-
Physiological Measurement Aug 2022The photoplethysmogram (PPG) signal is widely used in pulse oximeters and smartwatches. A fundamental step in analysing the PPG is the detection of heartbeats. Several...
The photoplethysmogram (PPG) signal is widely used in pulse oximeters and smartwatches. A fundamental step in analysing the PPG is the detection of heartbeats. Several PPG beat detection algorithms have been proposed, although it is not clear which performs best.This study aimed to: (i) develop a framework with which to design and test PPG beat detectors; (ii) assess the performance of PPG beat detectors in different use cases; and (iii) investigate how their performance is affected by patient demographics and physiology.Fifteen beat detectors were assessed against electrocardiogram-derived heartbeats using data from eight datasets. Performance was assessed using thescore, which combines sensitivity and positive predictive value.Eight beat detectors performed well in the absence of movement withscores of ≥90% on hospital data and wearable data collected at rest. Their performance was poorer during exercise withscores of 55%-91%; poorer in neonates than adults withscores of 84%-96% in neonates compared to 98%-99% in adults; and poorer in atrial fibrillation (AF) withscores of 92%-97% in AF compared to 99%-100% in normal sinus rhythm.Two PPG beat detectors denoted 'MSPTD' and 'qppg' performed best, with complementary performance characteristics. This evidence can be used to inform the choice of PPG beat detector algorithm. The algorithms, datasets, and assessment framework are freely available.
Topics: Adult; Algorithms; Atrial Fibrillation; Benchmarking; Electrocardiography; Heart Rate; Humans; Infant, Newborn; Photoplethysmography
PubMed: 35853440
DOI: 10.1088/1361-6579/ac826d -
Biomedical Journal Apr 2022Comprehensive Geriatric Assessment (CGA) is the gold standard for detecting frailty in elderly patients with cancer. Since CGA is time- and resource-consuming, many...
BACKGROUND
Comprehensive Geriatric Assessment (CGA) is the gold standard for detecting frailty in elderly patients with cancer. Since CGA is time- and resource-consuming, many alternative frailty screening tools have been developed; however, it remains unknown whether these tools are suitable for older and adult patients with cancer. Therefore, we used the data collected for a large longitudinal study to compare the diagnostic performances of two frailty screening tools (Geriatric 8 [G8] and Flemish version of the Triage Risk Screening Tool [fTRST]) to identify frailty risk profile among patients with cancer.
METHODS
Patients aged ≥20 years with newly diagnosed cancer were enrolled. Frailty screening with G8, fTRST, and CGA were performed before anti-cancer treatment. Diagnostic characteristics obtained using G8 and fTRST were analyzed by C-index, and the validity of G8 and fTRST was also determined.
RESULTS
40.9% of the 755 patients with cancer displayed frailty on CGA. Both G8 and fTRST showed high sensitivity (80.6-88.4%) and negative predictive value (81.0-81.2%). The C-index of G8 was higher than that of fTRST (0.77 vs 0.71, p = .01). Moreover, the best G8 and fTRST cut-off points were ≤13 and ≥ 2, respectively. The validities of G8 and fTRST were also confirmed; however, frailty age differences were not observed in our study.
CONCLUSION
Frailty is a common problem for patients with cancer, and routine frailty screening is essential for both older and adult patients. G8 and fTRST are simple and useful frailty screening tools, while G8 is more suitable than fTRST for Taiwanese patients with cancer.
Topics: Aged; Early Detection of Cancer; Frailty; Geriatric Assessment; Humans; Longitudinal Studies; Neoplasms; Taiwan
PubMed: 35550341
DOI: 10.1016/j.bj.2021.03.002 -
Chest Nov 2021Cryobiopsy enables specialists to perform high-quality, large, entirely circumferential biopsies; therefore, it may improve the diagnostic yield of peripheral pulmonary... (Observational Study)
Observational Study
BACKGROUND
Cryobiopsy enables specialists to perform high-quality, large, entirely circumferential biopsies; therefore, it may improve the diagnostic yield of peripheral pulmonary lesions (PPLs), as has been previously observed regarding endobronchial tumors and interstitial lung diseases.
RESEARCH QUESTION
How do the diagnostic accuracy and safety change by cryobiopsy when performed alongside conventional biopsy for PPLs?
STUDY DESIGN AND METHODS
Consecutive patients who underwent cryobiopsy in addition to conventional biopsies for PPL diagnosis at our institution between June 2017 and May 2018 were reviewed retrospectively. The target location was estimated and sampling was performed using conventional devices (ie, forceps, brush, aspiration needle), and cryobiopsy was performed at the same location. Diagnostic outcomes and cryobiopsy safety when performed in addition to conventional sampling methods were analyzed in this observational study.
RESULTS
In total, 257 patients were analyzed, and the overall diagnostic yield was 89.9%. Among them, 22 lesions were diagnosable by cryobiopsy exclusively, which improved the rate of diagnosis by 8.6%. Advantages of the use of cryobiopsy were the most apparent when lesions were adjacent to areas assessed via radial endobronchial ultrasound (69.4% vs 84.3%). Multivariable analysis identified bronchus sign (positive/negative, P = .001), lobe (other lobes/right upper lobe and left upper segment, P = .028), and visibility on radiograph (visible/invisible, P = .047) as factors that significantly affected diagnostic yield. On the other hand, three instances of severe hemorrhage (1.2%) and two of pneumothorax (0.8%) occurred. Although most complications were minor, two patients required hospitalization because of cerebral infarction and lung abscess.
INTERPRETATION
Cryobiopsy improves the diagnostic yield of PPLs when combined with other conventional sampling methods; however, caution is required because of the possibility of complications.
Topics: Bronchial Neoplasms; Cryosurgery; Female; Humans; Image-Guided Biopsy; Lung; Lung Diseases, Interstitial; Male; Middle Aged; Reproducibility of Results; Sensitivity and Specificity; Ultrasonography, Interventional
PubMed: 34022184
DOI: 10.1016/j.chest.2021.05.015 -
Diagnostics (Basel, Switzerland) May 2023Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), causing a disease called COVID-19, is a class of acute respiratory syndrome that has considerably affected... (Review)
Review
Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), causing a disease called COVID-19, is a class of acute respiratory syndrome that has considerably affected the global economy and healthcare system. This virus is diagnosed using a traditional technique known as the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, RT-PCR customarily outputs a lot of false-negative and incorrect results. Current works indicate that COVID-19 can also be diagnosed using imaging resolutions, including CT scans, X-rays, and blood tests. Nevertheless, X-rays and CT scans cannot always be used for patient screening because of high costs, radiation doses, and an insufficient number of devices. Therefore, there is a requirement for a less expensive and faster diagnostic model to recognize the positive and negative cases of COVID-19. Blood tests are easily performed and cost less than RT-PCR and imaging tests. Since biochemical parameters in routine blood tests vary during the COVID-19 infection, they may supply physicians with exact information about the diagnosis of COVID-19. This study reviewed some newly emerging artificial intelligence (AI)-based methods to diagnose COVID-19 using routine blood tests. We gathered information about research resources and inspected 92 articles that were carefully chosen from a variety of publishers, such as IEEE, Springer, Elsevier, and MDPI. Then, these 92 studies are classified into two tables which contain articles that use machine Learning and deep Learning models to diagnose COVID-19 while using routine blood test datasets. In these studies, for diagnosing COVID-19, Random Forest and logistic regression are the most widely used machine learning methods and the most widely used performance metrics are accuracy, sensitivity, specificity, and AUC. Finally, we conclude by discussing and analyzing these studies which use machine learning and deep learning models and routine blood test datasets for COVID-19 detection. This survey can be the starting point for a novice-/beginner-level researcher to perform on COVID-19 classification.
PubMed: 37238232
DOI: 10.3390/diagnostics13101749 -
Computational and Mathematical Methods... 2022Breast cancer incidence has been rising steadily during the past few decades. It is the second leading cause of death in women. If it is diagnosed early, there is a good... (Comparative Study)
Comparative Study
Breast cancer incidence has been rising steadily during the past few decades. It is the second leading cause of death in women. If it is diagnosed early, there is a good possibility of recovery. Mammography is proven to be an excellent screening technique for breast tumor diagnosis, but its detection and classification in mammograms remain a significant challenge. Previous studies' major limitation is an increase in false positive ratio (FPR) and false negative ratio (FNR), as well as a drop in Matthews correlation coefficient (MCC) value. A model that can lower FPR and FNR while increasing MCC value is required. To overcome prior research limitations, a modified network of YOLOv5 is used in this study to detect and classify breast tumors. Our research is conducted using publicly available datasets Curated Breast Imaging Subset of DDSM (CBIS-DDSM). The first step is to perform preprocessing, which includes image enhancing techniques and the removal of pectoral muscles and labels. The dataset is then annotated, augmented, and divided into 60% for training, 30% for validation, and 10% for testing. The experiment is then performed using a batch size of 8, a learning rate of 0.01, a momentum of 0.843, and an epoch value of 300. To evaluate the performance of our proposed model, our proposed model is compared with YOLOv3 and faster RCNN. The results show that our proposed model performs better than YOLOv3 and faster RCNN with 96% mAP, 93.50% MCC value, 96.50% accuracy, 0.04 FPR, and 0.03 FNR value. The results show that our suggested model successfully identifies and classifies breast tumors while also overcoming previous research limitations by lowering the FPR and FNR and boosting the MCC value.
Topics: Breast; Breast Neoplasms; Computational Biology; Databases, Factual; Diagnosis, Computer-Assisted; False Negative Reactions; False Positive Reactions; Female; Humans; Machine Learning; Mammography; Neural Networks, Computer; Radiographic Image Enhancement; Sensitivity and Specificity
PubMed: 35027940
DOI: 10.1155/2022/1359019 -
Journal of Clinical Pathology Nov 2021An increasing number of small pulmonary nodules are being screened by CT, and an intraoperative diagnosis is necessary for preventing excessive treatment. However, there...
AIMS
An increasing number of small pulmonary nodules are being screened by CT, and an intraoperative diagnosis is necessary for preventing excessive treatment. However, there is limited literature on the frozen diagnosis of small sclerosing pneumocytomas (SPs). In particular, tumours smaller than 1 cm are challenging for pathologists performing intraoperative frozen diagnosis.
METHODS
In total, 230 cases of SP were surgically resected between January 2015 and March 2019 at Shanghai Chest Hospital, and of them, 76 cases were smaller than 1 cm. The histology and clinical information of these 76 cases (33.0%, 76/230) were reviewed retrospectively, 54 cases of which were diagnosed intraoperatively, and the pitfalls were summarised. All diagnoses were confirmed on permanent sections and immunohistochemical sections.
RESULTS
Histologically, 78.9% (60/76) of the small SP was dominated by one growth pattern, and solid and papillary growth pattern were the most commonly misdiagnosed circumstances. The rate of intraoperative misdiagnosis of these SP smaller than 1 cm was 11.1% (6/54).
CONCLUSIONS
The main reason for misdiagnosis was failure to recognise the dual cell populations and the cellular atypia. Diagnostic clues include the gross morphology, the presence of dual-cell populations and a hypercellular papillary core, foam cell accumulation in glandular spaces and haemorrhage and haemosiderin on the periphery. In spite of awareness of pitfalls some cases may still be essentially impossible to diagnose on frozen section.
Topics: Adult; Aged; Cytodiagnosis; Diagnosis, Differential; Diagnostic Errors; Female; Frozen Sections; Humans; Intraoperative Period; Lung Neoplasms; Male; Middle Aged; Multiple Pulmonary Nodules; Retrospective Studies; Sclerosis; Sensitivity and Specificity; Solitary Pulmonary Nodule
PubMed: 33782195
DOI: 10.1136/jclinpath-2020-206729 -
Proceedings of the National Academy of... Jan 2020Engaging in altruistic behaviors is costly, but it contributes to the health and well-being of the performer of such behaviors. The present research offers a take on how...
Engaging in altruistic behaviors is costly, but it contributes to the health and well-being of the performer of such behaviors. The present research offers a take on how this paradox can be understood. Across 2 pilot studies and 3 experiments, we showed a pain-relieving effect of performing altruistic behaviors. Acting altruistically relieved not only acutely induced physical pain among healthy adults but also chronic pain among cancer patients. Using functional MRI, we found that after individuals performed altruistic actions brain activity in the dorsal anterior cingulate cortex and bilateral insula in response to a painful shock was significantly reduced. This reduced pain-induced activation in the right insula was mediated by the neural activity in the ventral medial prefrontal cortex (VMPFC), while the activation of the VMPFC was positively correlated with the performer's experienced meaningfulness from his or her altruistic behavior. Our findings suggest that incurring personal costs to help others may buffer the performers from unpleasant conditions.
Topics: Adult; Aged; Altruism; Brain; Brain Mapping; Cerebral Cortex; Female; Gyrus Cinguli; Humans; Magnetic Resonance Imaging; Male; Middle Aged; Nervous System Physiological Phenomena; Pain; Pilot Projects; Prefrontal Cortex; Young Adult
PubMed: 31888986
DOI: 10.1073/pnas.1911861117 -
A Deep Multi-Label Segmentation Network For Eosinophilic Esophagitis Whole Slide Biopsy Diagnostics.Annual International Conference of the... Jul 2022Eosinophilic esophagitis (EoE) is an allergic inflammatory condition of the esophagus associated with elevated numbers of eosinophils. Disease diagnosis and monitoring...
Eosinophilic esophagitis (EoE) is an allergic inflammatory condition of the esophagus associated with elevated numbers of eosinophils. Disease diagnosis and monitoring require determining the concentration of eosinophils in esophageal biopsies, a time-consuming, tedious and somewhat subjective task currently performed by pathologists. Here, we developed a machine learning pipeline to identify, quantitate and diagnose EoE patients' at the whole slide image level. We propose a platform that combines multi-label segmentation deep network decision support system with dynamics convolution that is able to process whole biopsy slide. Our network is able to segment both intact and not-intact eosinophils with a mean intersection over union (mIoU) of 0.93. This segmentation enables the local quantification of intact eosinophils with a mean absolute error of 0.611 eosinophils. We examined a cohort of 1066 whole slide images from 400 patients derived from multiple institutions. Using this set, our model achieved a global accuracy of 94.75%, sensitivity of 94.13%, and specificity of 95.25% in reporting EoE disease activity. Our work provides state-of-the-art performances on the largest EoE cohort to date, and successfully addresses two of the main challenges in EoE diagnostics and digital pathology, the need to detect several types of small features simultaneously, and the ability to analyze whole slides efficiently. Our results pave the way for an automated diagnosis of EoE and can be utilized for other conditions with similar challenges.
Topics: Biopsy; Eosinophilic Esophagitis; Humans; Leukocyte Count; Records
PubMed: 36085661
DOI: 10.1109/EMBC48229.2022.9871086 -
Pediatric Research Oct 2022Lung ultrasound (LUS) for critical patients requires trained operators to perform them, though little information exists on the level of training required for...
BACKGROUND
Lung ultrasound (LUS) for critical patients requires trained operators to perform them, though little information exists on the level of training required for independent practice. The aims were to implement a training plan for diagnosing pneumonia using LUS and to analyze the inter-observer agreement between senior radiologists (SRs) and pediatric intensive care physicians (PICPs).
METHODS
Prospective longitudinal and interventional study conducted in the Pediatric Intensive Care Unit of a tertiary hospital. Following a theoretical and practical training plan regarding diagnosing pneumonia using LUS, the concordance between SRs and the PICPs on their LUS reports was analyzed.
RESULTS
Nine PICPs were trained and tested on both theoretical and practical LUS knowledge. The mean exam mark was 13.5/15. To evaluate inter-observer agreement, a total of 483 LUS were performed. For interstitial syndrome, the global Kappa coefficient (K) was 0.51 (95% CI 0.43-0.58). Regarding the presence of consolidation, K was 0.67 (95% CI 0.53-0.78), and for the consolidation pattern, K was 0.82 (95% CI 0.79-0.85), showing almost perfect agreement.
CONCLUSIONS
Our training plan allowed PICPs to independently perform LUS and might improve pneumonia diagnosis. We found a high inter-observer agreement between PICPs and SRs in detecting the presence and type of consolidation on LUS.
IMPACT
Lung ultrasound (LUS) has been proposed as an alternative to diagnose pneumonia in children. However, the adoption of LUS in clinical practice has been slow, and it is not yet included in general clinical guidelines. The results of this study show that the implementation of a LUS training program may improve pneumonia diagnosis in critically ill patients. The training program's design, implementation, and evaluation are described. The high inter-observer agreement between LUS reports from the physicians trained and expert radiologists encourage the use of LUS not only for pneumonia diagnosis, but also for discerning bacterial and viral patterns.
Topics: Child; Humans; Prospective Studies; Pneumonia; Lung; Ultrasonography; Lung Diseases
PubMed: 34969992
DOI: 10.1038/s41390-021-01928-2 -
BMC Medical Informatics and Decision... Sep 2023One of the most common sleep disorders is sleep apnea syndrome. To diagnose sleep apnea syndrome, polysomnography is typically used, but it has limitations in terms of...
BACKGROUND
One of the most common sleep disorders is sleep apnea syndrome. To diagnose sleep apnea syndrome, polysomnography is typically used, but it has limitations in terms of labor, cost, and time. Therefore, studies have been conducted to develop automated detection algorithms using limited biological signals that can be more easily diagnosed. However, the lack of information from limited signals can result in uncertainty from artificial intelligence judgments. Therefore, we performed selective prediction by using estimated respiratory signals from electrocardiogram and oxygen saturation signals based on confidence scores to classify only those sleep apnea occurrence samples with high confidence. In addition, for samples with high uncertainty, this algorithm rejected them, providing a second opinion to the clinician.
METHOD
Our developed model utilized polysomnography data from 994 subjects obtained from Massachusetts General Hospital. We performed feature extraction from the latent vector using the autoencoder. Then, one dimensional convolutional neural network-long short-term memory (1D CNN-LSTM) was designed and trained to measure confidence scores for input, with an additional selection function. We set a confidence score threshold called the target coverage and performed optimization only on samples with confidence scores higher than the target coverage. As a result, we demonstrated that the empirical coverage trained in the model converged to the target coverage.
RESULT
To confirm whether the model has been optimized according to the objectives, the coverage violation was used to measure the difference between the target coverage and the empirical coverage. As a result, the value of coverage violation was found to be an average of 0.067. Based on the model, we evaluated the classification performance of sleep apnea and confirmed that it achieved 90.26% accuracy, 91.29% sensitivity, and 89.21% specificity. This represents an improvement of approximately 7.03% in all metrics compared to the performance achieved without using a selective prediction.
CONCLUSION
This algorithm based on selective prediction utilizes confidence measurement method to minimize the problem caused by limited biological information. Based on this approach, this algorithm is applicable to wearable devices despite low signal quality and can be used as a simple detection method that determine the need for polysomnography or complement it.
Topics: Humans; Artificial Intelligence; Algorithms; Benchmarking; Electrocardiography; Sleep Apnea Syndromes
PubMed: 37735681
DOI: 10.1186/s12911-023-02292-3