-
Journal of Pathology Informatics Dec 2024Numerous machine learning (ML) models have been developed for breast cancer using various types of data. Successful external validation (EV) of ML models is important... (Review)
Review
Performance of externally validated machine learning models based on histopathology images for the diagnosis, classification, prognosis, or treatment outcome prediction in female breast cancer: A systematic review.
Numerous machine learning (ML) models have been developed for breast cancer using various types of data. Successful external validation (EV) of ML models is important evidence of their generalizability. The aim of this systematic review was to assess the performance of externally validated ML models based on histopathology images for diagnosis, classification, prognosis, or treatment outcome prediction in female breast cancer. A systematic search of MEDLINE, EMBASE, CINAHL, IEEE, MICCAI, and SPIE conferences was performed for studies published between January 2010 and February 2022. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed, and the results were narratively described. Of the 2011 non-duplicated citations, 8 journal articles and 2 conference proceedings met inclusion criteria. Three studies externally validated ML models for diagnosis, 4 for classification, 2 for prognosis, and 1 for both classification and prognosis. Most studies used Convolutional Neural Networks and one used logistic regression algorithms. For diagnostic/classification models, the most common performance metrics reported in the EV were accuracy and area under the curve, which were greater than 87% and 90%, respectively, using pathologists' annotations/diagnoses as ground truth. The hazard ratios in the EV of prognostic ML models were between 1.7 (95% CI, 1.2-2.6) and 1.8 (95% CI, 1.3-2.7) to predict distant disease-free survival; 1.91 (95% CI, 1.11-3.29) for recurrence, and between 0.09 (95% CI, 0.01-0.70) and 0.65 (95% CI, 0.43-0.98) for overall survival, using clinical data as ground truth. Despite EV being an important step before the clinical application of a ML model, it hasn't been performed routinely. The large variability in the training/validation datasets, methods, performance metrics, and reported information limited the comparison of the models and the analysis of their results. Increasing the availability of validation datasets and implementing standardized methods and reporting protocols may facilitate future analyses.
PubMed: 38089005
DOI: 10.1016/j.jpi.2023.100348 -
Forensic Science International Nov 2023Dog bites pose a significant global public health issue and are the most common type of injury caused by animals. While most dog bites result in minor harm, they can... (Review)
Review
Dog bites pose a significant global public health issue and are the most common type of injury caused by animals. While most dog bites result in minor harm, they can also lead to severe or even fatal consequences. In cases involving serious injury or death, forensic pathologists investigate various aspects, including the crime scene, the injuries sustained by the victim, and the characteristics of the dog suspected to have caused the bite. The aim of this study is to provide a systematic review of the literature on the medical-legal implications of dog bites in forensic practice, in order to recognize the dog bite victim features, the injuries and their consequences related to, and to identify the offending dogs. The literature search was performed using PubMed, Scopus and Web of Science from January 1980 to March 2023. Eligible studies have investigated issues of interest to forensic medicine about dog bites to humans. A total of 116 studies met the inclusion criteria and were included in the review and they were organized and discussed by issue of interest (biting dog features, dog bite victim features, anatomical distribution of dog bites, injuries related to dog bites, cause of death, bite features, dog identification and post-mortem dog depredation). The findings of this systematic review highlight the importance of bite mark analysis in reconstructing the events leading to the attack and identifying the dog responsible. In medical forensic evaluations of dog bite cases, a multidisciplinary approach is crucial. This approach involves thorough analysis of the crime scene, identification of risk factors, examination of dog characteristics, and assessment of the victim's injuries. By combining expertise from both human and veterinary forensic fields, a comprehensive understanding can be achieved in dog bite cases.
Topics: Humans; Dogs; Animals; Bites and Stings; Forensic Medicine; Crime; Risk Factors; Autopsy
PubMed: 37783138
DOI: 10.1016/j.forsciint.2023.111849 -
Journal of Medical Internet Research Sep 2023Multimodal treatment-induced dysphagia has serious negative effects on survivors of head and neck cancer. Owing to advances in communication technologies, several... (Review)
Review
BACKGROUND
Multimodal treatment-induced dysphagia has serious negative effects on survivors of head and neck cancer. Owing to advances in communication technologies, several studies have applied telecommunication-based interventions that incorporate swallowing exercises, education, monitoring, feedback, self-management, and communication. It is especially urgent to implement home-based remote rehabilitation in the context of the COVID-19 pandemic. However, the optimal strategy and effectiveness of remote interventions are unclear.
OBJECTIVE
This systematic review aimed to examine the evidence regarding the efficacy of telerehabilitation for reducing physiological and functional impairments related to swallowing and for improving adherence and related influencing factors among head and neck cancer survivors.
METHODS
The PubMed, MEDLINE, CINAHL, Embase, and Cochrane Library databases were systematically searched up to July 2023 to identify relevant articles. In total, 2 investigators independently extracted the data and assessed the methodological quality of the included studies using the quality assessment tool of the Joanna Briggs Institute.
RESULTS
A total of 1465 articles were initially identified; ultimately, 13 (0.89%) were included in the systematic review. The quality assessment indicated that the included studies were of moderate to good quality. The results showed that home-based telerehabilitation improved the safety of swallowing and oral feeding, nutritional status, and swallowing-related quality of life; reduced negative emotions; improved swallowing rehabilitation adherence; was rated by participants as highly satisfactory and supportive; and was cost-effective. In addition, this review investigated factors that influenced the efficacy of telerehabilitation, which included striking a balance among swallowing training strategy, intensity, frequency, duration, and individual motor ability; treating side effects of radiotherapy; providing access to medical, motivational, and educational information; providing feedback on training; providing communication and support from speech pathologists, families, and other survivors; and addressing technical problems.
CONCLUSIONS
Home-based telerehabilitation has shown great potential in reducing the safety risks of swallowing and oral feeding, improving quality of life and adherence, and meeting information needs for dysphagia among survivors of head and neck cancer. However, this review highlights limitations in the current literature, and the current research is in its infancy. In addition, owing to the diversity of patient sociodemographic, medical, physiological and functional swallowing, and behavioral factors, we recommend the development of tailored telemedicine interventions to achieve the best rehabilitation effects with the fewest and most precise interventions.
Topics: Humans; Deglutition Disorders; Telerehabilitation; Pandemics; Quality of Life; COVID-19; Neoplasms
PubMed: 37682589
DOI: 10.2196/47324 -
Archives of Pathology & Laboratory... May 2024Automated prostate cancer detection using machine learning technology has led to speculation that pathologists will soon be replaced by algorithms. This review covers...
CONTEXT
Automated prostate cancer detection using machine learning technology has led to speculation that pathologists will soon be replaced by algorithms. This review covers the development of machine learning algorithms and their reported effectiveness specific to prostate cancer detection and Gleason grading.
OBJECTIVE
To examine current algorithms regarding their accuracy and classification abilities. We provide a general explanation of the technology and how it is being used in clinical practice. The challenges to the application of machine learning algorithms in clinical practice are also discussed.
DATA SOURCES
The literature for this review was identified and collected using a systematic search. Criteria were established prior to the sorting process to effectively direct the selection of studies. A 4-point system was implemented to rank the papers according to their relevancy. For papers accepted as relevant to our metrics, all cited and citing studies were also reviewed. Studies were then categorized based on whether they implemented binary or multi-class classification methods. Data were extracted from papers that contained accuracy, area under the curve (AUC), or κ values in the context of prostate cancer detection. The results were visually summarized to present accuracy trends between classification abilities.
CONCLUSIONS
It is more difficult to achieve high accuracy metrics for multiclassification tasks than for binary tasks. The clinical implementation of an algorithm that can assign a Gleason grade to clinical whole slide images (WSIs) remains elusive. Machine learning technology is currently not able to replace pathologists but can serve as an important safeguard against misdiagnosis.
Topics: Humans; Prostatic Neoplasms; Male; Machine Learning; Artificial Intelligence; Neoplasm Grading; Algorithms
PubMed: 37594900
DOI: 10.5858/arpa.2022-0460-RA -
Cancers Aug 2023Lung cancer is one of the deadliest cancers worldwide, with a high incidence rate, especially in tobacco smokers. Lung cancer accurate diagnosis is based on distinct... (Review)
Review
Lung cancer is one of the deadliest cancers worldwide, with a high incidence rate, especially in tobacco smokers. Lung cancer accurate diagnosis is based on distinct histological patterns combined with molecular data for personalized treatment. Precise lung cancer classification from a single H&E slide can be challenging for a pathologist, requiring most of the time additional histochemical and special immunohistochemical stains for the final pathology report. According to WHO, small biopsy and cytology specimens are the available materials for about 70% of lung cancer patients with advanced-stage unresectable disease. Thus, the limited available diagnostic material necessitates its optimal management and processing for the completion of diagnosis and predictive testing according to the published guidelines. During the new era of Digital Pathology, Deep Learning offers the potential for lung cancer interpretation to assist pathologists' routine practice. Herein, we systematically review the current Artificial Intelligence-based approaches using histological and cytological images of lung cancer. Most of the published literature centered on the distinction between lung adenocarcinoma, lung squamous cell carcinoma, and small cell lung carcinoma, reflecting the realistic pathologist's routine. Furthermore, several studies developed algorithms for lung adenocarcinoma predominant architectural pattern determination, prognosis prediction, mutational status characterization, and PD-L1 expression status estimation.
PubMed: 37568797
DOI: 10.3390/cancers15153981 -
BMC Medical Informatics and Decision... Jul 2023Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are...
INTRODUCTION
Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are critical for improving patients' outcomes, as over 40% of patients with EC are diagnosed after metastasis. Recent advances in machine learning (ML) techniques, particularly in computer vision, have demonstrated promising applications in medical image processing, assisting clinicians in making more accurate and faster diagnostic decisions. Given the significance of early detection of EC, this systematic review aims to summarize and discuss the current state of research on ML-based methods for the early detection of EC.
METHODS
We conducted a comprehensive systematic search of five databases (PubMed, Scopus, Web of Science, Wiley, and IEEE) using search terms such as "ML", "Deep Learning (DL (", "Neural Networks (NN)", "Esophagus", "EC" and "Early Detection". After applying inclusion and exclusion criteria, 31 articles were retained for full review.
RESULTS
The results of this review highlight the potential of ML-based methods in the early detection of EC. The average accuracy of the reviewed methods in the analysis of endoscopic and computed tomography (CT (images of the esophagus was over 89%, indicating a high impact on early detection of EC. Additionally, the highest percentage of clinical images used in the early detection of EC with the use of ML was related to white light imaging (WLI) images. Among all ML techniques, methods based on convolutional neural networks (CNN) achieved higher accuracy and sensitivity in the early detection of EC compared to other methods.
CONCLUSION
Our findings suggest that ML methods may improve accuracy in the early detection of EC, potentially supporting radiologists, endoscopists, and pathologists in diagnosis and treatment planning. However, the current literature is limited, and more studies are needed to investigate the clinical applications of these methods in early detection of EC. Furthermore, many studies suffer from class imbalance and biases, highlighting the need for validation of detection algorithms across organizations in longitudinal studies.
Topics: Humans; Deep Learning; Early Detection of Cancer; Machine Learning; Neural Networks, Computer; Esophageal Neoplasms
PubMed: 37460991
DOI: 10.1186/s12911-023-02235-y -
Biomedicines Jun 2023Oral cancer (OC) is one of the most common forms of head and neck cancer and continues to have the lowest survival rates worldwide, even with advancements in research... (Review)
Review
Oral cancer (OC) is one of the most common forms of head and neck cancer and continues to have the lowest survival rates worldwide, even with advancements in research and therapy. The prognosis of OC has not significantly improved in recent years, presenting a persistent challenge in the biomedical field. In the field of oncology, artificial intelligence (AI) has seen rapid development, with notable successes being reported in recent times. This systematic review aimed to critically appraise the available evidence regarding the utilization of AI in the diagnosis, classification, and prediction of oral cancer (OC) using histopathological images. An electronic search of several databases, including PubMed, Scopus, Embase, the Cochrane Library, Web of Science, Google Scholar, and the Saudi Digital Library, was conducted for articles published between January 2000 and January 2023. Nineteen articles that met the inclusion criteria were then subjected to critical analysis utilizing QUADAS-2, and the certainty of the evidence was assessed using the GRADE approach. AI models have been widely applied in diagnosing oral cancer, differentiating normal and malignant regions, predicting the survival of OC patients, and grading OC. The AI models used in these studies displayed an accuracy in a range from 89.47% to 100%, sensitivity from 97.76% to 99.26%, and specificity ranging from 92% to 99.42%. The models' abilities to diagnose, classify, and predict the occurrence of OC outperform existing clinical approaches. This demonstrates the potential for AI to deliver a superior level of precision and accuracy, helping pathologists significantly improve their diagnostic outcomes and reduce the probability of errors. Considering these advantages, regulatory bodies and policymakers should expedite the process of approval and marketing of these products for application in clinical scenarios.
PubMed: 37371706
DOI: 10.3390/biomedicines11061612 -
Multimedia Tools and Applications Mar 2023Speech is a powerful, natural mode of communication that facilitates effective interactions in human societies. However, when fluency or flow of speech is affected or...
Speech is a powerful, natural mode of communication that facilitates effective interactions in human societies. However, when fluency or flow of speech is affected or interrupted, it leads to speech impairment. There are several types of speech impairment depending on the speech pattern and range from mild to severe. Childhood apraxia of speech (CAS) is the most common speech disorder in children, with 1 out of 12 children diagnosed globally. Significant advancements in speech assessment tools have been reported to assist speech-language pathologists diagnosis speech impairment. In recent years, speech assessment tools have also gained popularity among pediatricians and teachers who work with preschoolers. Automatic speech tools can be more accurate for detecting speech sound disorders (SSD) than human-based speech assessment methods. This systematic literature review covers 88 studies, including more than 500 children, infants, toddlers, and a few adolescents, (both male and female) (age = 0-17) representing speech impairment from more than 10 countries. It discusses the state-of-the-art speech assessment methods, including tools, techniques, and protocols for speech-impaired children. Additionally, this review summarizes notable outcomes in detecting speech impairments using said assessment methods and discusses various limitations such as universality, reliability, and validity. Finally, we consider the challenges and future directions for speech impairment assessment tool research.
PubMed: 37362682
DOI: 10.1007/s11042-023-14913-0 -
Archives of Pathology & Laboratory... Sep 2023To update the American Society of Clinical Oncology-College of American Pathologists (ASCO-CAP) recommendations for human epidermal growth factor receptor 2 (HER2)...
PURPOSE.—
To update the American Society of Clinical Oncology-College of American Pathologists (ASCO-CAP) recommendations for human epidermal growth factor receptor 2 (HER2) testing in breast cancer. An Update Panel is aware that a new generation of antibody-drug conjugates targeting the HER2 protein is active against breast cancers that lack protein overexpression or gene amplification.
METHODS.—
The Update Panel conducted a systematic literature review to identify signals for updating recommendations.
RESULTS.—
The search identified 173 abstracts. Of 5 potential publications reviewed, none constituted a signal for revising existing recommendations.
RECOMMENDATIONS.—
The 2018 ASCO-CAP recommendations for HER2 testing are affirmed.
DISCUSSION.—
HER2 testing guidelines have focused on identifying HER2 protein overexpression or gene amplification in breast cancer to identify patients for therapies that disrupt HER2 signaling. This update acknowledges a new indication for trastuzumab deruxtecan when HER2 is not overexpressed or amplified but is immunohistochemistry (IHC) 1+ or 2+ without amplification by in situ hybridization. Clinical trial data on tumors that tested IHC 0 are limited (excluded from DESTINY-Breast04), and evidence is lacking that these cancers behave differently or do not respond similarly to newer HER2 antibody-drug conjugates. Although current data do not support a new IHC 0 versus 1+ prognostic or predictive threshold for response to trastuzumab deruxtecan, this threshold is now relevant because of the trial entry criteria that supported its new regulatory approval. Therefore, although it is premature to create new result categories of HER2 expression (eg, HER2-Low, HER2-Ultra-Low), best practices to distinguish IHC 0 from 1+ are now clinically relevant. This update affirms prior HER2 reporting recommendations and offers a new HER2 testing reporting comment to highlight the current relevance of IHC 0 versus 1+ results and best practice recommendations to distinguish these often subtle differences. Additional information is available at www.asco.org/breast-cancer-guidelines.
Topics: Humans; Female; Breast Neoplasms; In Situ Hybridization, Fluorescence; Receptor, ErbB-2; In Situ Hybridization; Biomarkers, Tumor
PubMed: 37303228
DOI: 10.5858/arpa.2023-0950-SA -
American Journal of Clinical Pathology Oct 2023This study aims to determine what pathologic and clinical factors differentiate Brachyspira species that may be useful to clinicians and pathologists.
Clinical and Pathologic Factors Associated With Colonic Spirochete (Brachyspira pilosicoli and Brachyspira aalborgi) Infection: A Comprehensive Systematic Review and Pooled Analysis.
OBJECTIVES
This study aims to determine what pathologic and clinical factors differentiate Brachyspira species that may be useful to clinicians and pathologists.
METHODS
We identified 21 studies of Brachyspira infection with individual patient information (n = 113) and conducted a pooled analysis comparing each species.
RESULTS
There were differences in the pathologic and clinical profiles of each Brachyspira species. Patients infected with Brachyspira pilosicoli infection were more likely to have diarrhea, fever, HIV, and immunocompromised conditions. Those patients infected with Brachyspira aalborgi were more likely to have lamina propria inflammation.
CONCLUSIONS
Our novel data provide potential insights into the pathogenic mechanism(s) and the specific risk factor profile of Brachyspira species. This may be clinically useful when assessing and managing patients.
Topics: Humans; Spirochaetales; Spirochaetales Infections; Brachyspira
PubMed: 37289435
DOI: 10.1093/ajcp/aqad063