Using Artificial Intelligence to Stratify Normal versus Abnormal Chest X-rays: External Validation of a Deep Learning Algorithm at East Kent Hospitals University NHS Foundation Trust.

Background: The chest radiograph (CXR) is the most frequently performed radiological examination worldwide. The increasing volume of CXRs performed in hospitals causes reporting backlogs and increased waiting times for patients, potentially compromising timely clinical intervention and patient safety. Implementing computer-aided detection (CAD) artificial intelligence (AI) algorithms capable of accurate and rapid CXR reporting could help address such limitations. A novel use for AI reporting is the classification of CXRs as 'abnormal' or 'normal'. This classification could help optimize resource allocation and aid radiologists in managing their time efficiently. Methods: qXR is a CE-marked computer-aided detection (CAD) software trained on over 4.4 million CXRs. In this retrospective cross-sectional pre-deployment study, we evaluated the performance of qXR in stratifying normal and abnormal CXRs. We analyzed 1040 CXRs from various referral sources, including general practices (GP), Accident and Emergency (A&E) departments, and inpatient (IP) and outpatient (OP) settings at East Kent Hospitals University NHS Foundation Trust. The ground truth for the CXRs was established by assessing the agreement between two senior radiologists. Results: The CAD software had a sensitivity of 99.7% and a specificity of 67.4%. The sub-group analysis showed no statistically significant difference in performance across healthcare settings, age, gender, and X-ray manufacturer. Conclusions: The study showed that qXR can accurately stratify CXRs as normal versus abnormal, potentially reducing reporting backlogs and resulting in early patient intervention, which may result in better patient outcomes.

Role of an Automated Deep Learning Algorithm for Reliable Screening of Abnormality in Chest Radiographs: A Prospective Multicenter Quality Improvement Study.

In medical practice, chest X-rays are the most ubiquitous diagnostic imaging tests. However, the current workload in extensive health care facilities and lack of well-trained radiologists is a significant challenge in the patient care pathway. Therefore, an accurate, reliable, and fast computer-aided diagnosis (CAD) system capable of detecting abnormalities in chest X-rays is crucial in improving the radiological workflow. In this prospective multicenter quality-improvement study, we have evaluated whether artificial intelligence (AI) can be used as a chest X-ray screening tool in real clinical settings. Methods: A team of radiologists used the AI-based chest X-ray screening tool (qXR) as a part of their daily reporting routine to report consecutive chest X-rays for this prospective multicentre study. This study took place in a large radiology network in India between June 2021 and March 2022. Results: A total of 65,604 chest X-rays were processed during the study period. The overall performance of AI achieved in detecting normal and abnormal chest X-rays was good. The high negatively predicted value (NPV) of 98.9% was achieved. The AI performance in terms of area under the curve (AUC), NPV for the corresponding subabnormalities obtained were blunted CP angle (0.97, 99.5%), hilar dysmorphism (0.86, 99.9%), cardiomegaly (0.96, 99.7%), reticulonodular pattern (0.91, 99.9%), rib fracture (0.98, 99.9%), scoliosis (0.98, 99.9%), atelectasis (0.96, 99.9%), calcification (0.96, 99.7%), consolidation (0.95, 99.6%), emphysema (0.96, 99.9%), fibrosis (0.95, 99.7%), nodule (0.91, 99.8%), opacity (0.92, 99.2%), pleural effusion (0.97, 99.7%), and pneumothorax (0.99, 99.9%). Additionally, the turnaround time (TAT) decreased by about 40.63% from pre-qXR period to post-qXR period. Conclusions: The AI-based chest X-ray solution (qXR) screened chest X-rays and assisted in ruling out normal patients with high confidence, thus allowing the radiologists to focus more on assessing pathology on abnormal chest X-rays and treatment pathways.

Frequency of Missed Findings on Chest Radiographs (CXRs) in an International, Multicenter Study: Application of AI to Reduce Missed Findings.

BACKGROUND: Missed findings in chest X-ray interpretation are common and can have serious consequences. METHODS: Our study included 2407 chest radiographs (CXRs) acquired at three Indian and five US sites. To identify CXRs reported as normal, we used a proprietary radiology report search engine based on natural language processing (mPower, Nuance). Two thoracic radiologists reviewed all CXRs and recorded the presence and clinical significance of abnormal findings on a 5-point scale (1-not important; 5-critical importance). All CXRs were processed with the AI model (Qure.ai) and outputs were recorded for the presence of findings. Data were analyzed to obtain area under the ROC curve (AUC). RESULTS: Of 410 CXRs (410/2407, 18.9%) with unreported/missed findings, 312 (312/410, 76.1%) findings were clinically important: pulmonary nodules (n = 157), consolidation (60), linear opacities (37), mediastinal widening (21), hilar enlargement (17), pleural effusions (11), rib fractures (6) and pneumothoraces (3). AI detected 69 missed findings (69/131, 53%) with an AUC of up to 0.935. The AI model was generalizable across different sites, geographic locations, patient genders and age groups. CONCLUSION: A substantial number of important CXR findings are missed; the AI model can help to identify and reduce the frequency of important missed findings in a generalizable manner.

Performance of a Chest Radiography AI Algorithm for Detection of Missed or Mislabeled Findings: A Multicenter Study.

Purpose: We assessed whether a CXR AI algorithm was able to detect missed or mislabeled chest radiograph (CXR) findings in radiology reports. Methods: We queried a multi-institutional radiology reports search database of 13 million reports to identify all CXR reports with addendums from 1999-2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addenda were created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs. The remaining reports contained addenda (279 patients) with errors related to side-discrepancies or missed findings such as pulmonary nodules, consolidation, pleural effusions, pneumothorax, and rib fractures. All CXRs were processed with an AI algorithm. Descriptive statistics were performed to determine the sensitivity, specificity, and accuracy of the AI in detecting missed or mislabeled findings. Results: The AI had high sensitivity (96%), specificity (100%), and accuracy (96%) for detecting all missed and mislabeled CXR findings. The corresponding finding-specific statistics for the AI were nodules (96%, 100%, 96%), pneumothorax (84%, 100%, 85%), pleural effusion (100%, 17%, 67%), consolidation (98%, 100%, 98%), and rib fractures (87%, 100%, 94%). Conclusions: The CXR AI could accurately detect mislabeled and missed findings. Clinical Relevance: The CXR AI can reduce the frequency of errors in detection and side-labeling of radiographic findings.

Text Classification for Clinical Trial Operations: Evaluation and Comparison of Natural Language Processing Techniques.

The ability to detect patterns and trends across protocol deviations (PDs) is key to ensure high data quality and sufficient oversight of patient safety. In clinical trial operations, some business processes and work instructions limit efficient protocol deviation trending because a majority of protocol deviations are left unclassified. When this occurs, it restricts clinical teams from determining systemic issues or signals in the data. The unstructured text in protocol deviation descriptions is an important component of trial operation knowledge. Natural language processing (NLP) can make protocol deviation descriptions more accessible and can support information extraction and trending analysis. This paper reviews how the natural language processing techniques of Term-Frequency Inverse-Document-Frequency (TF-IDF) combined with the supervised machine learning model of Support Vector Machines (SVM) and word embedding approaches such as word2vec can be used to categorize/label protocol deviations across multiple therapeutic areas. NLP is a key tool that will lead to more data driven decisions in clinical trial operations.

Predicting and explaining inflammation in Crohn's disease patients using predictive analytics methods and electronic medical record data.

Crohn's disease is among the chronic inflammatory bowel diseases that impact the gastrointestinal tract. Understanding and predicting the severity of inflammation in real-time settings is critical to disease management. Extant literature has primarily focused on studies that are conducted in clinical trial settings to investigate the impact of a drug treatment on the remission status of the disease. This research proposes an analytics methodology where three different types of prediction models are developed to predict and to explain the severity of inflammation in patients diagnosed with Crohn's disease. The results show that machine-learning-based analytic methods such as gradient boosting machines can predict the inflammation severity with a very high accuracy (area under the curve = 92.82%), followed by regularized regression and logistic regression. According to the findings, a combination of baseline laboratory parameters, patient demographic characteristics, and disease location are among the strongest predictors of inflammation severity in Crohn's disease patients.

Predicting hospital readmission for lupus patients: An RNN-LSTM-based deep-learning methodology.

Hospital readmission is one of the critical metrics used for measuring the performance of hospitals. The HITECH Act imposes penalties when patients are readmitted to hospitals if they are diagnosed with one of the six conditions mentioned in the Act. However, patients diagnosed with lupus are the sixth highest in terms of rehospitalization. The heterogeneity in the disease and patient characteristics makes it very hard to predict rehospitalization. This research utilizes deep learning methods to predict rehospitalization within 30 days by extracting the temporal relationships in the longitudinal EHR clinical data. Prediction results from deep learning methods such as LSTM are evaluated and compared with traditional classification methods such as penalized logistic regression and artificial neural networks. The simple recurrent neural network method and its variant, gated recurrent unit network, are also developed and validated to compare their performance against the proposed LSTM model. The results indicated that the deep learning method RNN-LSTM has a significantly better performance (with an AUC of .70) compared to traditional classification methods such as ANN (with an AUC of 0.66) and penalized logistic regression (with an AUC of 0.63). The rationale for the better performance of the deep learning method may be due to its ability to leverage the temporal relationships of the disease state in patients over time and to capture the progression of the disease-relevant clinical information from patients' prior visits is carried forward in the memory, which may have enabled the higher predictability for the deep learning methods.

Dorsal buccal mucosal graft urethroplasty for anterior urethral stricture by Asopa technique.

BACKGROUND: Buccal mucosal graft (BMG) substitution urethroplasty has become popular in the management of intractable anterior urethral strictures with good results. Excellent long-term results have been reported by both dorsal and ventral onlay techniques. Asopa reported a successful technique for dorsal placement of BMG in long anterior urethral strictures through a ventral sagittal approach. OBJECTIVE: To evaluate prospectively the results and advantages of dorsal BMG urethroplasty for recurrent anterior urethral strictures by a ventral sagittal urethrotomy approach (Asopa technique). DESIGN, SETTING, AND PARTICIPANTS: From December 2002 to December 2007, a total of 58 men underwent dorsal BMG urethroplasty by a ventral sagittal urethrotomy approach for recurrent urethral strictures. Forty-five of these patients with a follow-up period of 12-60 mo were prospectively evaluated, and the results were analysed. INTERVENTION: The urethra was split twice at the site of the stricture both ventrally and dorsally without mobilising it from its bed, and the buccal mucosal graft was secured in the dorsal urethral defect. The urethra was then retubularised in one stage. RESULTS AND LIMITATIONS: The overall results were good (87%), with a mean follow-up period of 42 mo. Seven patients developed minor wound infection, and five patients developed fistulae. There were six recurrences (6:45, 13%) during the follow-up period of 12-60 mo. Two patients with a panurethral stricture and four with bulbar or penobulbar strictures developed recurrences and were managed by optical urethrotomy and self-dilatation. The medium-term results were as good as those reported with the dorsal urethrotomy approach. Long-term results from this and other series are awaited. More randomised trials and meta-analyses are needed to establish this technique as a procedure of choice in future. CONCLUSIONS: The ventral sagittal urethrotomy approach is easier to perform than the dorsal urethrotomy approach, has good results, and is especially useful in long anterior urethral strictures.

Efficacy of peritubal local anesthetic infiltration in alleviating postoperative pain in percutaneous nephrolithotomy.

BACKGROUND AND PURPOSE: Percutaneous nephrolithotomy (PCNL) is a safe and effective endourologic procedure in patients with renal calculi. It is less morbid than open surgery. However, the patient complains of pain around the nephrostomy tube and demands for good postoperative analgesia. Skin infiltration with bupivacaine around the nephrostomy tube is not effective, so we hypothesize that peritubal infiltration of bupivacaine from renal capsule to the skin along the nephrostomy tract may alleviate postoperative pain. PATIENTS AND METHODS: A randomized controlled study was designed in 40 American Society of Anesthesiologists (ASA) grade I patients to assess the impact of peritubal bupivacaine infiltration with 23-gauge spinal needle along the nephrostomy tract after PCNL under fluoroscopic guidance. Patients were randomized to receive 20 mL of 0.25% bupivacaine in block group (n = 20) or no infiltration in control group (n = 20) at the conclusion of the procedure. Postoperative pain score and analgesic requirement for the first 24 hours were assessed by visual and dynamic visual analog scales second hourly. Rescue analgesia with injection tramadol Hcl 50-100 mg was given intravenously to a maximum total dose of 400 mg when pain score exceeded 4. RESULTS: Pain scores and analgesic requirement for the first 24 hours postoperatively were significantly lesser in the block group than in the control group of patients at all points of time and were statistically significant (p < 0.005). CONCLUSION: In this study a significant difference in the pain scores and analgesic requirement was noted in the two groups of patients. Peritubal infiltration of 0.25% bupivacaine solution is efficient in alleviating postoperative pain after PCNL.