-
World Journal of Emergency Surgery :... Dec 2023To assess the efficacy of artificial intelligence (AI) models in diagnosing and prognosticating acute appendicitis (AA) in adult patients compared to traditional... (Review)
Review
BACKGROUND
To assess the efficacy of artificial intelligence (AI) models in diagnosing and prognosticating acute appendicitis (AA) in adult patients compared to traditional methods. AA is a common cause of emergency department visits and abdominal surgeries. It is typically diagnosed through clinical assessments, laboratory tests, and imaging studies. However, traditional diagnostic methods can be time-consuming and inaccurate. Machine learning models have shown promise in improving diagnostic accuracy and predicting outcomes.
MAIN BODY
A systematic review following the PRISMA guidelines was conducted, searching PubMed, Embase, Scopus, and Web of Science databases. Studies were evaluated for risk of bias using the Prediction Model Risk of Bias Assessment Tool. Data points extracted included model type, input features, validation strategies, and key performance metrics.
RESULTS
In total, 29 studies were analyzed, out of which 21 focused on diagnosis, seven on prognosis, and one on both. Artificial neural networks (ANNs) were the most commonly employed algorithm for diagnosis. Both ANN and logistic regression were also widely used for categorizing types of AA. ANNs showed high performance in most cases, with accuracy rates often exceeding 80% and AUC values peaking at 0.985. The models also demonstrated promising results in predicting postoperative outcomes such as sepsis risk and ICU admission. Risk of bias was identified in a majority of studies, with selection bias and lack of internal validation being the most common issues.
CONCLUSION
AI algorithms demonstrate significant promise in diagnosing and prognosticating AA, often surpassing traditional methods and clinical scores such as the Alvarado scoring system in terms of speed and accuracy.
Topics: Adult; Humans; Artificial Intelligence; Appendicitis; Prognosis; Algorithms; Machine Learning; Acute Disease
PubMed: 38114983
DOI: 10.1186/s13017-023-00527-2 -
Ophthalmic Plastic and Reconstructive... Dec 2023Thyroid eye disease (TED) is the most common extrathyroidal manifestation of Graves disease. Patients may be severely affected with eyelid retraction, exophthalmos,... (Review)
Review
PURPOSE
Thyroid eye disease (TED) is the most common extrathyroidal manifestation of Graves disease. Patients may be severely affected with eyelid retraction, exophthalmos, diplopia, pain, and threatened vision. Autoantibodies against thyroid-stimulating hormone receptor and insulin-like growth factor 1 receptor have shown associations with pathophysiological and clinical traits. Autoantibodies against thyroid-stimulating hormone receptor is in current clinical use as biomarker, but not with unambiguous diagnostic performance. A biomarker with high diagnostic accuracy and/or prognostic capability would be of immense value in diagnosing TED, especially in subclinical cases or when TED precedes the thyroid dysfunction. This article is a literature review on molecular biomarkers of TED.
METHODS
A literature search was performed using PubMed and Embase. Studies on molecular biomarkers in blood, tear fluid, and urine were included in the review.
RESULTS
Forty-six papers were included, of which 30, 14, and 2 studies on biomarkers in blood, tears, and urine, respectively. Fourteen of the papers evaluated the diagnostic performance of various biomarkers, 12 in blood and 2 in tears. Most studies evaluated single biomarkers, but 3 tested a panel of several markers. Except for autoantibodies against thyroid-stimulating hormone receptor, the reported diagnostic performances for the biomarkers were not confirmed in independent cohorts. In 32 studies, no or insufficient performance data were given, but the findings indicated involvement of various biologic mechanisms in TED including inflammation, oxidative stress, fibrosis, lipid metabolism, and ocular surface microflora.
CONCLUSIONS
Currently, serum autoantibodies against thyroid-stimulating hormone receptor is the only molecular biomarker with clinical utility in patients with TED. Several potential biomarkers have been investigated, and particularly panels of multiple biomarkers in tears are promising. To improve patient care, biomarkers in TED should be studied further.
Topics: Humans; Graves Ophthalmopathy; Biomarkers; Graves Disease; Autoantibodies; Thyrotropin
PubMed: 38054982
DOI: 10.1097/IOP.0000000000002466 -
BMC Medical Ethics Oct 2023The introduction and wide application of non-invasive prenatal testing (NIPT) has triggered further evolution of routines in the practice of prenatal diagnosis....
BACKGROUND
The introduction and wide application of non-invasive prenatal testing (NIPT) has triggered further evolution of routines in the practice of prenatal diagnosis. 'Routinization' of prenatal diagnosis however has been associated with hampered informed choice and eugenic attitudes or outcomes. It is viewed, at least in some countries, with great suspicion in both bioethics and public discourse. However, it is a heterogeneous phenomenon that needs to be scrutinized in the wider context of social practices of reproductive genetics. In different countries with their different regulatory frameworks, different patterns of routines emerge that have different ethical implications. This paper discusses an ethics of routines informed by the perspectives of organizational sociology and psychology, where a routine is defined as a repetitive, recognizable pattern of interdependent organizational actions that is carried out by multiple performers. We favour a process approach that debunks the view - which gives way to most of the concerns - that routines are always blindly performed. If this is so, routines are therefore not necessarily incompatible with responsible decision-making. Free and informed decision-making can, as we argue, be a key criterion for the ethical evaluation of testing routines. If free and informed decision-making by each pregnant woman is the objective, routines in prenatal testing may not be ethically problematic, but rather are defensible and helpful. We compare recent experiences of NIPT routines in the context of prenatal screening programmes in Germany, Israel and the Netherlands. Notable variation can be observed between these three countries (i) in the levels of routinization around NIPT, (ii) in the scope of routinization, and (iii) in public attitudes toward routinized prenatal testing.
CONCLUSION
An ethics of routines in the field of prenatal diagnostics should incorporate and work with the necessary distinctions between levels and forms of routines, in order to develop sound criteria for their evaluation.
Topics: Pregnancy; Female; Humans; Genetic Testing; Prenatal Diagnosis; Pregnant Women; Attitude; Reproduction
PubMed: 37884894
DOI: 10.1186/s12910-023-00970-5 -
Cureus Jul 2023Diagnosing dental caries plays a pivotal role in preventing and treating tooth decay. However, traditional methods of diagnosing caries often fall short in accuracy and... (Review)
Review
Diagnosing dental caries plays a pivotal role in preventing and treating tooth decay. However, traditional methods of diagnosing caries often fall short in accuracy and efficiency. Despite the endorsement of radiography as a diagnostic tool, the identification of dental caries through radiographic images can be influenced by individual interpretation. Incorporating artificial intelligence (AI) into diagnosing dental caries holds significant promise, potentially enhancing the precision and efficiency of diagnoses. This review introduces the fundamental concepts of AI, including machine learning and deep learning algorithms, and emphasizes their relevance and potential contributions to the diagnosis of dental caries. It further explains the process of gathering and pre-processing radiography data for AI examination. Additionally, AI techniques for dental caries diagnosis are explored, focusing on image processing, analysis, and classification models for predicting caries risk and severity. Deep learning applications in dental caries diagnosis using convolutional neural networks are presented. Furthermore, the integration of AI systems into dental practice is discussed, including the challenges and considerations for implementation as well as ethical and legal aspects. The breadth of AI technologies and their prospective utility in clinical scenarios for diagnosing dental caries from dental radiographs is presented. This review outlines the advancements of AI and its potential in revolutionizing dental caries diagnosis, encouraging further research and development in this rapidly evolving field.
PubMed: 37575741
DOI: 10.7759/cureus.41694 -
Journal of Infection in Developing... Nov 2023Accurate identification of pathogens that cause pulmonary infections is essential for effective treatment and hastening recovery in adults diagnosed with pneumonia. At...
INTRODUCTION
Accurate identification of pathogens that cause pulmonary infections is essential for effective treatment and hastening recovery in adults diagnosed with pneumonia. At present, despite metagenomic next-generation sequencing (mNGS) technology has been widely used in clinical practice for pathogen identification, the clinical significance and necessity of detecting pathogen in bronchoalveolar lavage fluid (BALF) for pneumonia-stricken adults remain ambiguous.
METHODOLOGY
In this study, 80 patients suffering from pulmonary infection were enrolled, who were admitted to the Affiliated Changzhou Second People's Hospital of Nanjing Medical University between January 2020 and September 2022. The diagnostic performances of mNGS and conventional methods (CM) were systematically analyzed based on BALF samples, and we further investigated the influence of mNGS and CM in diagnosis modification and treatment.
RESULTS
We found a significantly higher positive rate for the mNGS method in contrast to CM. Bacteria were the most common pathogens, and Streptococcus pneumoniae was the most commonly identified pathogen. Candida albicans and Epstein-Barr virus were the most frequently identified fungus and virus. Atypical pathogens such as Mycobacterium tuberculosis, virus Nontuberculous mycobacteria, and Chlamydia psittaci were also identified. A total of 77 patients were identified with mixed infections by mNGS. As the disease progressed and recurrent antibiotic treatment persisted, significant dynamic changes in the clinical manifestation from the BALF samples could be found by mNGS.
CONCLUSIONS
This study underscores the efficacy of mNGS in detecting pathogens in BALF samples from patients suffering pulmonary infections. Compared with the CM, mNGS significantly enhanced the positive diagnosis ratio, particularly in diagnosing Mycobacterium tuberculosis, atypical pathogens, and viral or fungal infections.
Topics: Adult; Humans; Epstein-Barr Virus Infections; Herpesvirus 4, Human; Pneumonia; High-Throughput Nucleotide Sequencing; Streptococcus pneumoniae; Mycobacterium tuberculosis; Sensitivity and Specificity
PubMed: 38064390
DOI: 10.3855/jidc.18696 -
ESC Heart Failure Aug 2023The HFA-PEFF algorithm (Heart Failure Association-Pre-test assessment, Echocardiography and natriuretic peptide score, Functional testing in cases of uncertainty, Final...
AIMS
The HFA-PEFF algorithm (Heart Failure Association-Pre-test assessment, Echocardiography and natriuretic peptide score, Functional testing in cases of uncertainty, Final aetiology) is a three-step algorithm to diagnose heart failure with preserved ejection fraction (HFpEF). It provides a three-level likelihood of HFpEF: low (score < 2), intermediate (score 2-4), or high (score > 4). HFpEF may be confirmed in individuals with a score > 4 (rule-in approach). The second step of the algorithm is based on echocardiographic features and natriuretic peptide levels. The third step implements diastolic stress echocardiography (DSE) for controversial diagnostic cases. We sought to validate the three-step HFA-PEFF algorithm against a haemodynamic diagnosis of HFpEF based on rest and exercise right heart catheterization (RHC).
METHODS AND RESULTS
Seventy-three individuals with exertional dyspnoea underwent a full diagnostic work-up following the HFA-PEFF algorithm, including DSE and rest/exercise RHC. The association between the HFA-PEFF score and a haemodynamic diagnosis of HFpEF, as well as the diagnostic performance of the HFA-PEFF algorithm vs. RHC, was assessed. The diagnostic performance of left atrial (LA) strain < 24.5% and LA strain/E/E' < 3% was also assessed. The probability of HFpEF was low/intermediate/high in 8%/52%/40% of individuals at the second step of the HFA-PEFF algorithm and 8%/49%/43% at the third step. After RHC, 89% of patients were diagnosed as HFpEF and 11% as non-cardiac dyspnoea. The HFA-PEFF score resulted associated with the invasive haemodynamic diagnosis of HFpEF (P < 0.001). Sensitivity and specificity of the HFA-PEFF score for the invasive haemodynamic diagnosis of HFpEF were 45% and 100% for the second step of the algorithm and 46% and 88% for the third step of the algorithm. Neither age, sex, body mass index, obesity, chronic obstructive pulmonary disease, or paroxysmal atrial fibrillation influenced the performance of the HFA-PEFF algorithm, as these characteristics were similarly distributed over the true positive, true negative, false positive, and false negative cases. Sensitivity of the second step of the HFA-PEFF score was non-significantly improved to 60% (P = 0.08) by lowering the rule-in threshold to >3. LA strain alone had a sensitivity and specificity of 39% and 14% for haemodynamic HFpEF, increasing to 55% and 22% when corrected for E/E'.
CONCLUSIONS
As compared with rest/exercise RHC, the HFA-PEFF score lacks sensitivity: Half of the patients were wrongly classified as non-cardiac dyspnoea after non-invasive tests, with a minimal impact of DSE in modifying HFpEF likelihood.
Topics: Humans; Heart Failure; Stroke Volume; Hemodynamics; Natriuretic Peptides; Dyspnea; Algorithms
PubMed: 37321596
DOI: 10.1002/ehf2.14436 -
Clinics (Sao Paulo, Brazil) 2024Autism Spectrum Disorder (ASD) is a heterogeneous neurodevelopmental disorder, with main manifestations related to communication, social interaction, and behavioral... (Meta-Analysis)
Meta-Analysis Review
INTRODUCTION
Autism Spectrum Disorder (ASD) is a heterogeneous neurodevelopmental disorder, with main manifestations related to communication, social interaction, and behavioral patterns. The slight dynamics of change in the child over time require that the onset of clinical manifestations presented by the child be more valued, with the aim of stabilizing the condition. Faced with a variety of methods for diagnosing ASD, the question arises as to which method should be used. This systematic review aims to recommend the best tools to perform screening and diagnosis.
METHODOLOGY
This systematic review followed the PRISMA guidelines. The databases MEDLINE, Embase, CENTRAL (Cochrane), and Lilacs were accessed, and gray and manual searches were performed. The search strategy was created with terms referring to autism and the diagnosis/broad filter. The studies were qualitatively evaluated and quantitatively. Statistical analysis was performed using Meta-diSc-2.0 software, the confidence interval was 95 %.
RESULTS
The M-CHAT-R/F tool demonstrated a sensitivity of 78 % (95 % CI 0.57‒0.91) and specificity of 0.98 (95 % CI 0.88-1.00). The diagnostic tools demonstrated sensitivity and specificity respectively of: ADOS, sensitivity of 87 % (95 % CI 0.79‒0.92) and specificity 75 % (95 % CI 0.73‒0.78); ADI-R demonstrated test sensitivity of 77 % (95 % CI 0.56‒0.90) and specificity 68 % (95 % CI 0.52‒0.81), CARS test sensitivity was 89 % (95 % CI 0.78‒0.95) and specificity 79 % (95 % CI 0.65‒0.88).
CONCLUSION
It is mandatory to apply a screening test, the most recommended being the M-CHAT-R/F. For diagnosis CARS and ADOS are the most recommended tools.
Topics: Child; Humans; Autism Spectrum Disorder; Sensitivity and Specificity; Mass Screening; Communication; Research Design
PubMed: 38484581
DOI: 10.1016/j.clinsp.2023.100323 -
Frontiers in Cellular and Infection... 2024Invasive fungal diseases pose a significant threat to non-neutropenic ICU patients, with and infections being the most common. However, diagnosing these infections in... (Review)
Review
Invasive fungal diseases pose a significant threat to non-neutropenic ICU patients, with and infections being the most common. However, diagnosing these infections in the ICU population remains challenging due to overlapping clinical features, poor sensitivity of blood cultures, and invasive sampling requirements. The classical host criteria for defining invasive fungal disease do not fully apply to ICU patients, leading to missed or delayed diagnoses. Recent advancements have improved our understanding of invasive fungal diseases, leading to revised definitions and diagnostic criteria. However, the diagnostic difficulties in ICU patients remain unresolved, highlighting the need for further research and evidence generation. Invasive candidiasis is the most prevalent form of invasive fungal disease in non-neutropenic ICU patients, presenting as candidemia and deep-seated candidiasis. Diagnosis relies on positive blood cultures or histopathology, while non-culture-based techniques such as beta-D-glucan assay and PCR-based tests show promise. Invasive aspergillosis predominantly manifests as invasive pulmonary aspergillosis in ICU patients, often associated with comorbidities and respiratory deterioration in viral pneumonia. Diagnosis remains challenging due to poor sensitivity of blood cultures and difficulties in performing lung biopsies. Various diagnostic criteria have been proposed, including mycological evidence, clinical/radiological factors and expanded list of host factors. Non-culture-based techniques such as galactomannan assay and PCR-based tests can aid in diagnosis. Antifungal management involves tailored therapy based on guidelines and individual patient factors. The complexity of diagnosing and managing invasive fungal diseases in ICU patients underscore the importance of ongoing research and the need for updated diagnostic criteria and treatment approaches. Invasive fungal disease, Invasive fungal infection, Invasive candidiasis, Invasive aspergillosis, Antifungal drugs.
Topics: Humans; Antifungal Agents; Aspergillosis; Invasive Fungal Infections; Candidiasis, Invasive; Intensive Care Units; Candidiasis
PubMed: 38505289
DOI: 10.3389/fcimb.2024.1256158 -
JAMA Network Open Aug 2023Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal disorder. Routine physical examinations by trained personnel are critical to diagnose severity...
IMPORTANCE
Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal disorder. Routine physical examinations by trained personnel are critical to diagnose severity and monitor curve progression in AIS. In the presence of concerning malformation, radiographs are necessary for diagnosis or follow-up, guiding further management, such as bracing correction for moderate malformation and spine surgery for severe malformation. If left unattended, progressive deterioration occurs in two-thirds of patients, leading to significant health concerns for growing children.
OBJECTIVE
To assess the ability of an open platform application (app) using a validated deep learning model to classify AIS severity and curve type, as well as identify progression.
DESIGN, SETTING, AND PARTICIPANTS
This diagnostic study was performed with data from radiographs and smartphone photographs of the backs of adolescent patients at spine clinics. The ScolioNets deep learning model was developed and validated in a prospective training cohort, then incorporated and tested in the AlignProCARE open platform app in 2022. Ground truths (GTs) included severity, curve type, and progression as manually annotated by 2 experienced spine specialists based on the radiographic examinations of the participants' spines. The GTs and app results were blindly compared with another 2 spine surgeons' assessments of unclothed back appearance. Data were analyzed from October 2022 to February 2023.
EXPOSURE
Acquisitions of unclothed back photographs using a mobile app.
MAIN OUTCOMES AND MEASURES
Outcomes of interest were classification of AIS severity and progression. Quantitative statistical analyses were performed to assess the performance of the deep learning model in classifying the deformity as well as in distinguishing progression during 6-month follow-up.
RESULTS
The training data set consisted of 1780 patients (1295 [72.8%] female; mean [SD] age, 14.3 [3.3] years), and the prospective testing data sets consisted of 378 patients (279 [73.8%] female; mean [SD] age, 14.3 [3.8] years) and 376 follow-ups (294 [78.2%] female; mean [SD] age, 15.6 [2.9] years). The model recommended follow-up with an area under receiver operating characteristic curve (AUC) of 0.839 (95% CI, 0.789-0.882) and considering surgery with an AUC of 0.902 (95% CI, 0.859-0.936), while showing good ability to distinguish among thoracic (AUC, 0.777 [95% CI, 0.745-0.808]), thoracolumbar or lumbar (AUC, 0.760 [95% CI, 0.727-0.791]), or mixed (AUC, 0.860 [95% CI, 0.834-0.887]) curve types. For follow-ups, the model distinguished participants with or without curve progression with an AUC of 0.757 (95% CI, 0.630-0.858). Compared with both surgeons, the model could recognize severities and curve types with a higher sensitivity (eg, sensitivity for recommending follow-up: model, 84.88% [95% CI, 75.54%-91.70%]; senior surgeon, 44.19%; junior surgeon, 62.79%) and negative predictive values (NPVs; eg, NPV for recommending follow-up: model, 89.22% [95% CI, 84.25%-93.70%]; senior surgeon, 71.76%; junior surgeon, 79.35%). For distinguishing curve progression, the sensitivity and NPV were comparable with the senior surgeons (sensitivity, 63.33% [95% CI, 43.86%-80.87%] vs 77.42%; NPV, 68.57% [95% CI, 56.78%-78.37%] vs 72.00%). The junior surgeon reported an inability to identify curve types and progression by observing the unclothed back alone.
CONCLUSIONS
This diagnostic study of adolescent patients screened for AIS found that the deep learning app had the potential for out-of-hospital accessible and radiation-free management of children with scoliosis, with comparable performance as spine surgeons experienced in AIS management.
Topics: Deep Learning; Smartphone; Photography; Humans; Adolescent; Scoliosis; Monitoring, Physiologic; Mobile Applications; Male; Female
PubMed: 37610748
DOI: 10.1001/jamanetworkopen.2023.30617 -
The International Journal of... Aug 2023Spirometry is considered relevant for the diagnosis and monitoring of post-TB lung disease. However, spirometry is rarely done in newly diagnosed TB patients. Newly...
Spirometry is considered relevant for the diagnosis and monitoring of post-TB lung disease. However, spirometry is rarely done in newly diagnosed TB patients. Newly diagnosed, microbiologically confirmed TB patients were recruited for the study. Spirometry was performed within 21 days of TB treatment initiation according to American Thoracic Society/European Respiratory Society guidelines. Spirometry analysis was done using Global Lung Initiative equations for standardisation. Of 1,430 eligible study participants, 24.7% (353/1,430) had no spirometry performed mainly due to contraindications and 23.0% (329/1,430) had invalid results; 52.3% (748/1,430) of participants had a valid result, 82.8% (619/748) of whom had abnormal spirometry. Of participants with abnormal spirometry, 70% (436/619) had low forced vital capacity (FVC), 6.1% (38/619) had a low ratio of forced expiratory volume in 1 sec (FEV) to FVC, and 19.1% (118/619) had low FVC, as well as low FEV/FVC ratio. Among those with abnormal spirometry, 26.3% (163/619) had severe lung impairment. In this population, a high proportion of not performed and invalid spirometry assessments was observed; this was addressed by removing tachycardia as a (relative) contraindication from the study guidance and retraining. The high proportion of patients with severe pulmonary impairment at the time of TB diagnosis suggests a huge morbidity burden and calls for further longitudinal studies on the relevance of spirometry in predicting chronic lung impairment after TB.
Topics: Humans; Tuberculosis; Lung; Spirometry; Vital Capacity; Forced Expiratory Volume
PubMed: 37880896
DOI: 10.5588/ijtld.23.0040