-
Frontiers in Medicine 2022Artificial Intelligence (AI) holds considerable promise for diagnostics in the field of gastroenterology. This systematic review and meta-analysis aims to assess the...
BACKGROUND
Artificial Intelligence (AI) holds considerable promise for diagnostics in the field of gastroenterology. This systematic review and meta-analysis aims to assess the diagnostic accuracy of AI models compared with the gold standard of experts and histopathology for the diagnosis of various gastrointestinal (GI) luminal pathologies including polyps, neoplasms, and inflammatory bowel disease.
METHODS
We searched PubMed, CINAHL, Wiley Cochrane Library, and Web of Science electronic databases to identify studies assessing the diagnostic performance of AI models for GI luminal pathologies. We extracted binary diagnostic accuracy data and constructed contingency tables to derive the outcomes of interest: sensitivity and specificity. We performed a meta-analysis and hierarchical summary receiver operating characteristic curves (HSROC). The risk of bias was assessed using Quality Assessment for Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Subgroup analyses were conducted based on the type of GI luminal disease, AI model, reference standard, and type of data used for analysis. This study is registered with PROSPERO (CRD42021288360).
FINDINGS
We included 73 studies, of which 31 were externally validated and provided sufficient information for inclusion in the meta-analysis. The overall sensitivity of AI for detecting GI luminal pathologies was 91.9% (95% CI: 89.0-94.1) and specificity was 91.7% (95% CI: 87.4-94.7). Deep learning models (sensitivity: 89.8%, specificity: 91.9%) and ensemble methods (sensitivity: 95.4%, specificity: 90.9%) were the most commonly used models in the included studies. Majority of studies ( = 56, 76.7%) had a high risk of selection bias while 74% ( = 54) studies were low risk on reference standard and 67% ( = 49) were low risk for flow and timing bias.
INTERPRETATION
The review suggests high sensitivity and specificity of AI models for the detection of GI luminal pathologies. There is a need for large, multi-center trials in both high income countries and low- and middle- income countries to assess the performance of these AI models in real clinical settings and its impact on diagnosis and prognosis.
SYSTEMATIC REVIEW REGISTRATION
[https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=288360], identifier [CRD42021288360].
PubMed: 36405592
DOI: 10.3389/fmed.2022.1018937 -
Journal of Orthopaedics and... Nov 2022Synovial fluid markers (synovial leukocyte count and differential) have been shown to be most accurate in diagnosing prosthetic joint infection (PJI). An inverse...
BACKGROUND
Synovial fluid markers (synovial leukocyte count and differential) have been shown to be most accurate in diagnosing prosthetic joint infection (PJI). An inverse correlation for synovial leukocyte count and synovial pH is known assuming that leukocyte metabolism causes synovial fluid acidosis. This study's purpose is to analyze the use of synovial pH as a potential diagnostic marker for PJI.
MATERIALS AND METHODS
92 patients who presented with painful total joint arthroplasty (TJA) of the hip (THA; n = 25) or knee (TKA, n = 67) were prospectively investigated. In our cohort 33% (30/92) had PJI and 67% (62/92) were diagnosed non-infected based on the modified Musculoskeletal Infection Society (MSIS) criteria of 2018. Receiver operating curves and the Youden's index were used to define an ideal cut-off value for synovial pH and the sensitivity and specificity were calculated using cross-tables. Additionally, the sensitivity and specificity were calculated for synovial white blood cell (WBC) count (cut-off > 3000 leukocytes) and percentage of neutrophils (PMN%, cut-off > 80%).
RESULTS
The median synovial pH level was significantly lower in the group with chronic PJI compared to implants with aseptic failure (7.09 vs. 7.27; p < 0.001). The calculated optimal cut-off value was 7.11 (AUC 0.771) with a sensitivity of 53% and specificity of 89%. However, the sensitivity and specificity of synovial WBC count were 90% and 88% and for synovial PMN% 73% and 98%, respectively.
CONCLUSION
Synovial pH may be a useful adjunct parameter in the diagnosis of chronic PJI after hip or knee arthroplasty, but showed low sensitivity in this preliminary cohort. Future studies with larger numbers are needed.
LEVEL OF EVIDENCE
2a, diagnostic study. Trial registration German Clinical Trials Register (Registration number: DRKS00021038).
Topics: Humans; Synovial Fluid; Prosthesis-Related Infections; Arthritis, Infectious; Leukocyte Count; Arthroplasty, Replacement, Knee; Hydrogen-Ion Concentration
PubMed: 36402933
DOI: 10.1186/s10195-022-00672-5 -
American Journal of Infection Control Jul 2023Airborne contamination from microbe carrying particles (MCPs) is a risk factor for devastating early onset periprosthetic joint infection(PJIs). There are no published... (Observational Study)
Observational Study
Observational study of sterile field bioburden levels during orthopedic arthroplasty surgery in operating rooms complying with current United States ventilation specifications.
BACKGROUND
Airborne contamination from microbe carrying particles (MCPs) is a risk factor for devastating early onset periprosthetic joint infection(PJIs). There are no published guidelines to quantify this risk factor for PJI events. This observational cohort project addresses this gap and utilizes a simple passive system to produce quantitative data from 80 total joint replacement cases performed in operating rooms built to current USA standards.
METHODS
A petri dish-based system inspired by industrial cleanroom technology was deployed. Surgical helmet systems (SHSs) and strict protocols were used in all cases. 450 MCPs/m was used as a cutoff for bioburden. This benchmark corresponds to the ultraclean air standard of 10 MCPs/m.
RESULTS
75/80 cases (94%) achieved desired benchmark levels of bioburden at the wound zone compared to only 52/80 (65%) of back table zones. No surgical site infections (SSI) or PJI events (0/80; 95% CI, 0.00-3.68%) at minimum 18-month (average 25.8 months) follow-up were detected.
DISCUSSION
The current USA ventilation design uses low velocity airflow and appears to achieve ultraclean air conditions at the surgical site but requires SHSs and strict protocols. Higher contamination levels seen in back tables are consistent with this design.
CONCLUSIONS
This settle plate system may be useful for early onset PJI event investigations and thus lower the incidence of these complications.
Topics: Humans; Operating Rooms; Ventilation; Arthroplasty, Replacement; Environment, Controlled; Air Conditioning; Surgical Wound Infection; Air Microbiology
PubMed: 36375706
DOI: 10.1016/j.ajic.2022.10.016 -
Sensors (Basel, Switzerland) Nov 2022The occurrence of landslides has been increasing in recent years due to intense and prolonged rainfall events. Lowering the groundwater in natural and man-made slopes...
The occurrence of landslides has been increasing in recent years due to intense and prolonged rainfall events. Lowering the groundwater in natural and man-made slopes can help to mitigate the hazards. Subsurface drainage systems equipped with pumps have traditionally been regarded as a temporary remedy for lowering the groundwater in geosystems, whereas long-term usage of pumping-based techniques is uncommon due to the associated high operational costs in labor and energy. This study investigates the intelligent control of groundwater in slopes enabled by deep reinforcement learning (DRL), a subfield of machine learning for automated decision-making. The purpose is to develop an autonomous geosystem that can minimize the operating cost and enhance the system's safety without introducing human errors and interventions. To prove the concept, a seepage analysis model was implemented using a partial differential equation solver, FEniCS, to simulate the geosystem (i.e., a slope equipped with a pump and subjected to rainfall events). A Deep Q-Network (i.e., a DRL learning agent) was trained to learn the optimal control policy for regulating the pump's flow rate. The objective is to enable intermittent control of the pump's flow rate (i.e., 0%, 25%, 50%, 75%, and 100% of the pumping capacity) to keep the groundwater close to the target level during rainfall events and consequently help to prevent slope failure. A comparison of the results with traditional proportional-integral-derivative-controlled and uncontrolled water tables showed that the geosystem integrated with DRL can dynamically adapt its response to diverse weather events by adjusting the pump's flow rate and improve the adopted control policy by gaining more experience over time. In addition, it was observed that the DRL control helped to mitigate slope failure during rainfall events.
Topics: Humans; Groundwater; Machine Learning
PubMed: 36366203
DOI: 10.3390/s22218503 -
Journal of Multidisciplinary Healthcare 2022The nature of COVID-19 transmission creates significant risks in surgical departments owing to the close contact of medical staff with patients, the limited physical...
BACKGROUND
The nature of COVID-19 transmission creates significant risks in surgical departments owing to the close contact of medical staff with patients, the limited physical environment of the operating room and recovery room, the possibility of shared surgical equipment and challenges in the delivery of surgical care in all surgical departments. Globally, studies have reported that the effects of the pandemic on surgical departments are profound, potentially long-lasting and extensive. To manage these effects, different local guidelines and recommendations have been developed, with potential differences in their effectiveness and implementation. Therefore, harmonized and effective national/international guidelines for specific surgical departments during perioperative periods are pertinent to curtail the infection, and will inevitably need to be adapted for consistent and sustainable implementation by all medical staff. The pattern of surgical patient care during the COVID-19 pandemic at Jimma Medical Center (JMC), Ethiopia, has not been explored yet. The present study aimed to describe the pattern of perioperative surgical patient care, equipment handling and operating room management during the COVID-19 pandemic at JMC.
METHODS
A cross-sectional study was conducted to describe the pattern of perioperative surgical patient care, equipment handling and operating room management during the COVID-19 pandemic at JMC, using five-point Likert scales (0, not at all; 1, rarely; 2, sometimes; 3, most of the time; 4, frequently). A total of 90 respondents [35 patients (five patients from each of seven surgical departments) and 55 healthcare providers (six professionals from each of nine units, including the center of sterility room and anesthesia)] who were available during the study period, selected by a convenience sampling technique with multistage clustering, participated in the study. Data were collected using a structured questionnaire via direct observation and face-to-face interviews with patients undergoing surgery, healthcare providers and hospital administrators, against the standard surgical patient care guidelines. The collected data were manually checked for missing values and outliers, cleared, entered into EpiData (v4.3.1) and exported to SPSS (v22) for analysis. The mean score of practice was compared among different disciplines by applying the unpaired -test. The findings of the study were reported using tables and narration. A -value of less than 0.05 was declared as statistically significant.
RESULTS
Despite the surgical care practice having changed during the COVID-19 pandemic in all service domains, it is not implemented consistently among different surgical departments owing to different barriers (lack of training on the updated guidelines and financial constraints). The majority of surgical staff were implementing the use of preventive measures against COVID-19, while they were practiced less among patients. The guidelines for surgical practice during the preoperative phase were well applied, especially screening patients by different methods and the application of telemedicine to reduce physical contacts. But, against guidelines, elective patients were planned and underwent surgery, especially in the general surgery department. The implementation of recommended guidelines in the center of sterility room in handling surgical equipment was not very different before and during the pandemic. The extent of practice for anesthesia care, operating room management and postoperative care in the recovery room also changed, and the guidelines were sometimes applied.
CONCLUSION AND RECOMMENDATIONS
Although perioperative surgical care practice differed before and during the pandemic, the standard guidelines were inconsistently implemented among surgical departments. The implementation of recommended guidelines in the center of sterility room in handling surgical equipment was not very different before and during the pandemic. Thus, the authors developed safe surgical care guidelines throughout the different domains (infection prevention and PPE use; preoperative care, intraoperative care, operating room management, anesthesia care, equipment handling process and postoperative care) for all disciplines and shared them with all staff. We recommend that all surgical staff should access these guidelines and strictly adhere to them for surgical service during the pandemic.
PubMed: 36352855
DOI: 10.2147/JMDH.S372428 -
International Journal of Cancer Mar 2023Gestational trophoblastic neoplasia (GTN) patients are treated according to the eight-variable International Federation of Gynaecology and Obstetrics (FIGO) scoring...
Gestational trophoblastic neoplasia (GTN) patients are treated according to the eight-variable International Federation of Gynaecology and Obstetrics (FIGO) scoring system, that aims to predict first-line single-agent chemotherapy resistance. FIGO is imperfect with one-third of low-risk patients developing disease resistance to first-line single-agent chemotherapy. We aimed to generate simplified models that improve upon FIGO. Logistic regression (LR) and multilayer perceptron (MLP) modelling (n = 4191) generated six models (M1-6). M1, all eight FIGO variables (scored data); M2, all eight FIGO variables (scored and raw data); M3, nonimaging variables (scored data); M4, nonimaging variables (scored and raw data); M5, imaging variables (scored data); and M6, pretreatment hCG (raw data) + imaging variables (scored data). Performance was compared to FIGO using true and false positive rates, positive and negative predictive values, diagnostic odds ratio, receiver operating characteristic (ROC) curves, Bland-Altman calibration plots, decision curve analysis and contingency tables. M1-6 were calibrated and outperformed FIGO on true positive rate and positive predictive value. Using LR and MLP, M1, M2 and M4 generated small improvements to the ROC curve and decision curve analysis. M3, M5 and M6 matched FIGO or performed less well. Compared to FIGO, most (excluding LR M4 and MLP M5) had significant discordance in patient classification (McNemar's test P < .05); 55-112 undertreated, 46-206 overtreated. Statistical modelling yielded only small gains over FIGO performance, arising through recategorisation of treatment-resistant patients, with a significant proportion of under/overtreatment as the available data have been used a priori to allocate primary chemotherapy. Streamlining FIGO should now be the focus.
Topics: Pregnancy; Female; Humans; Gestational Trophoblastic Disease; Retrospective Studies; Models, Statistical
PubMed: 36346113
DOI: 10.1002/ijc.34352 -
Hypertension Research : Official... Dec 2022Growing epidemiological evidence has shown an association of the urinary sodium (Na) to potassium (K) ratio (Na/K ratio) with blood pressure and cardiovascular diseases.... (Observational Study)
Observational Study
Growing epidemiological evidence has shown an association of the urinary sodium (Na) to potassium (K) ratio (Na/K ratio) with blood pressure and cardiovascular diseases. However, no clear cutoff level has been defined. We investigated the cutoff level of the urinary Na/K ratio under different dietary guidelines for Japanese individuals, especially that endorsed by the 2020 revised Japanese Dietary Reference Intakes (DRIs). A population of 1145 Japanese men and women aged 40 to 59 years from the INTERMAP study was examined. Using high-quality standardized data, the averages of two 24 h urinary collections and four 24 h dietary recalls were used to calculate the 24 h urinary and dietary Na/K ratios, respectively. Associations between the urinary and dietary Na/K ratios were tested by sex- and age-adjusted partial correlation. The optimal urinary Na/K ratio cutoff level was determined by receiver operating characteristic (ROC) curves and sex-specific cross tables for recommended dietary K and salt. Overall, the average molar ratio of 24 h urinary Na/K was 4.3. We found moderate correlations (P < 0.001) of the 24 h urinary Na/K ratio with 24 h urinary Na and K excretion (r = 0.52, r = -0.49, respectively) and the dietary Na/K ratio (r = 0.53). ROC curves showed that a 24 h urinary Na/K ratio of approximately 2 predicted Na and K intake that meets the dietary goals of the Japanese DRIs. The range of urinary Na/K ratios meeting the dietary goals of the Japanese DRIs for both Na and K was 1.6‒2.2 for men and 1.7‒1.9 for women. Accomplishing a urinary Na/K ratio of 2 would be desirable to achieve the DRIs dietary goals for both Na and K simultaneously in middle-aged Japanese men and women accustomed to Japanese dietary habits. This observational study is registered at www.clinicaltrials.gov as NCT00005271.
Topics: Middle Aged; Male; Humans; Female; Japan; Goals; Sodium; Sodium, Dietary; Potassium; Eating
PubMed: 36344663
DOI: 10.1038/s41440-022-01007-x -
Medicine Nov 2022This meta-analysis aimed to explore the diagnostic value of diffusion kurtosis imaging (DKI) compared to mono-exponential diffusion weighted imaging (DWI) in the... (Meta-Analysis)
Meta-Analysis
BACKGROUND
This meta-analysis aimed to explore the diagnostic value of diffusion kurtosis imaging (DKI) compared to mono-exponential diffusion weighted imaging (DWI) in the diagnosis of breast cancer.
METHODS
A systematic electronic literature search (up to September 2020) was conducted for published English-language studies comparing the diagnostic values of DKI and DWI for the detection of breast cancer. The data of mean kurtosis (MK), mean diffusivity (MD), and apparent diffusion coefficient (ADC) were extracted to construct 2 × 2 contingency tables. The pooled sensitivities, specificities, and areas under the receiver operating characteristic curve (AUCs) were compared between DKI and DWI in the diagnosis of breast cancer.
RESULTS
Eight studies were finally included, with a total of 771 patients in the same population. Pooled sensitivities were 82.0% [95% confidence interval (95% CI), 78.2-85.3%] for ADC, 87.3% (95% CI, 83.9-90.1%) for MK, and 83.9% (95% CI, 80.2-87.1%) for MD. Pooled specificities were 81.1% (95% CI, 76.7-84.9%) for ADC, 85.1% (95% CI, 81.1-88.5%) for MK, and 83.2% (95% CI, 79.0-86.8%) for MD. According to the summary receiver operator characteristic curve analyses, the AUCwas 0.901 for ADC, 0.930 for MK, and 0.918 for MD (ADC vs MK, P = .353; ADC vs MD, P = .611). No notable publication bias was found, while significant heterogeneity was observed.
CONCLUSIONS
Although DKI is feasible for identifying breast cancer, MD and MK offer similar diagnostic performance to ADC values. Thus, we recommend that DKI should not be included in the routine evaluation of breast lesions now.
Topics: Humans; Female; Language; Sensitivity and Specificity; Diffusion Magnetic Resonance Imaging; Diffusion Tensor Imaging; Breast Neoplasms
PubMed: 36343063
DOI: 10.1097/MD.0000000000031574 -
Clinical Epigenetics Nov 2022The factors affecting cardioprotective collateral circulation are still incompletely understood. Recently, characteristics, such as CpG methylation of cell-free DNA...
BACKGROUND
The factors affecting cardioprotective collateral circulation are still incompletely understood. Recently, characteristics, such as CpG methylation of cell-free DNA (cfDNA), have been reported as markers with clinical utility. The aim of this study was to evaluate whether cfDNA methylation patterns are associated with the grade of coronary collateral circulation (CCC).
RESULT
In this case-control study, clinical and angiographic data were obtained from 143 patients (mean age, 58 years, male 71%) with chronic total coronary occlusion. Enzymatic methyl-sequencing (EM-seq) libraries were prepared using the cfDNA extracted from the plasma. Data were processed to obtain the average methylation fraction (AMF) tables of genomic regions from which blacklisted regions were removed. Unsupervised analysis of the obtained AMF values showed that some of the changes in methylation were due to CCC. Through random forest preparation process, 256 differentially methylated region (DMR) candidates showing strong association with CCC were selected. A random forest classifier was then constructed, and the area under the curve of the receiver operating characteristic curve indicated an appropriate predictive function for CCC. Finally, 20 DMRs were identified to have significantly different AMF values between the good and poor CCC groups. Particularly, the good CCC group exhibited hypomethylated DMRs. Pathway analysis revealed five pathways, including TGF-beta signaling, to be associated with good CCC.
CONCLUSION
These data have demonstrated that differential hypomethylation was identified in dozens of cfDNA regions in patients with good CCC. Our results support the clinical utility of noninvasively obtained epigenetic signatures for predicting collateral circulation in patients with vascular diseases.
Topics: Humans; Male; Middle Aged; Case-Control Studies; Cell-Free Nucleic Acids; Collateral Circulation; Coronary Artery Disease; DNA Methylation; Female
PubMed: 36320085
DOI: 10.1186/s13148-022-01349-w -
Healthcare (Basel, Switzerland) Sep 2022(1) Background: Cartilage degeneration with the natural aging process and the role of physical activity on cartilage wellness is still not clear. The objective of the... (Review)
Review
(1) Background: Cartilage degeneration with the natural aging process and the role of physical activity on cartilage wellness is still not clear. The objective of the present review was to understand how different physical activity interventions affect the cartilage and to propose a Standard Operating Procedure for an exercise program to maintain knee joint health; (2) Methods: Articles were collected on three different electronic databases and screened against the eligibility criteria. Results were collected in tables and the main outcomes were discussed narratively; (3) Results: A total of 24 studies have been included after the screening process and aerobic, strength, flexibility, postural balance, and mobility interventions were detected. Different protocols and types of interventions were adopted by the authors; (4) Conclusions: Physical activity interventions have mainly positive outcomes on cartilage structure, but the protocols adopted are different and various. A Standard Operating Procedure has been proposed for a physical intervention focalized on cartilage wellness that could be adopted as an intervention in the clinical setting. Furthermore, the creation of a standardized protocol wants to help scientific research to move in the same direction.
PubMed: 36292268
DOI: 10.3390/healthcare10101821