures were completed without any adverse events and none of the patients recalled any intraoperative event. Overall, we analysed 3417 monitoring points corresponding to 285 min of surgery. All patients presented a GSBIS below the cut-off value of 50. Conclusions: The TI.VA algorithm provides adequate control of clinical anaesthesia. A more sophisticated prototype needs to be developed before the trial is expanded to include larger patient populations. Clinical trial registration: NCT05199883.

Transforming medical sciences with high-performance computing, high-performance data analytics and AI.

The advance of high-performance computing (HPC), high-performance data analytics (HPDA) and AI and their synergetic integration into workflows has revolutionized numerous industries, amongst others the medical and pharmaceutical sectors. In this special section of Technology and Health Care, we delve into the remarkable advancements and potential of HPC, HPDA and AI (together termed HPC+) in driving innovation, improving patient outcomes, and accelerating drug discovery. The articles in this issue shed light onto the potential of HPC+ in addressing several critical areas, including medical imaging, personalized medicine, drug discovery, and clinical as well as political decision support.

Computer-Assisted Clinical Diagnosis and Treatment.

PURPOSE OF REVIEW: Computer-assisted diagnosis and treatment (CAD/CAT) is a rapidly growing field of medicine that uses computer technology and telehealth to aid in the diagnosis and treatment of various diseases. The purpose of this paper is to provide a review on computer-assisted diagnosis and treatment. This technology gives providers access to diagnostic tools and treatment options so that they can make more informed decisions leading to improved patient outcomes. RECENT FINDINGS: CAD/CAT has expanded in allergy and immunology in the form of digital tools that enable remote patient monitoring such as digital inhalers, pulmonary function tests, and E-diaries. By incorporating this information into electronic medical records (EMRs), providers can use this information to make the best, evidence-based diagnosis and to recommend treatment that is likely to be most effective. A major benefit of CAD/CAT is that by analyzing large amounts of data, tailored recommendations can be made to improve patient outcomes and reduce the risk of adverse events. Machine learning can assist with medical data acquisition, feature extraction, interpretation, and decision support. It is important to note that this technology is not meant to replace human professionals. Instead, it is designed to assist healthcare professionals to better diagnose and treat patients.

Modeling Clinical Guidelines for an Epilepsy-CDSS: The EDiTh Project.

The knowledge transformation process involves the guideline for the diagnosis and therapy of epilepsy to an executable and computable knowledge base that serves as the basis for a decision-support system. We present a transparent knowledge representation model which facilitates technical implementation and verification. Knowledge is represented in a plain table, used in the frontend code of the software where simple reasoning is performed. The simple structure is sufficient and comprehensible also for non-technical persons (i.e., clinicians).

Artificial intelligence-supported web application design and development for reducing polypharmacy side effects and supporting rational drug use in geriatric patients.

Introduction: The main complications of polypharmacy, which is known as the simultaneous use of more than five drugs, are potentially inappropriate medicines(PIMs), drug-drug, and drug-disease interaction. It is aimed to prepare an auxiliary tool to reduce the complications of polypharmacy and to support rational drug use(RDU), by evaluating the patient with age, drugs, and chronic diseases in this study. Materials and methods: In the first phase of this study, as methodological research, an up-to-date and comprehensive auxiliary tool as a reference method was generated with a database containing interaction information of 430 most commonly used drug agents and chronic diseases in geriatrics in the light of current and valid 6 PIM criteria for geriatric patients, and medication prospectuses, relevant current articles, and guidelines. Then, an artificial intelligence(AI) supported web application was designed and developed to facilitate the practical use of the tool. Afterward, the data of a cross-sectional observational single-center study were used for the rate and time of PIM and drug interaction detection with the web application. The proposed web application is publicly available at https://fastrational.com/. Results: While the PIM coverage rate with the proposed tool was 75.3%, the PIM coverage rate of EU(7)-PIM, US-FORTA, TIME-to-STOPP, Beers 2019, STOPP, Priscus criteria in the web application database respectively(63.5%-19.5%) from the highest to the lowest. The proposed tool includes all PIMs, drug-drug, and drug-disease interaction information detected with other criteria. A general practitioner detects interactions for a patient without the web application in 2278 s on average, while the time with the web application is decreased to 33.8 s on average, and this situation is statistically significant. Discussion: In the literature and this study, the PIM criteria alone are insufficient to include actively used medicines and it shows heterogeneity. In addition, many studies showed that the biggest obstacle to drug regulation in practice is "time constraints." The proposed comprehensive auxiliary tool analyzes age, drugs, and diseases specifically for the patient 60 times faster than the manual method, and it provides quick access to the relevant references, and ultimately supports RDU for the clinician, with the first and only AI-supported web application.

Implementation of a patient-centered mobile shared decision making platform and healthcare workers' evaluation: a case in a medical center.

Shared decision making is a patient-centered clinical decision-making process that allows healthcare workers to share the existing empirical medical outcomes with patients before making critical decisions. This study aims to explore a project in a medical center of developing a mobile SDM in Taiwan. Chi Mei Medical Center developed the mobile SDM platform and conducted a survey of evaluation from healthcare workers. A three-tier platform that based on cloud infrastructure with seven functionalities was developed. The survey revealed that healthcare workers with sufficient SDM knowledge have an antecedent effect on the three perceptive factors of acceptance of mobile SDM. Resistance to change and perceived ease of use show significant effect on behavioral intention. We provided a comprehensive architecture of mobile SDM and observed the implementation in a medical center. The majority of healthcare workers expressed their acceptancem; however, resistance to change still present. It is, therefore, necessary to be eliminated by continuously promoting activities that highlight the advantages of the Mobile SDM platform. In clinical practice, we validated that the mobile SDM provides patients and their families with an easy way to express their concerns to healthcare workers improving significantly their relationship with each other.

Development and testing of "Is Lung Cancer Screening for You?" A computer-based decision aid.

PURPOSE: To reduce lung cancer mortality, individuals at high-risk should receive a low-dose computed tomography screening annually. To increase the likelihood of screening, interventions that promote shared decision-making are needed. The goal of this study was to investigate the feasibility, acceptability, usability, and preliminary effectiveness of a computer-based decision aid. METHODS: Thirty-three participants were recruited through primary-care clinics in a small southeastern-US city. Participants used a computer-based decision aid ("Is Lung Cancer Screening for You?") during a clinic appointment. Paper surveys collected self-reported feasibility, acceptability, and usability data. A research coordinator was present to observe each patient's and health-care provider's interactions, and to assess the fidelity of shared decision-making. RESULTS: The decision aid was feasible, acceptable for use in a clinic setting, and easy for participants to use. Patients had low decisional conflict following use of the decision aid and had high screening intention and actual screening rates. Shared decision-making discussions using the decision aid were nearly 6 min on average. CONCLUSION: Computer-based decision aids are feasible for promoting shared lung cancer-screening decisions. A more robust study is warranted to measure the added value of a computer-based version of this aid versus a paper-based aid.

How are ontologies implemented to represent clinical practice guidelines in clinical decision support systems: protocol for a systematic review.

BACKGROUND: Clinical practice guidelines are statements which are based on the best available evidence, and their goal is to improve the quality of patient care. Integrating clinical practice guidelines into computer systems can help physicians reduce medical errors and help them to have the best possible practice. Guideline-based clinical decision support systems play a significant role in supporting physicians in their decisions. Meantime, system errors are the most critical concerns in designing decision support systems that can affect their performance and efficacy. A well-developed ontology can be helpful in this matter. The proposed systematic review will specify the methods, components, language of rules, and evaluation methods of current ontology-driven guideline-based clinical decision support systems. METHODS: This review will identify literature through searching MEDLINE (via Ovid), PubMed, EMBASE, Cochrane Library, CINAHL, ScienceDirect, IEEEXplore, and ACM Digital Library. Gray literature, reference lists, and citing articles of the included studies will be searched. The quality of the included studies will be assessed by the mixed methods appraisal tool (MMAT-version 2018). At least two independent reviewers will perform the screening, quality assessment, and data extraction. A third reviewer will resolve any disagreements. Proper data analysis will be performed based on the type of system and ontology engineering evaluation data. DISCUSSION: The study will provide evidence regarding applying ontologies in guideline-based clinical decision support systems. The findings of this systematic review will be a guide for decision support system designers and developers, technologists, system providers, policymakers, and stakeholders. Ontology builders can use the information in this review to build well-structured ontologies for personalized medicine. SYSTEMATIC REVIEW REGISTRATION: PROSPERO CRD42018106501.

A novel machine learning model for class III surgery decision.

PURPOSE: The primary purpose of this study was to develop a new machine learning model for the surgery/non-surgery decision in class III patients and evaluate the validity and reliability of this model. METHODS: The sample consisted of 196 skeletal class III patients. All the cases were allocated randomly, 136 to the training set and the remaining 60 to the test set. Using the test set, the success rate of the artificial neural network model was estimated, along with a 95% confidence interval. To predict surgical cases, we trained a binary classifier using two different methods: random forest (RF) and logistic regression (LR). RESULTS: Both the RF and the LR model showed high separability when classifying each patient for surgical or non-surgical treatment. RF achieved an area under the curve (AUC) of 0.9395 on the test set. 95% confidence intervals were computed by bootstrap sampling as lower bound = 0.7908 and higher bound = 0.9799. On the other hand, LR achieved an AUC of 0.937 on the test set. 95% confidence intervals were computed by bootstrap sampling as lower bound = 0.8467 and higher bound = 0.9812. CONCLUSIONS: RF and LR machine learning models can be used to generate accurate and reliable algorithms to successfully classify patients up to 90%. The features selected by the algorithms coincide with the clinical features that we as clinicians weigh heavily when determining a treatment plan. This study further supports that overjet, Wits appraisal, lower incisor angulation, and Holdaway H angle can be used as strong predictors in assessing a patient's surgical needs.

Evaluation of electronic screening in the preoperative process.

STUDY OBJECTIVE: Rising patient numbers, with increasing complexity, challenge the sustainability of the current preoperative process. We evaluated whether an electronic screening application can distinguish patients that need a preoperative consultation from low-risk patients that can be first seen on the day of surgery. DESIGN: Prospective cohort study. SETTING: Preoperative clinic of a tertiary academic hospital. PATIENTS: 1395 adult patients scheduled for surgery or procedural sedation. INTERVENTIONS: We assessed a novel electronic preoperative screening application which consists of a questionnaire with a maximum of 185 questions regarding the patient's medical history and current state of health. The application provides an extensive health report, including an American Society of Anesthesiologists physical status (ASA-PS) classification and a recommendation for either consultation by an anesthesiologist at the preoperative clinic or approval for screening on the day of surgery. MEASUREMENTS: The recommendation of the electronic screening system was compared with the regular preoperative assessment using measures of diagnostic accuracy and agreement. Secondary outcomes included ASA-PS classification, patient satisfaction, and the anesthesiologists' opinion on the completeness and quality of the screening report. RESULTS: Sensitivity to detect patients who needed additional consultation was 97.5% (95%CI 91.2-99.7) and the negative likelihood ratio was 0.08 (95%CI 0.02-0.32). 407 (29.2%) patients were approved for surgery by both electronic screening and anesthesiologist. In 909 (65.2%) cases, the electronic screening system recommended further consultation while the anesthesiologist approved the patient (specificity 30.9% (95%CI 28.4-33.5); poor level of agreement (ĸ = 0.04)). Agreement regarding ASA-PS classification scores was weak (ĸ = 0.48). The majority of patients (78.0%) felt positive about electronic screening replacing the regular preoperative assessment. CONCLUSIONS: Electronic screening can reliably identify patients who can have their first contact with an anesthesiologist on the day of surgery, potentially allowing a major proportion of patients to safely bypass the preoperative clinic.

Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients.

Structured Abstract-Objective: Abnormal elevation of intracranial pressure (ICP) can cause dangerous or even fatal outcomes. The early detection of high intracranial pressure events can be crucial in saving lives in an intensive care unit (ICU). Despite many applications of machine learning (ML) techniques related to clinical diagnosis, ML applications for continuous ICP detection or short-term predictions have been rarely reported. This study proposes an efficient method of applying an artificial recurrent neural network on the early prediction of ICP evaluation continuously for TBI patients. Methods: After ICP data preprocessing, the learning model is generated for thirteen patients to continuously predict the ICP signal occurrence and classify events for the upcoming 10 minutes by inputting the previous 20-minutes of the ICP signal. Results: As the overall model performance, the average accuracy is 94.62%, the average sensitivity is 74.91%, the average specificity is 94.83%, and the average root mean square error is approximately 2.18 mmHg. Conclusion: This research addresses a significant clinical problem with the management of traumatic brain injury patients. The machine learning model data enables early prediction of ICP continuously in a real-time fashion, which is crucial for appropriate clinical interventions. The results show that our machine learning-based model has high adaptive performance, accuracy, and efficiency.