From Patient-Controlled Analgesia to Artificial Intelligence-Assisted Patient-Controlled Analgesia: Practices and Perspectives

Knowledge, Attitudes and Practices Among Anesthesia and Thoracic Surgery Medical Staff Toward Ai-PCA

Purpose

Artificial intelligence (AI) is increasingly influencing various medical fields, including anesthesiology. The Introduction of artificial intelligent patient-controlled analgesia (Ai-PCA) has been seen as a significant advancement in pain management. However, the adoption and practical application of Ai-PCA by medical staff, particularly in anesthesia and thoracic surgery, have not been extensively studied. This study aimed to investigate the knowledge, attitudes and practices (KAP) among anesthesia and thoracic surgery medical staff toward artificial intelligent patient-controlled analgesia (Ai-PCA).

Participants and Methods

This web-based cross-sectional study was conducted between November 1, 2023 and November 15, 2023 at Jiangsu Cancer Hospital. A self-designed questionnaire was developed to collect demographic information of anesthesia and thoracic surgery medical staff, and to assess their knowledge, attitudes and practices toward Ai-PCA.

Results

A total of 519 valid questionnaires were collected. Among the participants, 278 (53.56%) were female, 497 (95.76%) were employed in the field of anesthesiology, and 188 (36.22%) had participated in Ai-PCA training. The mean knowledge, attitude, and practice scores were 7.8±1.75 (possible range: 0-10), 37.43±4.16 (possible range: 9-45), and 28.38±9.27 (possible range: 9-45), respectively.

Conclusion

The findings revealed that anesthesia and thoracic surgery medical staff have sufficient knowledge, active attitudes, but poor practices toward the Ai-PCA. Comprehensive training programs are needed to improve anesthesia and thoracic surgery medical staff's practices in this area.

Incorporation of "Artificial Intelligence" for Objective Pain Assessment: A Comprehensive Review

Pain is a significant health issue, and pain assessment is essential for proper diagnosis, follow-up, and effective management of pain. The conventional methods of pain assessment often suffer from subjectivity and variability. The main issue is to understand better how people experience pain. In recent years, artificial intelligence (AI) has been playing a growing role in improving clinical diagnosis and decision-making. The application of AI offers promising opportunities to improve the accuracy and efficiency of pain assessment. This review article provides an overview of the current state of AI in pain assessment and explores its potential for improving accuracy, efficiency, and personalized care. By examining the existing literature, research gaps, and future directions, this article aims to guide further advancements in the field of pain management. An online database search was conducted via multiple websites to identify the relevant articles. The inclusion criteria were English articles published between January 2014 and January 2024). Articles that were available as full text clinical trials, observational studies, review articles, systemic reviews, and meta-analyses were included in this review. The exclusion criteria were articles that were not in the English language, not available as free full text, those involving pediatric patients, case reports, and editorials. A total of (47) articles were included in this review. In conclusion, the application of AI in pain management could present promising solutions for pain assessment. AI can potentially increase the accuracy, precision, and efficiency of objective pain assessment.

The Effect of Everyday-Life Social Contact on Pain

Pain is a biopsychosocial phenomenon, resulting from the interplay between physiological and psychological processes and social factors. Given that humans constantly interact with others, the effect of social factors is particularly relevant. Documenting the significance of the social modulation of pain, an increasing number of studies have investigated the effect of social contact on subjective pain intensity and pain-related physiological changes. While evidence suggests that social contact can alleviate pain, contradictory findings indicate an increase in pain intensity and a deterioration of pain coping strategies. This evidence primarily stems from studies examining the effect of social contact on pain within highly controlled laboratory conditions. Moreover, pain assessments often rely on one-time subjective reports of average pain intensity across a predefined period. Ecological momentary assessments (EMAs) can circumvent these problems, as they can capture diverse aspects of behavior and experiences multiple times a day, in real time, with high resolution, and within naturalistic and ecologically valid settings. These multiple measures allow for the examination of fluctuations of pain symptoms throughout the day in relation to affective, cognitive, behavioral, and social factors. In this opinion paper, we review the current state and future relevance of EMA-based social pain research in daily life. Specifically, we examine whether everyday-life social support reduces or enhances pain. The first part of the paper provides a comprehensive overview of the use of EMA in pain research and summarizes the main findings. The review of the relatively limited number of existing EMA studies shows that the association between pain and social contact in everyday life depends on numerous factors, including pain syndromes, temporal dynamics, the nature of social interactions, and characteristics of the interaction partners. In line with laboratory research, there is evidence that everyday-life social contact can alleviate, but also intensify pain, depending on the type of social support. Everyday-life emotional support seems to reduce pain, while extensive solicitous support was found to have opposite effects. Moreover, positive short-term effects of social support can be overshadowed by other symptoms such as fatigue. Overall, gathering and integrating experiences from a patient's social environment can offer valuable insights. These insights can help interpret dynamics in pain intensity and accompanying symptoms such as depression or fatigue. We conclude that factors determining the reducing versus enhancing effects of social contact on pain need to be investigated more thoroughly. We advocate EMA as the assessment method of the future and highlight open questions that should be addressed in future EMA studies on pain and the potential of ecological momentary interventions for pain treatment.

Cloud platform to improve efficiency and coverage of asynchronous multidisciplinary team meetings for patients with digestive tract cancer

Background

Multidisciplinary team (MDT) meetings are the gold standard of cancer treatment. However, the limited participation of multiple medical experts and the low frequency of MDT meetings reduce the efficiency and coverage rate of MDTs. Herein, we retrospectively report the results of an asynchronous MDT based on a cloud platform (cMDT) to improve the efficiency and coverage rate of MDT meetings for digestive tract cancer.

Methods

The participants and cMDT processes associated with digestive tract cancer were discussed using a cloud platform. Software programming and cMDT test runs were subsequently conducted to further improve the software and processing. cMDT for digestive tract cancer was officially launched in June 2019. The doctor response duration, cMDT time, MDT coverage rate, National Comprehensive Cancer Network guidelines compliance rate for patients with stage III rectal cancer, and uniformity rate of medical experts' opinions were collected.

Results

The final cMDT software and processes used were determined. Among the 7462 digestive tract cancer patients, 3143 (control group) were diagnosed between March 2016 and February 2019, and 4319 (cMDT group) were diagnosed between June 2019 and May 2022. The average number of doctors participating in each cMDT was 3.26 ± 0.88. The average doctor response time was 27.21 ± 20.40 hours, and the average duration of cMDT was 7.68 ± 1.47 min. The coverage rates were 47.85% (1504/3143) and 79.99% (3455/4319) in the control and cMDT groups, respectively. The National Comprehensive Cancer Network guidelines compliance rates for stage III rectal cancer patients were 68.42% and 90.55% in the control and cMDT groups, respectively. The uniformity rate of medical experts' opinions was 89.75% (3101/3455), and 8.97% (310/3455) of patients needed online discussion through WeChat; only 1.28% (44/3455) of patients needed face-to-face discussion with the cMDT group members.

Conclusion

A cMDT can increase the coverage rate of MDTs and the compliance rate with National Comprehensive Cancer Network guidelines for stage III rectal cancer. The uniformity rate of the medical experts' opinions was high in the cMDT group, and it reduced contact between medical experts during the COVID-19 pandemic.

Using Video to Describe the Patient-Controlled Analgesia Pump Programming Process: A Qualitative Study

BACKGROUND

Patient-controlled analgesia (PCA) pumps are complex medical devices frequently used for postoperative pain control. Differences in how nurses program PCA pumps can lead to preventable medication errors.

PURPOSE

To describe similarities and differences in how surgical nurses program PCA pumps.

METHODS

We conducted a qualitative study using video reflexive ethnography (VRE) to film nurses as they programmed a PCA pump. We spliced and collated videos into separate clips and showed to nursing leaders for their deliberation and action.

RESULTS

We found nurses ignored or immediately silenced alarms, were uncertain about the correct programming sequence, and interpreted how to load a syringe in the pump in multiple ways; in addition, the PCA pump design did not align with nurses' workflow.

CONCLUSIONS

VRE was effective in visualizing common challenges nurses experienced during PCA pump programming. Nursing leaders are planning several nursing process changes due to these findings.

Artificial intelligent patient-controlled intravenous analgesia improves the outcomes of older patients with laparoscopic radical resection for colorectal cancer

METHODS

Patients undergoing elective laparoscopic radical resection of colorectal cancer from July 2019 to May 2021 were selected. The patients were assigned to Ai-PCIA group and control group. Ai-PCIA group received postoperative analgesia management and effect evaluation through intelligent wireless analgesia system + postoperative follow-up twice a day, while control group received analgesia management and effect evaluation through ward physician feedback + postoperative follow-up twice a day. The pain numerical score (NRS), Richards-Campbell Sleep Scale (RCSQ), and adverse outcomes were collected and compared.

RESULTS

A total of 60 patients (20 females and 40 males with average (78.26 ± 6.42) years old) were included. The NRS scores at rest and during activity of the Ai-PCA group at 8, 12, and 24 h after the operation were significantly lower than that of the control group (all P < 0.05). The RCSQ score of Ai-PCA group was significantly higher than that of control group on the 1st and 2nd days after operation (all P < 0.05). There were no significant differences in the incidence of dizziness and nausea, vomiting, and myocardial ischemia (all P > 0.05).

CONCLUSIONS

Ai-PCIA can improve the analgesic effect and sleep quality of older patients after laparoscopic radical resection, which may be promoted in clinical analgesia practice.

Analgesia quality index improves the quality of postoperative pain management: a retrospective observational study of 14,747 patients between 2014 and 2021

BACKGROUND

The application of artificial intelligence patient-controlled analgesia (AI-PCA) facilitates the remote monitoring of analgesia management, the implementation of mobile ward rounds, and the automatic recording of all types of key data in the clinical setting. However, it cannot quantify the quality of postoperative analgesia management. This study aimed to establish an index (analgesia quality index (AQI)) to re-monitor and re-evaluate the system, equipment, medical staff and degree of patient matching to quantify the quality of postoperative pain management through machine learning.

METHODS

Utilizing the wireless analgesic pump system database of the Cancer Hospital Affiliated with Nantong University, this retrospective observational study recruited consecutive patients who underwent postoperative analgesia using AI-PCA from June 1, 2014, to August 31, 2021. All patients were grouped according to whether or not the AQI was used to guide the management of postoperative analgesia: The control group did not receive the AQI guidance for postoperative analgesia and the experimental group received the AQI guidance for postoperative analgesia. The primary outcome was the incidence of moderate-to-severe pain (numeric rating scale (NRS) score ≥ 4) and the second outcome was the incidence of total adverse reactions. Furthermore, indicators of AQI were recorded.

RESULTS

A total of 14,747 patients were included in this current study. The incidence of moderate-to-severe pain was 26.3% in the control group and 21.7% in the experimental group. The estimated ratio difference was 4.6% between the two groups (95% confidence interval [CI], 3.2% to 6.0%; P < 0.001). There were significant differences between groups. Otherwise, the differences in the incidence of total adverse reactions between the two groups were nonsignificant.

CONCLUSIONS

Compared to the traditional management of postoperative analgesia, application of the AQI decreased the incidence of moderate-to-severe pain. Clinical application of the AQI contributes to improving the quality of postoperative analgesia management and may provide guidance for optimum pain management in the postoperative setting.

Virtual Pain Unit Is Associated with Improvement of Postoperative Analgesia Quality: A Retrospective Single-Center Clinical Study

INTRODUCTION

Acute postoperative pain is a major concern among surgical patients. Thus, this study established a new acute pain management model and compared the effects of the acute pain service (APS) model in 2020 and the virtual pain unit (VPU) model in 2021 on postoperative analgesia quality.

METHODS

This retrospective, single-center clinical study involved 21,281 patients from 2020 to 2021. First, the patients were grouped on the basis of their pain management model (APS and VPU). The incidence of moderate to severe postoperative pain (MSPP) [numeric rating scale (NRS) score ≥ 5], postoperative nausea and vomiting (PONV), and postoperative dizziness were recorded.

RESULTS

The VPU group recorded significantly lower MSPP incidence (1-12 months), PONV, and postoperative dizziness (1-10 months and 12 months) compared with the APS group. In addition, the annual average incidence of MSPP, PONV, and postoperative dizziness in the VPU group was significantly lower than in the APS group.

CONCLUSIONS

The VPU model reduces the incidence of moderate to severe postoperative pain, nausea, vomiting, and dizziness; hence, it is a promising acute pain management model.

Postoperative Analgesia Management Evaluation in the Postanesthesia Unit: An Exploratory Analysis Based on Patient and Surgery Characteristics

PURPOSE

Several methods have been proposed for postoperative pain management, including administration of opioid analgesics, epidural analgesia, and perineural and infiltrative techniques; however, data are lacking on the relationship between pain intensity, patients' age and gender, and surgery duration.

DESIGN

Prospective, observational, single-center study.

METHODS

The study included patients greater than or equal to 18 years old who underwent surgery with different anesthesia types, grouped according to the American Society of Anesthesiologists' physical status classification score. The McGill Pain Questionnaire was used to assess postoperative pain intensity. The postoperative pain evaluation was performed in the first 5 minutes on entering the postanesthesia care unit (PACU), and at 30 minutes and 24 hours after the operation.

RESULTS

Our results showed a significant negative relationship between pain intensity as assessed at 5 and 30 minutes postoperatively and age. Postoperative pain intensity at 24 hours was significantly lower after low-risk surgeries lasting up to 1 hour; pain intensity was also significantly lower at 30 minutes following epidural anesthesia. When nonsteroidal anti-inflammatory drugs were not administered in the PACU, pain intensity was significantly lower at 5 minutes, 30 minutes, and 3 hours.

CONCLUSIONS

Postoperative analgesic administration should be conducted in accordance with age and surgery type. Additionally, epidural anesthesia can reduce the immediate postoperative pain intensity.

Postoperative pain management in non-traumatic emergency general surgery: WSES-GAIS-SIAARTI-AAST guidelines

BACKGROUND

Non-traumatic emergency general surgery involves a heterogeneous population that may present with several underlying diseases. Timeous emergency surgical treatment should be supplemented with high-quality perioperative care, ideally performed by multidisciplinary teams trained to identify and handle complex postoperative courses. Uncontrolled or poorly controlled acute postoperative pain may result in significant complications. While pain management after elective surgery has been standardized in perioperative pathways, the traditional perioperative treatment of patients undergoing emergency surgery is often a haphazard practice. The present recommended pain management guidelines are for pain management after non-traumatic emergency surgical intervention. It is meant to provide clinicians a list of indications to prescribe the optimal analgesics even in the absence of a multidisciplinary pain team.

MATERIAL AND METHODS

An international expert panel discussed the different issues in subsequent rounds. Four international recognized scientific societies: World Society of Emergency Surgery (WSES), Global Alliance for Infection in Surgery (GAIS), Italian Society of Anesthesia, Analgesia Intensive Care (SIAARTI), and American Association for the Surgery of Trauma (AAST), endorsed the project and approved the final manuscript.

CONCLUSION

Dealing with acute postoperative pain in the emergency abdominal surgery setting is complex, requires special attention, and should be multidisciplinary. Several tools are available, and their combination is mandatory whenever is possible. Analgesic approach to the various situations and conditions should be patient based and tailored according to procedure, pathology, age, response, and available expertise. A better understanding of the patho-mechanisms of postoperative pain for short- and long-term outcomes is necessary to improve prophylactic and treatment strategies.

Preparation and evaluation of liposome with ropivacaine ion-pairing in local pain management

Local analgesia is one of the most desirable methods for postoperative pain control, while the existing local anesthetics have a short duration of analgesic effect. Nano-drug carriers have been widely used in various fields and provide an excellent strategy for traditional drugs. Although the existing liposomes for local anesthetics have certain advantages, their instability and complexity of the preparation process still cannot be ignored. Here, we developed novel ropivacaine hydrochloride liposomes with improved stability and sustained release performance by combining ropivacaine hydrochloride with sodium oleate in liposomes via hydrophobic ion-pairing (HIP). The liposomes are easy to prepare, inexpensive, and suitable for mass production. The infrared (IR), particle size, and Zeta potential measurements adequately characterized the complex, which showed a diameter of 81.09 nm and a zeta potential of -83.3 mV. Animal behavioral experiments, including the hot plate test and von Frey fiber test, demonstrated that the liposome system had a prolonged analgesic effect of 2 h versus conventional liposome preparations, consistent with the results of in vitro release experiments. In addition, in vitro cytotoxicity evaluations in RAW264.7 cells and in vivo evaluations revealed the biocompatibility and safety of the ropivacaine-sodium oleate ion-paired liposome (Rop-Ole-Lipo) system as a suitable local anesthetic for local pain management. Our findings provide a new idea for the preparation of local anesthetics.

A Smarter Health through the Internet of Surgical Things

(1) Background: In the last few years, technological developments in the surgical field have been rapid and are continuously evolving. One of the most revolutionizing breakthroughs was the introduction of the IoT concept within surgical practice. Our systematic review aims to summarize the most important studies evaluating the IoT concept within surgical practice, focusing on Telesurgery and surgical Telementoring. (2) Methods: We conducted a systematic review of the current literature, focusing on the Internet of Surgical Things in Telesurgery and Telementoring. Forty-eight (48) studies were included in this review. As secondary research questions, we also included brief overviews of the use of IoT in image-guided surgery, and patient Telemonitoring, by systematically analyzing fourteen (14) and nineteen (19) studies, respectively. (3) Results: Data from 219 patients and 757 healthcare professionals were quantitively analyzed. Study designs were primarily observational or based on model development. Palpable advantages from the IoT incorporation mainly include less surgical hours, accessibility to high quality treatment, and safer and more effective surgical education. Despite the described technological advances, and proposed benefits of the systems presented, there are still identifiable gaps in the literature that need to be further explored in a systematic manner. (4) Conclusions: The use of the IoT concept within the surgery domain is a widely incorporated but less investigated concept. Advantages have become palpable over the past decade, yet further research is warranted.

Artificial intelligence and anesthesia: A narrative review

Rapid advances in Artificial Intelligence (AI) have led to diagnostic, therapeutic, and intervention-based applications in the field of medicine. Today, there is a deep chasm between AI-based research articles and their translation to clinical anesthesia, which needs to be addressed. Machine learning (ML), the most widely applied arm of AI in medicine, confers the ability to analyze large volumes of data, find associations, and predict outcomes with ongoing learning by the computer. It involves algorithm creation, testing and analyses with the ability to perform cognitive functions including association between variables, pattern recognition, and prediction of outcomes. AI-supported closed loops have been designed for pharmacological maintenance of anesthesia and hemodynamic management. Mechanical robots can perform dexterity and skill-based tasks such as intubation and regional blocks with precision, whereas clinical-decision support systems in crisis situations may augment the role of the clinician. The possibilities are boundless, yet widespread adoption of AI is still far from the ground reality. Patient-related “Big Data” collection, validation, transfer, and testing are under ethical scrutiny. For this narrative review, we conducted a PubMed search in 2020-21 and retrieved articles related to AI and anesthesia. After careful consideration of the content, we prepared the review to highlight the growing importance of AI in anesthesia. Awareness and understanding of the basics of AI are the first steps to be undertaken by clinicians. In this narrative review, we have discussed salient features of ongoing AI research related to anesthesia and perioperative care.

Pharmacokinetic comparison of nalbuphine with single injection and patient-controlled analgesia mimic method in healthy Chinese volunteers

WHAT IS KNOWN AND OBJECTIVE

Nalbuphine is a mu (μ) receptor partial antagonist/kappa (κ) receptor agonist analgesic and can be administered as a single injection or using patient-controlled analgesia (PCA) in the clinical setting. However, differences in the pharmacokinetics of the two administration methods are unclear. Here, a clinical trial was performed to compare the pharmacokinetic characteristics and superiority of nalbuphine with a single-injection or PCA-mimic method to provide a reference for the selection of an appropriate administration method.

METHODS

Twenty healthy individuals were divided into two groups and injected with 10 mg nalbuphine intravenously using a single-injection or a PCA-mimic method (2 mg once for five times with a 30-min interval). Blood samples were collected, and safety was investigated. The liquid chromatography-tandem mass spectrometry was adopted to determine the concentration of nalbuphine in plasma.

RESULTS AND DISCUSSION

The maximum concentration (C_max ) and area under concentration-time curve (AUC_0-t ) values of nalbuphine in the single-injection and PCA groups were as follows: C_max , 81.3 ± 24.7 and 39.8 ± 6.4 ng/ml, respectively; moreover, AUC_0-t , 110.3 ± 19.5 and 128.3 ± 23.0 h ng/ml, respectively. The effective analgesic concentration durations (EACDs) for the two administration methods were 1.39 ± 0.64 and 1.96 ± 0.91 h, respectively. Nalbuphine was well tolerated, and improvements were observed in the PCA group.

WHAT IS NEW AND CONCLUSION

Compared with those in the single-injection group, the AUC_0-t and EACDs in the PCA group were similar, whereas C_max was decreased significantly. Therefore, the PCA method was more suitable for the clinical application of nalbuphine injection owing to the superiority of lower concentration fluctuation and the improved safety profile.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Artificial Intelligence and technology in COVID Era: A narrative review

Application of artificial intelligence (AI) in the medical field during the coronavirus disease 2019 (COVID-19) era is being explored further due to its beneficial aspects such as self-reported data analysis, X-ray interpretation, computed tomography (CT) image recognition, and patient management. This narrative review article included published articles from MEDLINE/PubMed, Google Scholar and National Informatics Center egov mobile apps. The database was searched for "Artificial intelligence" and "COVID-19" and "respiratory care unit" written in the English language during a period of one year 2019-2020. The relevance of AI for patients is in hands of people with digital health tools, Aarogya setu app and Smartphone technology. AI shows about 95% accuracy in detecting COVID-19-specific chest findings. Robots with AI are being used for patient assessment and drug delivery to patients to avoid the spread of infection. The pandemic outbreak has replaced the classroom method of teaching with the online execution of teaching practices and simulators. AI algorithms have been used to develop major organ tissue characterization and intelligent pain management techniques for patients. The Blue-dot AI-based algorithm helps in providing early warning signs. The AI model automatically identifies a patient in respiratory distress based on face detection, face recognition, facial action unit detection, expression recognition, posture, extremity movement analysis, visitation frequency detection sound pressure, and light level detection. There is now no looking back as AI and machine learning are to stay in the field of training, teaching, patient care, and research in the future.