Challenges involved in the application of artificial intelligence in gastroenterology: The race is on!

Gastroenterology is a particularly data-rich field, generating vast repositories of data that are a fruitful ground for artificial intelligence (AI) and machine learning (ML) applications. In this opinion review, we initially elaborate on the current status of the application of AI/ML-based software in gastroenterology. Currently, AI/ML-based models have been developed in the following applications: Models integrated into the clinical setting following real-time patient data flagging patients at high risk for developing a gastrointestinal disease, models employing non-invasive parameters that provide accurate diagnoses aiming to either replace, minimize, or refine the indications of endoscopy, models utilizing genomic data to diagnose various gastrointestinal diseases, computer-aided diagnosis systems facilitating the interpretation of endoscopy images, models to facilitate treatment allocation and predict the response to treatment, and finally, models in prognosis predicting complications, recurrence following treatment, and overall survival. Then, we elaborate on several challenges and how they may negatively impact the widespread application of AI in healthcare and gastroenterology. Specifically, we elaborate on concerns regarding accuracy, cost-effectiveness, cybersecurity, interpretability, oversight, and liability. While AI is unlikely to replace physicians, it will transform the skillset demanded by future physicians to practice. Thus, physicians are expected to engage with AI to avoid becoming obsolete.

Three-Dimensional Printing and Bioprinting in Renal Transplantation and Regenerative Medicine: Current Perspectives

For patients with end-stage kidney disease (ESKD), renal transplantation is the treatment of choice, constituting the most common solid organ transplantation. This study aims to provide a comprehensive review regarding the application of three-dimensional (3D) printing and bioprinting in renal transplantation and regenerative medicine. Specifically, we present studies where 3D-printed models were used in the training of surgeons through renal transplantation simulations, in patient education where patients acquire a higher understanding of their disease and the proposed operation, in the preoperative planning to facilitate decision-making, and in fabricating customized, tools and devices. Three-dimensional-printed models could transform how surgeons train by providing surgical rehearsal platforms across all surgical specialties, enabling training with tissue realism and anatomic precision. The use of 3D-printed models in renal transplantations has shown a positive impact on surgical outcomes, including the duration of the operation and the intraoperative blood loss. Regarding 3D bioprinting, the technique has shown promising results, especially in the field of microfluidic devices, with the development of tissue demonstrating proximal tubules, glomerulus, and tubuloinerstitium function, and in renal organoid development. Such models can be applied for renal disease modeling, drug development, and renal regenerative medicine.

Short vs long-course antibiotic therapy in adults with acute cholangitis: A systematic review, meta-analysis, and evidence quality assessment

BACKGROUND

Acute cholangitis (AC) constitutes an infection with increased mortality rates in the past. Due to new diagnostic tools and therapeutic methods, the mortality of AC has been significantly reduced nowadays. The initial antibiotic treatment of AC has been oriented to the most common pathogens connected to this infection. However, the optimal duration of the antibiotic treatment of AC is still debatable.

AIM

To investigate if shorter-course antibiotic treatments could be similarly effective to long-course treatments in adults with AC.

METHODS

This study constitutes a systematic review and meta-analysis of the existing literature concerning the duration of antibiotic therapy of AC and an assessment of the quality of the evidence. The study was conducted in accordance with the recommendations of the Preferred Reporting Items for Systematic Review and Meta-Analyses. Fifteen studies were included in the systematic review, and eight were eligible for meta-analysis. Due to heterogeneous duration cutoffs, three study-analysis groups were formed, with a cutoff of 2-3, 6-7, and 14 d.

RESULTS

A total of 2763 patients were included in the systematic review, and 1313 were accounted for the meta-analysis. The mean age was 73.66 ± 14.67 years, and the male and female ratio was 1:08. No significant differences were observed in the mortality rates of antibiotic treatment of 2-3 d, compared to longer treatments (odds ratio = 0.78, 95% confidence interval: 0.23-2.67, I² = 9%) and the recurrence rates and hospitalization length were also not different in all study groups.

CONCLUSION

Short- and long-course antibiotic treatments may be similarly effective concerning the mortality and recurrence rates of AC. Safe conclusions cannot be extracted concerning the hospitalization duration.

When should cataract surgeons seek assistance from experienced colleagues?

PURPOSE

To assess which cases should be assorted exclusively to high-volume surgeons and identify when should a cataract surgeon seek assistance from a senior colleague.

METHODS

The medical records of 2853 patients with age-related cataract were reviewed. Preoperative risk factors were documented for each case, and they were divided into surgeons who had more (> 400 surgeries/year) or less experience (< 400 surgeries/year). Ophthalmology residents were excluded from this review. The cases that involved posterior capsule rupture, dropped nucleus, zonular dehiscence and anterior capsular tear with or without vitreous loss were defined as "complicated".

RESULTS

From the 3247 cataract extraction surgeries that were reviewed, we were unable to identify any statistically significant difference in the complication rates between the two surgeon groups. In the stepwise regression analysis, both groups supported advanced age (> 85) and mature cataracts with up to fourfold odds ratios (OR). Low-volume surgeons had a fivefold OR in the presence of phacodonesis and a fourfold OR in the case of posterior polar cataract. Finally, the low- and high-volume groups had their highest complication rates in the cumulative four and five risk factors, respectively.

CONCLUSION

In the presence of advanced age, mature cataracts, phacodonesis and posterior polar cataract, the complication rates appear to be higher for the less experienced surgeons. Meticulous preoperative assessment with detailed documentation of each patient's risk factors can result in fewer complications. The medical complexity of each case can be used as indicator of whether a more experienced surgeon should perform the surgery or not.

Factors predisposing to intraoperative floppy-iris syndrome: An up-to-date meta-analysis

Intraoperative floppy-iris syndrome (IFIS) is an increasingly recognized condition that is proven to lead to higher rates of intraoperative complications. This study provides an updated systematic review and meta-analysis regarding all the identified factors predisposing to IFIS. The study was performed in accordance with the PRISMA guidelines. 38 studies were finally included in the meta-analysis. The factors that were found to predispose to IFIS significantly were male sex (odds ratio [OR], 4.25; CI, 2.58-7.01), hypertension (OR, 1.55; CI, 1.01-2.37), tamsulosin (OR, 31.06; CI, 13.74-70.22), finasteride (OR, 4.60; CI, 1.97-10.73), benzodiazepines (OR, 2.88; CI, 1.17-7.12), and antipsychotics intake (OR, 6.91; CI, 2.22-21.50). A decreased dilated pupil preoperatively was found predisposing to IFIS (weighted mean difference -0.93; CI, -1.19 to -0.67). Intracameral epinephrine, which was investigated as a potential prophylactic measure for preventing IFIS, did not reach statistical significance (OR, 0.29; CI, 0.08-1.06). A comprehensive preoperative assessment of all risk factors is vital to stratify the surgical risk, which is crucial in addressing IFIS because unanticipated IFIS could turn a routine surgery into one of significant visual morbidity.

The Use of Machine Learning in MicroRNA Diagnostics: Current Perspectives

MicroRNAs constitute small non-coding RNAs that play a pivotal role in regulating the translation and degradation of mRNA and have been associated with many diseases. Artificial Intelligence (AI) is an evolving cluster of interrelated fields, with machine learning (ML) standing out as one of the most prominent AI fields, with a plethora of applications in almost every aspect of human life. ML could be defined as computer algorithms that learn from past data to predict future data. This review comprehensively reviews the current applications of microRNA-based ML models in healthcare. The majority of the identified studies investigated the role of microRNA-based ML models in the management of cancer and specifically gastric cancer (maximum diagnostic accuracy (Accmax): 94%), pancreatic cancer (Accmax: 93%), colorectal cancer (Accmax: 100%), breast cancer (Accmax: 97%), ovarian cancer, neck squamous cell carcinoma, liver cancer, lung cancer (Accmax: 100%), and melanoma. Except for cancer, microRNA-based ML models have been applied for a plethora of other diseases, including ulcerative colitis (Accmax: 92.8%), endometriosis, gestational diabetes mellitus (Accmax: 86%), hearing loss, ischemic stroke, coronary heart disease (Accmax: 96%), tuberculosis, pulmonary arterial hypertension (Accmax: 83%), dementia (Accmax: 82.9%), major cardiovascular events in end-stage renal disease patients, and alcohol dependence (Accmax: 79.1%). Our findings suggest that the development of microRNA-based ML models could be used to enhance the diagnostic accuracy of a plethora of diseases while at the same time substituting or minimizing the use of more invasive diagnostic means (such as endoscopy). Even not as fast as anticipated, AI will eventually infiltrate the entire healthcare industry. AI is the key to a clinical practice where medicine's inherent complexity is embraced. Therefore, AI will become a reality that physicians should conform with to avoid becoming obsolete.

Pneumomediastinum in the COVID-19 era: to drain or not to drain?

Pneumomediastinum (PNM) is a rare clinical finding, usually with a benign course, which is managed conservatively in the majority of cases. However, during the COVID-19 pandemic, an increased incidence of PNM has been observed. Several reports of PNM cases in COVID-19 have been reported in the literature and were managed either conservatively or surgically. In this study, we present our institutional experience of COVID-19 associated PNM, propose a management algorithm, and review the current literature. In total, 43 Case Series were identified, including a total of 747 patients, of whom 374/747 (50.1%) were intubated at the time of diagnosis, 168/747 (22.5%) underwent surgical drain insertion at admission, 562/747 (75.2%) received conservative treatment (observation or mechanical ventilation. Inpatient mortality was 51.8% (387/747), while 45.1% of the population recovered and/or was discharged (337/747). In conclusion, with increased incidence of PNM in COVID-19 patients reported in the literature, it is still difficult to assign a true causal relationship between PNM and mortality. We can, however, see that PMN plays an important role in disease prognosis.  Due to increased complexity, high mortality, and associated complications, conservative management may not be sufficient, and a surgical approach is needed.

Role of three-dimensional printing and artificial intelligence in the management of hepatocellular carcinoma: Challenges and opportunities

Hepatocellular carcinoma (HCC) constitutes the fifth most frequent malignancy worldwide and the third most frequent cause of cancer-related deaths. Currently, treatment selection is based on the stage of the disease. Emerging fields such as three-dimensional (3D) printing, 3D bioprinting, artificial intelligence (AI), and machine learning (ML) could lead to evidence-based, individualized management of HCC. In this review, we comprehensively report the current applications of 3D printing, 3D bioprinting, and AI/ML-based models in HCC management; we outline the significant challenges to the broad use of these novel technologies in the clinical setting with the goal of identifying means to overcome them, and finally, we discuss the opportunities that arise from these applications. Notably, regarding 3D printing and bioprinting-related challenges, we elaborate on cost and cost-effectiveness, cell sourcing, cell viability, safety, accessibility, regulation, and legal and ethical concerns. Similarly, regarding AI/ML-related challenges, we elaborate on intellectual property, liability, intrinsic biases, data protection, cybersecurity, ethical challenges, and transparency. Our findings show that AI and 3D printing applications in HCC management and healthcare, in general, are steadily expanding; thus, these technologies will be integrated into the clinical setting sooner or later. Therefore, we believe that physicians need to become familiar with these technologies and prepare to engage with them constructively.

The process of estimating the cost of surgery: Providing a practical framework for surgeons

Over the last decades, health care costs have been increasing at an alarming, exponential rate which is considered unsustainable. Surgical care utilizes one-third of health care costs. Estimating, evaluating, and understanding the cost of surgery is a vital step towards cost management and reduction. Current cost estimation studies and cost-effectiveness studies have vast disparities in their methodology, with published costs of Operating Room varying from as low as $7 and as high as $113 per minute. Costs in surgery are distinguished as direct and indirect. Allocation of direct costs involves identification, measurement, and valuation processes. Allocation of indirect costs involves the allocation of capital and overhead costs and of indirect department costs. Annualised capital costs and overhead hospital costs are then allocated to surgery by either the cost-centre allocation or the activity-based allocation frameworks. Indirect department costs are allocated to a specific surgery by weighted service allocation or hourly rate allocation or inpatient day allocation, or marginal markup allocation. The growing societal, financial and political pressure for cost reduction has brought cost analysis to the forefront of healthcare discussions. Thus, we believe that almost every single surgeon will eventually enter the field of healthcare economics by necessity. This review aims to provide surgeons with a practical framework for engaging in cost estimation studies.

Challenges and opportunities in the application of artificial intelligence in gastroenterology and hepatology

Artificial intelligence (AI) is an umbrella term used to describe a cluster of interrelated fields. Machine learning (ML) refers to a model that learns from past data to predict future data. Medicine and particularly gastroenterology and hepatology, are data-rich fields with extensive data repositories, and therefore fruitful ground for AI/ML-based software applications. In this study, we comprehensively review the current applications of AI/ML-based models in these fields and the opportunities that arise from their application. Specifically, we refer to the applications of AI/ML-based models in prevention, diagnosis, management, and prognosis of gastrointestinal bleeding, inflammatory bowel diseases, gastrointestinal premalignant and malignant lesions, other nonmalignant gastrointestinal lesions and diseases, hepatitis B and C infection, chronic liver diseases, hepatocellular carcinoma, cholangiocarcinoma, and primary sclerosing cholangitis. At the same time, we identify the major challenges that restrain the widespread use of these models in healthcare in an effort to explore ways to overcome them. Notably, we elaborate on the concerns regarding intrinsic biases, data protection, cybersecurity, intellectual property, liability, ethical challenges, and transparency. Even at a slower pace than anticipated, AI is infiltrating the healthcare industry. AI in healthcare will become a reality, and every physician will have to engage with it by necessity.

The Role of microRNA in Hepatic Ischemia/Reperfusion Injury

INTRODUCTION

Ischemia-Reperfusion (I/R) injuries are caused by complex interrelated mechanisms and pathways. Regarding the liver, I/R injuries and their clinical manifestations are crucial for the surgical outcome. Despite its importance, there is no broadly accepted therapy either for the prevention or for the management of I/R injury. I/R injury of the liver can occur either during hepatic surgery (warm) or during the transplantation procedure (cold). MicroRNAs play a pivotal role in the mechanism of I/R injury, as they regulate the expression of the cellular participants and humoral factors associated with I/R injury.

OBJECTIVE

In this review, we highlight the microRNAs that are involved in the I/R injury of the liver, and the molecular pathways that they regulate. In addition, we discuss the potential role of circulating microRNAs as biomarkers and their role as pharmacological targets in the prevention, diagnosis and treatment of I/R injuries.

METHOD

We conducted a comprehensive review of the PubMed bibliographic database regarding microRNAs and I/R injuries of the liver.

RESULTS

In diagnostics, microRNA panels could replace invasive diagnostic procedures, relieving patients of the associated complications. In therapeutics, microRNAs, agomirs, antagomirs and other drugs can be used to shift the balance between proapoptotic and survival pathways, to alleviate the liver damage caused by I/R. In transplantation procedures, microRNA profiling could decrease the incidence of early graft dysfunction, especially regarding marginal grafts.

CONCLUSION

Although microRNAs seem a very promising clinical tool in the management of I/R injuries, further research is required, until microRNAs become a novel tool in the diagnosis and monitoring of an I/R injury of the liver.

Intraoperative Floppy Iris Syndrome: Updated Perspectives

Almost fifteen years since its initial description, intraoperative floppy iris syndrome (IFIS) during phacoemulsification surgery remains a challenge for cataract surgeons in all its key aspects that include the stratification of the preoperative risk, preoperative prophylaxis treatment, surgery design and intraoperative management. Since its original association with tamsulosin intake, IFIS has been positively correlated with a plethora of risk factors which include: gender, age, hypertension, other a1-adrenergic receptor antagonists, finasteride, angiotensin II receptor inhibitors, benzodiazepines, antipsychotics, hypertension drugs and decreased dilated pupil diameter. The assessment and stratification of the preoperative risk is pivotal in screening patients prone to develop IFIS. For these patients, it is essential that preoperative prophylaxis, employment of necessary measures and surgical technique modifications are considered. A multidisciplinary approach of IFIS is a mandate, thus ophthalmologists, urologists and sometimes other specialties should cooperate to “educate” each other about the risks of their respective fields. They both must be aware of the joint statement on IFIS by the American Academy of Ophthalmology and the American Society of Cataract and Refractive Surgery which suggests either the initiation of tamsulosin after phacoemulsification or the use of a non-selective a1-ARA for benign prostatic hyperplasia treatment. In conclusion, awareness of the risk factors associated with IFIS and their detailed preoperative documentation is crucial in addressing IFIS. The lack of such an awareness can turn a routine, uneventful surgery into one with significant visual morbidity.