Application of machine learning for lung cancer survival prognostication-A systematic review and meta-analysis.

Introduction: Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer. Methods: We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models. Results: The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models. Conclusion: Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.

Pleural plasmacytomas in a patient with multiple myeloma relapse.

Extramedullary plasmacytoma with pleural involvement in the setting of relapsed multiple myeloma (MM) is a rare yet serious condition, which is associated with an adverse prognosis. This report describes a patient with MM who was in complete remission but relapsed with multiple pleural plasmacytomas. The diagnosis was established in a timely manner and the patient was started on appropriate treatment.

Utility of bronchoscopic intra-tumoral alcohol injection to restore airway patency.

BACKGROUND: In cases of malignant airway obstruction, achieving airway patency using conventional bronchoscopic modalities can be challenging and may not be satisfactory. We aim to present our experience of using intra-tumoral alcohol injection (ITAI) to help achieve airway patency in malignant airway obstruction. METHODS: A retrospective study of adult patients presenting with malignant airway obstruction who underwent bronchoscopy with ITAI at a university center between 2015 and 2020 was conducted. We present procedural and patients' characteristics along with any additional bronchoscopic or systemic interventions received. Patients were classified based on airway patency response (assessed qualitatively by an interventional pulmonologist) into those with good response (≥50% improvement in airway patency) vs. those with low response (<50% improvement in airway patency). RESULTS: Forty-two patients underwent ITAI, of which 34 (81%) had at least two bronchoscopies to evaluate response. The patient median age was 65.5 [interquartile range (IQR) 57.8-72]. Most patients had stage IV malignancy at the time of the bronchoscopy (57.1%) and had Eastern Cooperative Oncology Group (ECOG) performance status score of between 2-3. Eighty-two percent of the patients achieved good airway patency response at the conclusion of the procedures. The procedures were generally well-tolerated and only one patient had significant bleeding that was not directly related to ITAI and required intensive care unit monitoring for 24 hours after the procedure. CONCLUSIONS: Dehydrated alcohol is readily available, inexpensive and a safe drug that can be potentially injected directly in malignant airway obstructive lesions in a multimodality approach to achieve airway patency when traditional modalities reach their limitation. Further studies are warranted to determine whether ITAI is superior to other interventional methods, explore its utilization to treat peripheral malignant tumors, as well as to standardize the treatment protocol and determine the effects of ITAI on patient symptoms and quality of life.

A 29-Year-Old Woman With Cough, Dry Eyes, Pulmonary Cysts, and Nodules.

CASE PRESENTATION: A 29-year-old woman who is a never smoker and has a medical history of systemic hypertension presented with a 3-week history of generalized fatigue and dry cough. She endorsed sicca symptoms of dry eyes and dry mouth. She denied breathlessness, fever, chills, night sweats, or weight loss. She had no heartburn, postnasal drip, joint pain, swelling, or skin lesions. She had no known lung disease or history of pneumothorax. Her family history was unremarkable.

A 57-Year-Old Man With Stridor and Critical Tracheal Narrowing.

CASE PRESENTATION: A 57-year-old man with a history of polysubstance use presented with shortness of breath, wheezing, productive cough, subjective fever, and chills of 3-day duration. Additionally, he reported worsening shortness of breath for the last 3 months. Of note, the patient was reported to have had, in the previous 6 months, two episodes of pneumonia that was treated with antibiotics and steroids. He was also diagnosed several years prior with adult-onset asthma due to intermittent wheezing and was prescribed an albuterol inhaler. The albuterol did not help relieve his wheezing, and he stopped refilling it.

A Review of Clinical Trials That Contributed to Chronic Obstructive Pulmonary Disease Treatment Protocols.

Chronic obstructive pulmonary disease (COPD) has remained a leading cause of death worldwide and is expected to increase its burden on the healthcare system in the coming future. Numerous clinical trials have been conducted over the years and as a result, many drugs became a part of the treatment protocols of COPD. Currently, there are also several drugs under development. This review will help future researchers to grasp salient features of previous studies and use them in their future trials in order to reduce the morbidity and mortality of COPD. Randomized control trials provide strong evidence for any hypothesis in a research study. This review focuses on major COPD trials in the last two decades including TORCH, UPLIFT, POET, WISDOM, and TIOSPIR. It showcases the main clinical question, primary outcome, and result of these five trials.

Tunneled Pleural Catheter for the Treatment of Malignant Pleural Effusion: A Systematic Review and Meta-analysis.

Tunneled pleural catheter (TPC) has been widely used to control malignant pleural effusion (MPE); however, it is still not clear whether it is more effective than chemical pleurodesis. We performed a systematic review with meta-analysis to evaluate success and complication rate of TPC as compared with chemical pleurodesis in the management of MPE. PubMed, EMBASE, Cochrane central register of controlled trials, and MEDLINE were searched for English-language studies of clinical controlled trials comparing TPC with chemical pleurodesis until May 2014. Overall success and complication rate were evaluated. Relative risks (RRs) were estimated using random-effects model, and statistical heterogeneity was assessed using I test. Three trials involving 307 patients with MPE were included. The success rate was comparable between TPC and chemical pleurodesis group when all studies included in the analysis (RR, 0.8; 95% confidence interval, 0.53-1.19; P = 0.27). TPC had slightly higher complication rate but was not statistically significant (RR, 2; 95% confidence interval, 0.91-4.4; P = 0.09). Current evidence suggests that TPC and chemical pleurodesis are both effective treatment for recurrent MPE with similar success and complication rate. Further randomized controlled trials are needed to compare TPC with other therapies in patients with MPE.

Effect of audit and feedback on improving handovers: a nonrandomized comparative study.

BACKGROUND: High-quality, shift-to-shift handovers by residents are critical to ensuring to patient safety. The 2011 Accreditation Council for Graduate Medical Education duty hour requirements have increased the number of handovers occurring daily, necessitating new approaches to this challenge. Research suggests standardized approaches, electronic systems, and education programs can improve the handover process. METHODS: We conducted a 2-phase, observational study comparing an electronic handover system (experimental) in one clinical setting to a standard card-based system (control) at a second site. Outcome data included an objective assessment of the completeness and accuracy of handovers, and resident assessment of the handover systems. In phase 1, data were recorded at both sites and not shared with residents. In phase 2, data from the experimental system were used to provide standardized feedback to residents on the quality of their handovers. RESULTS: A total of 3184 individual patient sign-outs were evaluated during the 11-month period. Following introduction of a feedback intervention in the experimental arm, errors were present in only 5.2% of handovers, compared with 16.1% of controls (P < .001), and 67% of the 38 residents responding reported they perceived the experimental system as facilitating better patient care. CONCLUSION: Regular, real-time feedback through an electronic handover system can improve the accuracy and completeness of handovers in patient care.