Artificial intelligence-based recurrence prediction outperforms classical histopathological methods in pulmonary adenocarcinoma biopsies

INTRODUCTION

Between 10 and 50% of early-stage lung adenocarcinoma patients experience local or distant recurrence. Histological parameters such as a solid or micropapillary growth pattern are well-described risk factors for recurrence. However, not every patient presenting with such a pattern will develop recurrence. Designing a model which can more accurately predict recurrence on small biopsy samples can aid the stratification of patients for surgery, (neo-)adjuvant therapy, and follow-up.

MATERIAL AND METHODS

In this study, a statistical model on biopsies fed with histological data from early and advanced-stage lung adenocarcinomas was developed to predict recurrence after surgical resection. Additionally, a convolutional neural network (CNN)-based artificial intelligence (AI) classification model, named AI-based Lung Adenocarcinoma Recurrence Predictor (AILARP), was trained to predict recurrence, with an ImageNet pre-trained EfficientNet that was fine-tuned on lung adenocarcinoma biopsies using transfer learning. Both models were validated using the same biopsy dataset to ensure that an accurate comparison was demonstrated.

RESULTS

The statistical model had an accuracy of 0.49 for all patients when using histology data only. The AI classification model yielded a test accuracy of 0.70 and 0.82 and an area under the curve (AUC) of 0.74 and 0.87 on patch-wise and patient-wise hematoxylin and eosin (H&E) stained whole slide images (WSIs), respectively.

CONCLUSION

AI classification outperformed the traditional clinical approach for recurrence prediction on biopsies by a fair margin. The AI classifier may stratify patients according to their recurrence risk, based only on small biopsies. This model warrants validation in a larger lung biopsy cohort.

The clinical application of venous ultrasound in diagnosis and follow-up of lower extremity deep vein thrombosis (DVT): a case-based discussion

Current clinical practice guidelines lack explicit guidance on the indications and appropriate timing of venous ultrasound (US) in lower extremity deep vein thrombosis (DVT) follow-up. Moreover, abnormal findings reported on venous US in DVT follow-up or suspected recurrent DVT may be difficult for clinicians to interpret, which carries risk of harm from inappropriate use of anti- coagulation and increased healthcare resource utilization. Due to the above factors, over-use of ultrasound in diagnosis and follow-up of lower extremity DVT has been reported in western health systems. We have undertaken a case-based discussion and a scoping review of existing guidelines on the use of venousUS following prior diagnosis of DVT, to guide appropriate interpretation of commonly reported US abnormalities and provide our suggestions in the light of best available evidence on appropriate timing to perform follow-up US in management of lower extremity DVT.

The value of prognostic and predictive parameters in early-stage lung adenocarcinomas: A comparison between biopsies and resections

INTRODUCTION

Since lung adenocarcinoma (LUAD) biopsies are usually small, it is questionable if their prognostic and predictive information is comparable to what is offered by large resection specimens. This study compares LUAD biopsies and resection specimens for their ability to provide prognostic and predictive parameters.

METHODS

We selected 187 biopsy specimens with stage I and II LUAD. In 123 cases, subsequent resection specimens were also available. All specimens were evaluated for growth pattern, nuclear grade, fibrosis, inflammation, and genomic alterations. Findings were compared using non-parametric testing for categorical variables. Model performance was assessed using the area under the curve for both biopsies and resection specimens, and overall (OS) and disease-free survival (DFS) was calculated.

RESULTS

The overall growth pattern concordance between biopsies and resections was 73.9%. The dominant growth pattern correlated with OS and DFS in resected adenocarcinomas and for high-grade growth pattern in biopsies. Multivariate analysis of biopsy specimens revealed that T2-tumors, N1-status, KRAS mutations and a lack of other driver mutations were associated with poorer survival. Model performance using clinical, histological and genetic data from biopsy specimens for predicting OS and DSF demonstrated an AUC of 0.72 and 0.69, respectively.

CONCLUSIONS

Our data demonstrated the prognostic relevance of a high-grade growth pattern in biopsy specimens of LUAD. Combining clinical, histological and genetic information in one model demonstrated a suboptimal performance for DFS prediction and good performance for OS prediction. However, for daily practice, more robust (bio)markers are required to predict prognosis and stratify patients for therapy and follow-up.

Improving quantification of anticholinergic burden using the Anticholinergic Effect on Cognition Scale - a healthcare improvement study in a geriatric ward setting

OBJECTIVE

Anticholinergic burden refers to the cumulative effects of taking multiple medications with anticholinergic effects. This study was carried out in a public hospital in Singapore, aimed to improve and achieve a 100% comprehensive identification and review of measured, anticholinergic burden in a geriatric psychiatry liaison service to geriatric wards. We evaluated changes in pre-to post-assessment anticholinergic burden scores and trainee feedback.

METHOD

Plan Do Study Act methodology was employed, and Anticholinergic Effect on Cognition scale (AEC) was implemented as the study intervention. A survey instrument evaluated trainee feedback.

RESULTS

There was no measured anticholinergic burden in a baseline of 170 assessments. 75 liaison psychiatry assessments were conducted between June and November 2021 in two cycles. 94.7% of pre-assessments (at the time of assessment) and 71.1% of post-assessments (following assessment) had a record of AEC scores in clinical documentation in cycle one, improving in the second cycle to 100%, 94.6%, respectively. A high post-assessment AEC score of 3 and over reduced from 15.8% in cycle one to 5.4% in cycle two. The trainee feedback suggested an enriching educational experience.

CONCLUSIONS

Using the AEC scale, the findings support the feasibility of comprehensive identification and review of measured anticholinergic burden in older people with neurocognitive disorders.

Protease production and molecular characterization of a protease dipeptidyl-aminopeptidase gene from different strains of Sordaria fimicola

The current research was designed to reach extracellular protease production potential in different strains of Sordaria fimicola which were previously obtained from Dr. Lamb (Imperial College, London) from North Facing Slope and South Facing Slope of Evolution Canyon. After initial and secondary screening, two hyper-producers strains S2 and N6 were selected for submerged fermentation and cultural conditions including temperature, pH, incubation period, inoculum size, substrate concentration, and different carbon and nitrogen sources were optimized for enzyme production. S2 strain showed maximum protease production of 3.291 U/mL after 14 days of incubation at 30 °C with 7 pH, 1% substrate concentration and 1 mL inoculum, While N6 strain showed maximum protease production of 1.929 U/mL under fermentation optimized conditions. Another aim of the present research was to underpin the biodiversity of genetics and post-translational modifications (PTMs) of protease DPAP (peptidyl-aminopeptidase) in Sordaria fimicola. Five polymorphic sites were observed in amino acid sequence of S. fimicola strains with reference to Neurospora crassa. PTMs prediction from bioinformatics tools predicted 38 phosphorylation sites on serine residues for protease peptidyl-aminopeptidase in S1 strain of S. fimicola while 45 phosphorylation sites on serine in N7 strain and 47 serine phosphorylation modifications were predicted in N. crassa. Current research gave an insight that change in genetic makeup effected PTMs which ultimately affected the production of protease enzyme in different strains of same organism (S. fimicola). The production and molecular data of the research revealed that environmental stress has strong effects on the specific genes through mutations which may cause genetic diversity. S. fimicola is non- pathogenic fungus and has a short life cycle. This fungus can be chosen to produce protease enzyme on a commercial scale.

Moral injury and the COVID-19 pandemic: A philosophical viewpoint

Introduction

Much has changed in healthcare during the coronavirus disease (COVID)-19 pandemic. Medicine, a profession of traditional principles and virtues, has faced unprecedented challenges in the light of scarce and unequal distribution of ventilators, testing, and personal protective equipment. Healthcare workers have been- and are increasingly likely to be- forced into situations that require difficult decision making under life-and-death conditions. Concepts of "medical necessity" and "maximum benefit" challenge healthcare systems that already struggle to manage unequal treatment and access to services, giving rise to moral distress and moral injury on the front lines.

Methods

This article focuses on moral injury in the context of coronavirus disease (COVID)-19 pandemic. I review recent literature to highlight the psychological impact of many morally-injurious events that have been reported during the COVID-19 pandemic. With the help of a clinical vignette, I point out how healthcare systems adopt many utilitarian policies in times of excessive healthcare burden. A viewpoint is offered that many morally injurious events happen when healthcare workers, traditionally practicing Kantian and virtue ethics, are forced to follow utilitarian policies of healthcare system.

Conclusion

One form of moral injury may arise from inherent conflicts between individual deontological moral judgments and organizational utilitarian moral judgments. More research is needed to validate the philosophical viewpoint as well as to explore whether increased awareness and education of key principles within moral philosophy can better equip healthcare workers in situations when public health takes precedence over individual health.

Association of plasma nitrite levels with obesity and metabolic syndrome in the Old Order Amish

OBJECTIVES

Plasma nitrite is a metabolite of nitric oxide and reflects endogenous nitric oxide synthase (NOS) activity. Although plasma nitrites were previously linked with obesity and metabolic syndrome (MetS), the direction of association remains inconsistent, possibly due to sample heterogeneity. In a relatively homogeneous population, we hypothesized that nitrite levels will be positively associated with overweight/obesity and MetS.

METHODS

Fasting nitrite levels were measured in 116 Old Order Amish (78% women). We performed age-and-sex-adjusted ancovas to compare nitrite levels between three groups (a) overweight/obese(-)MetS(-), (b) overweight/obese(+)MetS(-) and (c) overweight/obese(+)MetS)(+). Multivariate linear regressions were conducted on nitrite associations with continuous metabolic variables, with successive adjustments for demographics, body mass index, C-reactive protein and neopterin.

RESULTS

Nitrite levels were higher in the obese/overweight(+)MetS(+) group than in the other two groups (p < 0.001). Nitrites were positively associated with levels of triglycerides (p < 0.0001), total cholesterol (p = 0.048), high-density lipoprotein/cholesterol ratio (p < 0.0001) and fasting glucose (p < 0.0001), and negatively correlated with high-density lipoprotein-cholesterol (p < 0.0001). These associations were robust to adjustments for body mass index and inflammatory markers.

CONCLUSION

Further investigation of the connection between obesity/MetS and plasma nitrite levels may lead to novel dietary and pharmacological approaches that ultimately may contribute to reducing the increasing burden of obesity, MetS and cardiovascular morbidity and mortality.

Medication discrepancies and associated risk factors identified among elderly patients discharged from a tertiary hospital in Singapore

INTRODUCTION

Medication discrepancies and poor documentation of medication changes (e.g. lack of justification for medication change) in physician discharge summaries can lead to preventable medication errors and adverse outcomes. This study aimed to identify and characterise discrepancies between preadmission and discharge medication lists, to identify associated risk factors, and in cases of intentional medication discrepancies, to determine the adequacy of the physician discharge summaries in documenting reasons for the changes.

METHODS

A retrospective clinical record review of 150 consecutive elderly patients was done to estimate the number of medication discrepancies between preadmission and discharge medication lists. The two lists were compared for discrepancies (addition, omission or duplication of medications, and/or a change in dosage, frequency or formulation of medication). The patients' clinical records and physician discharge summaries were reviewed to determine whether the discrepancies found were intentional or unintentional. Physician discharge summaries were reviewed to determine if the physicians endorsed and documented reasons for all intentional medication changes.

RESULTS

A total of 279 medication discrepancies were identified, of which 42 were unintentional medication discrepancies (35 were related to omission/addition of a medication and seven were related to a change in medication dosage/frequency) and 237 were documented intentional discrepancies. Omission of the baseline medication was the most common unintentional discrepancy. No reasons were provided in the physician discharge summaries for 54 (22.8%) of the intentional discrepancies.

CONCLUSION

Unintentional medication discrepancies are a common occurrence at hospital discharge. Physician discharge summaries often do not have adequate information on the reasons for medication changes.

Proton pump inhibitors: Are we still prescribing them without valid indications?

BACKGROUND

Evidence from several Western studies has shown an alarmingly high and inappropriate rate of prescription of proton pump inhibitors (PPIs), which may be associated with increased healthcare costs and adverse outcomes. PPI prescribing patterns remain largely unknown in well-developed healthcare systems in Southeast Asia.

AIMS

We aimed to determine the prevalence of inappropriate prescription of PPI among elderly patients without documentation of valid indications, in a tertiary teaching hospital in Singapore.

METHOD

We carried out a retrospective clinical records review of 150 elderly patients aged ≥65 years that had been admitted to two internal medicine wards between 25 May 2011 and 28 June 2011 to determine the appropriateness of indications for PPIs prescribed at hospital discharge. PPI indications were categorised as "valid", "likely invalid", and "probable" based on current clinical literature. Pre-admission and discharge prescriptions were reviewed to determine continuation of pre-admission and new PPI prescriptions at discharge. Data on clinical characteristics and concurrent use of ulcerogenic medications were collected.

RESULTS

From a total of 150 patients, 80 (53 per cent) received prescriptions for PPIs. Of these, 65 (81.2 per cent) had no valid documented indications (i.e., the indication was classed as "likely invalid"); 10 (12.5 per cent) had valid indications; and in five cases (6.2 per cent) the indication was "probable". The most common "likely invalid" indication was primary gastrointestinal bleeding prophylaxis (GIP) among low-dose aspirin users in 28 patients (43 per cent) of invalid PPI prescriptions.

CONCLUSION

Inappropriate prescribing of PPIs without documented valid indications was prevalent among elderly patients at our tertiary teaching hospital in Singapore, providing evidence that shows a similar trend to PPI prescribing to data from Western countries.