-
The Indian Journal of Radiology &... Jul 2024Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely... (Review)
Review
Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.
PubMed: 38912238
DOI: 10.1055/s-0043-1775737 -
Current Status and Role of Artificial Intelligence in Anorectal Diseases and Pelvic Floor Disorders.JSLS : Journal of the Society of... 2024Anorectal diseases and pelvic floor disorders are prevalent among the general population. Patients may present with overlapping symptoms, delaying diagnosis, and... (Review)
Review
BACKGROUND
Anorectal diseases and pelvic floor disorders are prevalent among the general population. Patients may present with overlapping symptoms, delaying diagnosis, and lowering quality of life. Treating physicians encounter numerous challenges attributed to the complex nature of pelvic anatomy, limitations of diagnostic techniques, and lack of available resources. This article is an overview of the current state of artificial intelligence (AI) in tackling the difficulties of managing benign anorectal disorders and pelvic floor disorders.
METHODS
A systematic literature review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched the PubMed database to identify all potentially relevant studies published from January 2000 to August 2023. Search queries were built using the following terms: AI, machine learning, deep learning, benign anorectal disease, pelvic floor disorder, fecal incontinence, obstructive defecation, anal fistula, rectal prolapse, and anorectal manometry. Malignant anorectal articles and abstracts were excluded. Data from selected articles were analyzed.
RESULTS
139 articles were found, 15 of which met our inclusion and exclusion criteria. The most common AI module was convolutional neural network. researchers were able to develop AI modules to optimize imaging studies for pelvis, fistula, and abscess anatomy, facilitated anorectal manometry interpretation, and improved high-definition anoscope use. None of the modules were validated in an external cohort.
CONCLUSION
There is potential for AI to enhance the management of pelvic floor and benign anorectal diseases. Ongoing research necessitates the use of multidisciplinary approaches and collaboration between physicians and AI programmers to tackle pressing challenges.
Topics: Humans; Pelvic Floor Disorders; Artificial Intelligence; Rectal Diseases; Anus Diseases; Manometry; Fecal Incontinence
PubMed: 38910957
DOI: 10.4293/JSLS.2024.00007 -
Cureus May 2024Neuroendocrine tumors (NETs) represent a heterogeneous group of neoplasms with diverse clinical presentations and prognoses. Accurate and timely diagnosis of these... (Review)
Review
Neuroendocrine tumors (NETs) represent a heterogeneous group of neoplasms with diverse clinical presentations and prognoses. Accurate and timely diagnosis of these tumors is crucial for appropriate management and improved patient outcomes. In recent years, exciting advancements in artificial intelligence (AI) technologies have been revolutionizing medical diagnostics, particularly in the realm of detecting and characterizing pulmonary NETs, offering promising avenues for improved patient care. This article aims to provide a comprehensive overview of the role of AI in diagnosing lung NETs. We discuss the current challenges associated with conventional diagnostic approaches, including histopathological examination and imaging modalities. Despite advancements in these techniques, accurate diagnosis remains challenging due to the overlapping features with other pulmonary lesions and the subjective interpretation of imaging findings. AI-based approaches, including machine learning and deep learning algorithms, have demonstrated remarkable potential in addressing these challenges. By leveraging large datasets of radiological images, histopathological samples, and clinical data, AI models can extract complex patterns and features that may not be readily discernible to human observers. Moreover, AI algorithms can continuously learn and improve from new data, leading to enhanced diagnostic accuracy and efficiency over time. Specific AI applications in the diagnosis of lung NETs include computer-aided detection and classification of pulmonary nodules on CT scans, quantitative analysis of PET imaging for tumor characterization, and integration of multi-modal data for comprehensive diagnostic assessments. These AI-driven tools hold promise for facilitating early detection, risk stratification, and personalized treatment planning in patients with lung NETs.
PubMed: 38910787
DOI: 10.7759/cureus.61012 -
Cureus May 2024Diagnosing endometrial carcinoma correctly is essential for appropriate treatment, as it is a major health risk. As machine learning (ML) and artificial intelligence... (Review)
Review
Diagnosing endometrial carcinoma correctly is essential for appropriate treatment, as it is a major health risk. As machine learning (ML) and artificial intelligence (AI) have grown in popularity, so has interest in their potential to improve cancer diagnosis accuracy. In the context of endometrial cancer, this study attempts to examine the efficacy as well as the accuracy of AI-assisted diagnostic approaches. Additionally, it aims to methodically evaluate the contribution of AI and ML techniques to the improvement of endometrial cancer diagnosis. Following PRISMA guidelines, we performed a thorough search of numerous databases, including Medline via Ovid, PubMed, Scopus, Web of Science, and Google Scholar. Ten years were searched, encompassing both basic and advanced research. Peer-reviewed papers and original research studies that explicitly looked at the application of AI/ML in endometrial cancer diagnosis were the main targets of the well-defined selection criteria. Using the Critical Appraisal Skills Programme (CASP) methodology, two independent researchers conducted a thorough screening process and quality assessment of included studies. The review found a notable inclination towards the effective use of AI in endometrial carcinoma diagnostics, namely in the identification and categorization of endometrial cancer. Artificial intelligence models, particularly Convolutional Neural Networks (CNNs) and deep learning algorithms have shown remarkable precision in detecting endometrial cancer. They frequently achieve or even exceed the diagnostic proficiency of human specialists. The use of artificial intelligence in medical diagnostics signifies revolutionary progress in the field of oncology. AI-assisted diagnostic tools have demonstrated the potential to improve the precision and effectiveness of cancer diagnosis, namely in cases of endometrial carcinoma. This innovation not only enhances the quality of patient care but also indicates a transition towards more individualized and efficient treatment approaches in the field of oncology. The advancement of AI technology is expected to play a crucial role in medical diagnostics, particularly in the field of cancer detection and treatment, perhaps leading to a significant transformation in the approach to these areas.
PubMed: 38910646
DOI: 10.7759/cureus.60973 -
Journal of Affective Disorders Jun 2024Bipolar disorder (BD) is a mental disorder associated with increased morbidity/mortality. Adverse outcome prediction helps with the management of patients with BD. (Review)
Review
BACKGROUND
Bipolar disorder (BD) is a mental disorder associated with increased morbidity/mortality. Adverse outcome prediction helps with the management of patients with BD.
METHODS
We systematically reviewed the performance of machine learning (ML) studies in predicting adverse outcomes (relapse or recurrence, hospital admission, and suicide-related events) in patients with BD. Demographic, clinical, and neuroimaging-related poor outcome predictors were also reviewed. Three databases (PubMed, Scopus, and Web of Science) were explored from inception to July 2023.
RESULTS
Eighteen studies, accounting for >30,000 patients, were included. Support vector machine, decision trees, random forest, and logistic regression were the most frequently used ML algorithms. ML models' area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity ranged from 0.71 to 0.98, 72.7-92.8 %, and 59.0-95.2 % for relapse/recurrence prediction (5 studies (3 on relapses and 1 on recurrences). The corresponding values were 0.78-0.88, 21.4-100 %, and 77.0-99.7 % for hospital admissions (3 studies, 21,266 patients), and 0.71-0.99, 44.4-97.9 %, and 38.9-95.0 % for suicide-related events (10 studies, 5558 patients). Also, one study addressed a combination of the interest outcomes. Adverse outcome predictors included early onset BD, type I BD, comorbid psychiatric or substance use disorder, circadian rhythm disruption, hospitalization characteristics, and neuroimaging parameters, including increased dynamic amplitude of low-frequency fluctuation, decreased frontolimbic functional connectivity and aberrant dynamic FC in corticostriatal circuitry.
CONCLUSIONS
ML models can predict adverse outcomes of BD with relatively acceptable performance measures. Future studies with larger samples and nested cross-validation validation should be conducted to reach more reliable results.
PubMed: 38908556
DOI: 10.1016/j.jad.2024.06.061 -
BMC Medical Informatics and Decision... Jun 2024Enhancing Local Control (LC) of brain metastases is pivotal for improving overall survival, which makes the prediction of local treatment failure a crucial aspect of...
BACKGROUND
Enhancing Local Control (LC) of brain metastases is pivotal for improving overall survival, which makes the prediction of local treatment failure a crucial aspect of treatment planning. Understanding the factors that influence LC of brain metastases is imperative for optimizing treatment strategies and subsequently extending overall survival. Machine learning algorithms may help to identify factors that predict outcomes.
METHODS
This paper systematically reviews these factors associated with LC to select candidate predictor features for a practical application of predictive modeling. A systematic literature search was conducted to identify studies in which the LC of brain metastases is assessed for adult patients. EMBASE, PubMed, Web-of-Science, and the Cochrane Database were searched up to December 24, 2020. All studies investigating the LC of brain metastases as one of the endpoints were included, regardless of primary tumor type or treatment type. We first grouped studies based on primary tumor types resulting in lung, breast, and melanoma groups. Studies that did not focus on a specific primary cancer type were grouped based on treatment types resulting in surgery, SRT, and whole-brain radiotherapy groups. For each group, significant factors associated with LC were identified and discussed. As a second project, we assessed the practical importance of selected features in predicting LC after Stereotactic Radiotherapy (SRT) with a Random Forest machine learning model. Accuracy and Area Under the Curve (AUC) of the Random Forest model, trained with the list of factors that were found to be associated with LC for the SRT treatment group, were reported.
RESULTS
The systematic literature search identified 6270 unique records. After screening titles and abstracts, 410 full texts were considered, and ultimately 159 studies were included for review. Most of the studies focused on the LC of the brain metastases for a specific primary tumor type or after a specific treatment type. Higher SRT radiation dose was found to be associated with better LC in lung cancer, breast cancer, and melanoma groups. Also, a higher dose was associated with better LC in the SRT group, while higher tumor volume was associated with worse LC in this group. The Random Forest model predicted the LC of brain metastases with an accuracy of 80% and an AUC of 0.84.
CONCLUSION
This paper thoroughly examines factors associated with LC in brain metastases and highlights the translational value of our findings for selecting variables to predict LC in a sample of patients who underwent SRT. The prediction model holds great promise for clinicians, offering a valuable tool to predict personalized treatment outcomes and foresee the impact of changes in treatment characteristics such as radiation dose.
Topics: Humans; Machine Learning; Brain Neoplasms
PubMed: 38907265
DOI: 10.1186/s12911-024-02579-z -
Frontiers in Pharmacology 2024[This corrects the article DOI: 10.3389/fphar.2023.1156655.].
[This corrects the article DOI: 10.3389/fphar.2023.1156655.].
PubMed: 38903988
DOI: 10.3389/fphar.2024.1426608 -
Clinical Kidney Journal Jun 2024Acute kidney injury (AKI) is associated with increased morbidity/mortality. With artificial intelligence (AI), more dynamic models for mortality prediction in AKI...
BACKGROUND
Acute kidney injury (AKI) is associated with increased morbidity/mortality. With artificial intelligence (AI), more dynamic models for mortality prediction in AKI patients have been developed using machine learning (ML) algorithms. The performance of various ML models was reviewed in terms of their ability to predict in-hospital mortality for AKI patients.
METHODS
A literature search was conducted through PubMed, Embase and Web of Science databases. Included studies contained variables regarding the efficacy of the AI model [the AUC, accuracy, sensitivity, specificity, negative predictive value and positive predictive value]. Only original studies that consisted of cross-sectional studies, prospective and retrospective studies were included, while reviews and self-reported outcomes were excluded. There was no restriction on time and geographic location.
RESULTS
Eight studies with 37 032 AKI patients were included, with a mean age of 65.3 years. The in-hospital mortality was 18.0% in the derivation and 15.8% in the validation cohorts. The pooled [95% confidence interval (CI)] AUC was observed to be highest for the broad learning system (BLS) model [0.852 (0.820-0.883)] and elastic net final (ENF) model [0.852 (0.813-0.891)], and lowest for proposed clinical model (PCM) [0.765 (0.716-0.814)]. The pooled (95% CI) AUC of BLS and ENF did not differ significantly from other models except PCM [Delong's test = .022]. PCM exhibited the highest negative predictive value, which supports this model's use as a possible rule-out tool.
CONCLUSION
Our results show that BLS and ENF models are equally effective as other ML models in predicting in-hospital mortality, with variability across all models. Additional studies are needed.
PubMed: 38903953
DOI: 10.1093/ckj/sfae150 -
Frontiers in Psychology 2024This study analyzes the existing academic literature to identify the effects of artificial intelligence (AI) on human resource (HR) activities, highlighting both...
INTRODUCTION
This study analyzes the existing academic literature to identify the effects of artificial intelligence (AI) on human resource (HR) activities, highlighting both opportunities and associated challenges, and on the roles of employees, line managers, and HR professionals, collectively referred to as the HR triad.
METHODS
We employed the scoping review method to capture and synthesize relevant academic literature in the AI-human resource management (HRM) field, examining 27 years of research (43 peer-reviewed articles are included).
RESULTS
Based on the results, we propose an integrative framework that outlines the five primary effects of AI on HR activities: task automation, optimized HR data use, augmentation of human capabilities, work context redesign, and transformation of the social and relational aspects of work. We also detail the opportunities and challenges associated with each of these effects and the changes in the roles of the HR triad.
DISCUSSION
This research contributes to the ongoing debate on AI-augmented HRM by discussing the theoretical contributions and managerial implications of our findings, along with avenues for future research. By considering the most recent studies on the topic, this scoping review sheds light on the effects of AI on the roles of the HR triad, enabling these key stakeholders to better prepare for this technological change. The findings can inform future academic research, organizations using or considering the application of AI in HRM, and policymakers. This is particularly timely, given the growing adoption of AI in HRM activities.
PubMed: 38903456
DOI: 10.3389/fpsyg.2024.1360401 -
BMJ Health & Care Informatics Jun 2024Risk stratification tools that predict healthcare utilisation are extensively integrated into primary care systems worldwide, forming a key component of anticipatory...
OBJECTIVES
Risk stratification tools that predict healthcare utilisation are extensively integrated into primary care systems worldwide, forming a key component of anticipatory care pathways, where high-risk individuals are targeted by preventative interventions. Existing work broadly focuses on comparing model performance in retrospective cohorts with little attention paid to efficacy in reducing morbidity when deployed in different global contexts. We review the evidence supporting the use of such tools in real-world settings, from retrospective dataset performance to pathway evaluation.
METHODS
A systematic search was undertaken to identify studies reporting the development, validation and deployment of models that predict healthcare utilisation in unselected primary care cohorts, comparable to their current real-world application.
RESULTS
Among 3897 articles screened, 51 studies were identified evaluating 28 risk prediction models. Half underwent external validation yet only two were validated internationally. No association between validation context and model discrimination was observed. The majority of real-world evaluation studies reported no change, or indeed significant increases, in healthcare utilisation within targeted groups, with only one-third of reports demonstrating some benefit.
DISCUSSION
While model discrimination appears satisfactorily robust to application context there is little evidence to suggest that accurate identification of high-risk individuals can be reliably translated to improvements in service delivery or morbidity.
CONCLUSIONS
The evidence does not support further integration of care pathways with costly population-level interventions based on risk prediction in unselected primary care cohorts. There is an urgent need to independently appraise the safety, efficacy and cost-effectiveness of risk prediction systems that are already widely deployed within primary care.
Topics: Humans; Risk Assessment; Primary Health Care; Patient Acceptance of Health Care; Algorithms
PubMed: 38901863
DOI: 10.1136/bmjhci-2024-101065