From Big Data's 5Vs to clinical practice's 5Ws: enhancing data-driven decision making in healthcare

The use of AI-based algorithms is rapidly growing in healthcare, but there is still an ongoing debate about how to manage and ensure accountability for their clinical use. While most of the studies focus on demonstrating a good algorithm performance it is important to acknowledge that several additional steps are needed for reaching an effective implementation of AI-based models in daily clinical practice, with implementation being one of the main key factors. We propose a model characterized by five questions that can guide in this process. Additionally, we believe that a hybrid intelligence, human and artificial respectively, is the new clinical paradigm that offer the most benefits for developing clinical decision support systems for bedside use.

"Emerging Topics in Pain Medicine": Advancing Research and Patient-Centered Health Strategies

Pain, in all its various forms and manifestations, impacts the lives of millions worldwide [...].

KRAS p.G12C Mutation in Metastatic Colorectal Cancer: Prognostic Implications and Advancements in Targeted Therapies

KRAS is frequently mutated in tumors. It is mutated in approximately 30% of all cancer cases and in nearly 50% of cases of metastatic colorectal cancer (CRC), which is the third leading cause of cancer-related deaths worldwide. Recent advancements in understanding CRC biology and genetics have highlighted the significance of KRAS mutations in the progression of CRC. The KRAS gene encodes a small GTPase (Guanosine TriPhosphatases) that plays a key role in signaling pathways associated with important proteins involved in amplifying growth factor and receptor signals. Mutations in KRAS are frequently observed in codons 12 and 13, and these mutations have oncogenic properties. Abnormal activation of KRAS proteins strongly stimulates signals associated with various cancer-related processes in CRC, including cell proliferation, migration and neoangiogenesis. In this review, we explore the distinct prognostic implications of KRAS mutations. Specifically, the KRAS p.G12C mutation is associated with a worse prognosis in metastatic CRC. The correlation between structure, conformation and mutations is visually presented to emphasize how alterations in individual amino acids at the same position in a single protein can unexpectedly exhibit complex involvement in cancer. Last, KRAS p.G12C is discussed as an emerging and promising therapeutic target in metastatic CRC, providing a concise overview of available clinical data regarding the use of new inhibitors.

[The body of pain. The experience of pain in the cancer patient.]

In oncological disease, a definition of pain as total suffering emerges. This complex phenomenon is characterized by the simultaneous involvement of several dimensions (bodily, cognitive, emotional, family, social, and cultural) held together by a bond of mutual interdependence. Cancer pain is pervasive and affects all aspects of a person's life. It alters the individual's perspective and perception of the world, creating a sense of stagnation and uncertainty characterized by anguish and precariousness. It threatens the sense of personal identity and extends its influence on the entire relational system in which the patient is inserted. The pain of the individual affects the entire family system: priorities, needs, rhythms, methods of communication, and family relationships change to cope with the devastating pathological condition. The relationship between pain and emotions is close as cancer pain stimulates powerful emotional experiences that exert a significant influence on the modalities the patient adopts to manage pain. In addition to the emotional aspects, cognitive factors contribute to characterizing the pain experience: each individual has a set of beliefs, convictions, expectations, and ways of understanding pain built on his/her life experiences and socio-cultural context. Careful understanding of these aspects is of fundamental importance in clinical practice as they modulate the whole pain experience. Furthermore, the patient's experiences with pain can affect the overall response to the disease and have a negative impact on functionality and well-being. Consequently, the impact of cancer pain extends to the patient's family and social network. Because of the multicomponent nature of the cancer pain phenomenon, there is a need for an integrated and multidimensional approach to its study and treatment. This approach must provide for the activation of a flexible setting oriented to the patient's global care and encompassing the totality of the biopsychosocial needs. In addition to the symptom assessment, recognizing the "person" is the challenge that must be taken in the authentic space of a relationship that nourishes and sustains itself. The aim is to go through the experience of pain together with the patient in the direction of consolation and hope.

Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives

Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported pain level assessment has several limitations. Data-driven artificial intelligence (AI) methods can be employed for research on automatic pain assessment (APA). The goal is the development of objective, standardized, and generalizable instruments useful for pain assessment in different clinical contexts. The purpose of this article is to discuss the state of the art of research and perspectives on APA applications in both research and clinical scenarios. Principles of AI functioning will be addressed. For narrative purposes, AI-based methods are grouped into behavioral-based approaches and neurophysiology-based pain detection methods. Since pain is generally accompanied by spontaneous facial behaviors, several approaches for APA are based on image classification and feature extraction. Language features through natural language strategies, body postures, and respiratory-derived elements are other investigated behavioral-based approaches. Neurophysiology-based pain detection is obtained through electroencephalography, electromyography, electrodermal activity, and other biosignals. Recent approaches involve multimode strategies by combining behaviors with neurophysiological findings. Concerning methods, early studies were conducted by machine learning algorithms such as support vector machine, decision tree, and random forest classifiers. More recently, artificial neural networks such as convolutional and recurrent neural network algorithms are implemented, even in combination. Collaboration programs involving clinicians and computer scientists must be aimed at structuring and processing robust datasets that can be used in various settings, from acute to different chronic pain conditions. Finally, it is crucial to apply the concepts of explainability and ethics when examining AI applications for pain research and management.

Utilizing an artificial intelligence framework (conditional generative adversarial network) to enhance telemedicine strategies for cancer pain management

BACKGROUND

The utilization of artificial intelligence (AI) in healthcare has significant potential to revolutionize the delivery of medical services, particularly in the field of telemedicine. In this article, we investigate the capabilities of a specific deep learning model, a generative adversarial network (GAN), and explore its potential for enhancing the telemedicine approach to cancer pain management.

MATERIALS AND METHODS

We implemented a structured dataset comprising demographic and clinical variables from 226 patients and 489 telemedicine visits for cancer pain management. The deep learning model, specifically a conditional GAN, was employed to generate synthetic samples that closely resemble real individuals in terms of their characteristics. Subsequently, four machine learning (ML) algorithms were used to assess the variables associated with a higher number of remote visits.

RESULTS

The generated dataset exhibits a distribution comparable to the reference dataset for all considered variables, including age, number of visits, tumor type, performance status, characteristics of metastasis, opioid dosage, and type of pain. Among the algorithms tested, random forest demonstrated the highest performance in predicting a higher number of remote visits, achieving an accuracy of 0.8 on the test data. The simulations based on ML indicated that individuals who are younger than 45 years old, and those experiencing breakthrough cancer pain, may require an increased number of telemedicine-based clinical evaluations.

CONCLUSION

As the advancement of healthcare processes relies on scientific evidence, AI techniques such as GANs can play a vital role in bridging knowledge gaps and accelerating the integration of telemedicine into clinical practice. Nonetheless, it is crucial to carefully address the limitations of these approaches.

Investigating Functional Impairment in Chronic Low Back Pain: A Qualitative Study from the Patients and Specialists' Perspectives

Prompt and appropriate treatment of chronic low back pain (cLBP) is of the utmost importance for preventing relevant disability, high burden of disease, and increasing costs for the healthcare system. Recently, the concept of functional impairment has been associated with any type of chronic pain, and mounting attention has been paid to extending the aims of treatment beyond mere pain remission, including restoration of working capacity, everyday functioning, mobility, and quality of life. Nevertheless, a shared definition of functionality is still lacking. Notably, different specialists involved in the treatment of cLBP such as general practitioners, orthopedists, pain therapists, and physiatrists, and patients themselves have different opinions on what "functional impairment" actually means. On these premises, a qualitative interview study was performed to investigate how the concept of "functionality" is interpreted by different specialists involved in the management of cLBP, and by patients. Overall, all different specialists agreed that functionality should be assessed in clinical practice. However, in spite of several instruments available for evaluating functionality, no homogeneity of behavior is observable.

Delphi-Based Expert Consensus Statements for the Management of Percutaneous Radiofrequency Neurotomy in the Treatment of Lumbar Facet Joint Syndrome

INTRODUCTION

A modified Delphi strategy was implemented for obtaining recommendations that could be useful in the management of percutaneous radiofrequency treatment of lumbar facet joint syndrome, as the literature on the argument was poor in quality.

METHODS

An Italian research team conducted a comprehensive literature search, defined the investigation topics (diagnosis, treatment, and outcome evaluation), and developed an explorative semi-structured questionnaire. They also selected the members of the panel. After an online meeting with the participants, the board developed a structured questionnaire of 15 closed statements (round 1). A five-point Likert scale was used and the cut-off for consensus was established at a minimum of 70% of the number of respondents (level of agreement ≥ 4, agree or strongly agree). The statements without consensus were rephrased (round 2).

RESULTS

Forty-one clinicians were included in the panel and responded in both rounds. After the first round, consensus (≥ 70%) was obtained in 9 out of 15 statements. In the second round, only one out of six statements reached the threshold. The lack of consensus was observed for statements concerning the use of imaging for a diagnosis [54%, median 4, interquartile range (IQR) 3-5], number of diagnostic blocks (37%, median 4, IQR 2-4), bilateral denervation (59%, median 4, IQR 2-4), technique and number of lesions (66%, median 4, IQR 3-5), and strategy after denervation failure (68%, median 4, IQR 3-4).

CONCLUSION

Results of the Delphi investigations suggest that there is a need to define standardized protocols to address this clinical problem. This step is essential for designing high-quality studies and filling current gaps in scientific evidence.

Circulating Vitamin D Level and Its Impact on Mortality and Recurrence in Stage III Colorectal Cancer Patients: A Systematic Review and Meta-Analysis

BACKGROUND

Vitamin D (VD) has been implicated in several diseases, including colorectal cancer (CRC). This study aimed to determine whether there is an association between VD levels and time-to-outcome in stage III CRC patients through a systematic review and meta-analysis.

METHODS

The study adhered to the PRISMA 2020 statement. Articles were searched in PubMed/MEDLINE and Scopus/ELSEVIER. Four articles were selected, with the primary objective of providing a pooled estimate of the risk of death specifically in stage III CRC patients based on pre-operative VD levels. Study heterogeneity and publication bias were analyzed using Tau² statistics and funnel plots.

RESULTS

The selected studies showed significant heterogeneity regarding time-to-outcome, technical assessments, and serum VD concentration measures. The pooled analysis of 2628 and 2024 patients revealed a 38% and 13% increase in the risk of death (HR: 1.38, 95% CI: 0.71-2.71) and recurrence (HR: 1.13; 95% CI: 0.84-1.53), respectively, for random-effects models among patients with lower levels of VD.

CONCLUSIONS

Our findings suggest that a low concentration of VD has a significant negative impact on time-to-outcome in stage III CRC.

Exploring Artificial Intelligence in Anesthesia: A Primer on Ethics, and Clinical Applications

The field of anesthesia has always been at the forefront of innovation and technology, and the integration of Artificial Intelligence (AI) represents the next frontier in anesthesia care. The use of AI and its subtypes, such as machine learning, has the potential to improve efficiency, reduce costs, and ameliorate patient outcomes. AI can assist with decision making, but its primary advantage lies in empowering anesthesiologists to adopt a proactive approach to address clinical issues. The potential uses of AI in anesthesia can be schematically grouped into clinical decision support and pharmacologic and mechanical robotic applications. Tele-anesthesia includes strategies of telemedicine, as well as device networking, for improving logistics in the operating room, and augmented reality approaches for training and assistance. Despite the growing scientific interest, further research and validation are needed to fully understand the benefits and limitations of these applications in clinical practice. Moreover, the ethical implications of AI in anesthesia must also be considered to ensure that patient safety and privacy are not compromised. This paper aims to provide a comprehensive overview of AI in anesthesia, including its current and potential applications, and the ethical considerations that must be considered to ensure the safe and effective use of the technology.

The prognostic role of p53 mutations in metastatic colorectal cancer: a systematic review and meta-analysis

INTRODUCTION

P53 is one of the most frequently mutated genes in colorectal cancer (CRC). The present study was undertaken to provide a solid estimate of the prognostic value of p53 mutations in metastatic CRC patients.

METHODS

This meta-analysis was done in accordance to the Preferred Reporting Item For Systematic Reviews and Meta-Analysis 2020 guidelines. Studies in English published in the last ten years were searched through PubMed and Google Scholar. Final selection criteria were: 1) association with overall survival, 2) presence of Hazard Ratios (HRs) with 95% Confidence Intervals (CIs). The articles were evaluated for quality and risk of bias using the Newcastle-Ottawa Scale and QUIPS tool, respectively. The meta-analysis was conducted with random-effects model according to the Hartung-Knapp-Sidik-Jonkman method and results were depicted in classical Forest plots. Studies heterogeneity was determined by I² and Tau² statistics. The relationship between p53 mutation and clinic-pathological variables was examined using the χ² test.

RESULTS

Nine articles met the eligibility criteria and went to the final analysis. Sample size ranged from 51 to 1043 patients. All studies were retrospective. The Newcastle Ottawa Scale score was >6 in all studies, QUIPS risk of bias was low in 6, moderate in 3 studies. Only three studies analysed the entire p53 gene coding region. The DNA sequencing technological platforms varied from Sanger to NGS sequencing techniques. The p53 mutational frequencies ranged from 35.0 to 73.0%. A strong association (p<0.0001) emerged between p53 alteration and left-sided CRC. The final pooled HR (p53 mutated vs p53 wild-type tumours) for overall survival was 1.30 (95% CI: 0.75-2.25) at random-effects model.

CONCLUSIONS

The available evidence does not support a prognostic role for p53 in metastatic CRC patients. Prospective studies, with larger sample sizes and consistent and harmonized methodology, are needed to explore the prognostic role of p53 in metastatic CRC patients.

Crossing the AI Chasm in Neurocritical Care

Despite the growing interest in possible applications of computer science and artificial intelligence (AI) in the field of neurocritical care (neuro-ICU), widespread clinical applications are still missing. In neuro-ICU, the collection and analysis in real time of large datasets can play a crucial role in advancing this medical field and improving personalized patient care. For example, AI algorithms can detect subtle changes in brain activity or vital signs, alerting clinicians to potentially life-threatening conditions and facilitating rapid intervention. Consequently, data-driven AI and predictive analytics can greatly enhance medical decision making, diagnosis, and treatment, ultimately leading to better outcomes for patients. Nevertheless, there is a significant disparity between the current capabilities of AI systems and the potential benefits and applications that could be achieved with more advanced AI technologies. This gap is usually indicated as the AI chasm. In this paper, the underlying causes of the AI chasm in neuro-ICU are analyzed, along with proposed recommendations for utilizing AI to attain a competitive edge, foster innovation, and enhance patient outcomes. To bridge the AI divide in neurocritical care, it is crucial to foster collaboration among researchers, clinicians, and policymakers, with a focus on specific use cases. Additionally, strategic investments in AI technology, education and training, and infrastructure are needed to unlock the potential of AI technology. Before implementing a technology in patient care, it is essential to conduct thorough studies and establish clinical validation in real-world environments to ensure its effectiveness and safety. Finally, the development of ethical and regulatory frameworks is mandatory to ensure the secure and efficient deployment of AI technology throughout the process.

Health Status Perception and Psychological Sequelae in Buried Victims: An Observational Study on Survivors of the Earthquake in Amatrice (Italy), Three Years Later

INTRODUCTION

The extrication from rubble is particularly critical for the survival of the victims of an earthquake. Early repeated infusion of sedative agents (SAs) in the acute trauma phase may interfere with neural processes leading to posttraumatic stress disorder (PTSD).

STUDY OBJECTIVE

This study aimed to analyze the psychological status reported by the buried victims of the earthquake in Amatrice (August 24, 2016; Italy) by considering type of the SAs administered during the extrication maneuvers.

METHODS

This was an observational study on data from 51 patients directly rescued under the rubble during the earthquake in Amatrice. During extrication maneuvers, a moderate sedation was administered by titrating ketamine (0.3-0.5mg/kg) or morphine (0.1-0.15mg/kg) with respect to the Richmond Agitation and Sedation Scale (RASS; between -2 and -3) in buried victims.Three years following the rescue, the survivors were interviewed on their perceived health status and stress using a questionnaire which consisted of 17 items: the standard four-item set of healthy days core questions (CDC HRQOL-4); the 12-item General Health Questionnaire (GHQ-12); and in addition, survivors were asked if they had a diagnosis for anxiety, depression, or for PTSD.

RESULTS

The study analyzed data from the complete clinical documentation of 51 survivors; 30 were males and 21 females, with an average age of 52 years. Twenty-six (26) subjects were treated with ketamine, while 25 were treated with morphine, during the extrication procedures. Concerning the quality-of-life analysis, only 10 survivors out of 51 perceived their health status as good; the others reported psychological disorders. The GHQ-12 scores showed that all survivors had psychological distress with a mean total score of 22.2 (SD = 3.5). Eighteen (18) victims declared to have had a diagnosis of generalized anxiety (35%), while 29 were treated for depression (57%) and PTSD (57%) by a specialist. With regards to the perceived distress level and the anxiety disorder, this analysis showed significant associations with SAs used during extrication, with a better performance for ketamine than for morphine.

CONCLUSION

These findings suggest investigating whether early sedation with ketamine directly in the disaster setting may promote the prophylaxis and reduce the risk of developing trauma-related disorders (TRDs) on the buried victims of major natural disasters in future studies.

Pain prevalence and pain management in children and adolescents in an italian third level pediatric hospital: a cross-sectional study

BACKGROUND

In 2016, we performed a one-day investigation to analyze the prevalence of pain, pain intensity, and pain therapy in the Departments of Surgery and Onco-Hematology of the Ospedale Pediatrico Bambino Gesù. To improve the knowledge gap highlighted in the previous study, refresher courses and even personalized audits have been carried out during these years. The purpose of this study is to evaluate if, after 5 years, there have been improvements in the management of pain.

METHODS

The study was conducted on 25 January 2020. Pain assessment, pain therapies, pain prevalence and intensity in the preceding 24 h and during the recovery period were recorded. Pain outcomes were compared with previous audit results.

RESULTS

Out of the 63 children with at least one documented pain assessment (starting from 100 eligible), 35 (55.4%) experienced pain: 32 children (50.7%) experienced moderate /severe pain while 3 patients (4%) felt mild pain. In the preceding 24 h, 20 patients (31.7%) reported moderate/severe pain while 10 (16%) reported moderate or severe pain during the interview. The average value of the Pain Management Index (PMI) was - 1.3 ± 0.9 with a minimum of -3 and a maximum of 0. 28 patients (87%) undergoing analgesic therapy for moderate/severe pain had a PMI of less than 0 (undertreated pain), while 3 patients (13%) scored value of 0 or higher (adequate pain therapy), 4 patients (12.5%) received multimodal analgesia with opioids and 2 patients (6%) opioids alone. Time-based therapy was prescribed to 20 patients (62.5%), intermittent therapy was prescribed to 7 patients (22%) and 5 patients (15.5%) did not receive any therapy. The prevalence of pain was higher during hospitalization and 24 h before the interview, while at the time of the interview, the proportion was the same. In this audit, the daily prescription modality of the therapy had some improvements (time-based: 62.5% vs. 44%; intermittent: 22%vs 25%; no therapy: 15.5% vs. 31%).

CONCLUSION

Pain management in hospitalized children constantly requires special daily attention from health professionals aimed at mitigating the components of intractable pain and resolving those of treatable pain.

TRIAL REGISTRATION

This study is registered with ClinicalTrials.gov, number (NCT04209764), registered 24 December 2019, https://clinicaltrials.gov/ct2/show/NCT04209764?term=NCT04209764&draw=2&rank=1 .

The Clinical Researcher Journey in the Artificial Intelligence Era: The PAC-MAN’s Challenge

Artificial intelligence (AI) is a powerful tool that can assist researchers and clinicians in various settings. However, like any technology, it must be used with caution and awareness as there are numerous potential pitfalls. To provide a creative analogy, we have likened research to the PAC-MAN classic arcade video game. Just as the protagonist of the game is constantly seeking data, researchers are constantly seeking information that must be acquired and managed within the constraints of the research rules. In our analogy, the obstacles that researchers face are represented by “ghosts”, which symbolize major ethical concerns, low-quality data, legal issues, and educational challenges. In short, clinical researchers need to meticulously collect and analyze data from various sources, often navigating through intricate and nuanced challenges to ensure that the data they obtain are both precise and pertinent to their research inquiry. Reflecting on this analogy can foster a deeper comprehension of the significance of employing AI and other powerful technologies with heightened awareness and attentiveness.

Oligo-Metastatic Cancers: Putative Biomarkers, Emerging Challenges and New Perspectives

Some cancer patients display a less aggressive form of metastatic disease, characterized by a low tumor burden and involving a smaller number of sites, which is referred to as "oligometastatic disease" (OMD). This review discusses new biomarkers, as well as methodological challenges and perspectives characterizing OMD. Recent studies have revealed that specific microRNA profiles, chromosome patterns, driver gene mutations (ERBB2, PBRM1, SETD2, KRAS, PIK3CA, SMAD4), polymorphisms (TCF7L2), and levels of immune cell infiltration into metastases, depending on the tumor type, are associated with an oligometastatic behavior. This suggests that OMD could be a distinct disease with specific biological and molecular characteristics. Therefore, the heterogeneity of initial tumor burden and inclusion of OMD patients in clinical trials pose a crucial methodological question that requires responses in the near future. Additionally, a solid understanding of the molecular and biological features of OMD will be necessary to support and complete the clinical staging systems, enabling a better distinction of metastatic behavior and tailored treatments.

Impact of Epstein Barr Virus Infection on Treatment Opportunities in Patients with Nasopharyngeal Cancer

Chemical, physical, and infectious agents may induce carcinogenesis, and in the latter case, viruses are involved in most cases. The occurrence of virus-induced carcinogenesis is a complex process caused by an interaction across multiple genes, mainly depending by the type of the virus. Molecular mechanisms at the basis of viral carcinogenesis, mainly suggest the involvement of a dysregulation of the cell cycle. Among the virus-inducing carcinogenesis, Epstein Barr Virus (EBV) plays a major role in the development of both hematological and oncological malignancies and importantly, several lines of evidence demonstrated that nasopharyngeal carcinoma (NPC) is consistently associated with EBV infection. Cancerogenesis in NPC may be induced by the activation of different EBV "oncoproteins" which are produced during the so called "latency phase" of EBV in the host cells. Moreover, EBV presence in NPC does affect the tumor microenvironment (TME) leading to a strongly immunosuppressed status. Translational implications of the above-mentioned statements are that EBV-infected NPC cells can express proteins potentially recognized by immune cells in order to elicit a host immune response (tumor associated antigens). Three immunotherapeutic approaches have been implemented for the treatment of NPC including active, adoptive immunotherapy, and modulation of immune regulatory molecules by use of the so-called checkpoint inhibitors. In this review, we will highlight the role of EBV infection in NPC development and analyze its possible implications on therapy strategies.