Intensive care medicine in 2050: the ICU in vivo

Discrepancy between perceptions and acceptance of clinical decision support Systems: implementation of artificial intelligence for vancomycin dosing

BACKGROUND

Artificial intelligence (AI) tools are more effective if accepted by clinicians. We developed an AI-based clinical decision support system (CDSS) to facilitate vancomycin dosing. This qualitative study assesses clinicians' perceptions regarding CDSS implementation.

METHODS

Thirteen semi-structured interviews were conducted with critical care pharmacists, at Mayo Clinic (Rochester, MN), from March through April 2020. Eight clinical cases were discussed with each pharmacist (N = 104). Following initial responses, we revealed the CDSS recommendations to assess participants' reactions and feedback. Interviews were audio-recorded, transcribed, and summarized.

RESULTS

The participants reported considerable time and effort invested daily in individualizing vancomycin therapy for hospitalized patients. Most pharmacists agreed that such a CDSS could favorably affect (N = 8, 62%) or enhance (9, 69%) their ability to make vancomycin dosing decisions. In case-based evaluations, pharmacists' empiric doses differed from the CDSS recommendation in most cases (88/104, 85%). Following revealing the CDSS recommendations, we noted 78% (69/88) discrepant doses. In discrepant cases, pharmacists indicated they would not alter their recommendations. The reasons for declining the CDSS recommendation were general distrust of CDSS, lack of dynamic evaluation and in-depth analysis, inability to integrate all clinical data, and lack of a risk index.

CONCLUSION

While pharmacists acknowledged enthusiasm about the advantages of AI-based models to improve drug dosing, they were reluctant to integrate the tool into clinical practice. Additional research is necessary to determine the optimal approach to implementing CDSS at the point of care acceptable to clinicians and effective at improving patient outcomes.

Intelligent automated drug administration and therapy: future of healthcare

In the twenty-first century, the collaboration of control engineering and the healthcare sector has matured to some extent; however, the future will have promising opportunities, vast applications, and some challenges. Due to advancements in processing speed, the closed-loop administration of drugs has gained popularity for critically ill patients in intensive care units and routine life such as personalized drug delivery or implantable therapeutic devices. For developing a closed-loop drug delivery system, the control system works with a group of technologies like sensors, micromachining, wireless technologies, and pharmaceuticals. Recently, the integration of artificial intelligence techniques such as fuzzy logic, neural network, and reinforcement learning with the closed-loop drug delivery systems has brought their applications closer to fully intelligent automatic healthcare systems. This review's main objectives are to discuss the current developments, possibilities, and future visions in closed-loop drug delivery systems, for providing treatment to patients suffering from chronic diseases. It summarizes the present insight of closed-loop drug delivery/therapy for diabetes, gastrointestinal tract disease, cancer, anesthesia administration, cardiac ailments, and neurological disorders, from a perspective to show the research in the area of control theory.

Physiology and technology for the ICU in vivo

This paper discusses the physiological and technological concepts that might form the future of critical care medicine. Initially, we discuss the need for a personalized approach and introduce the concept of personalized physiological medicine (PPM), including (1) assessment of frailty and physiological reserve, (2) continuous assessment of organ function, (3) assessment of the microcirculation and parenchymal cells, and (4) integration of organ and cell function for continuous therapeutic feedback control. To understand the cellular basis of organ failure, we discuss the processes that lead to cell death, including necrosis, necroptosis, autophagy, mitophagy, and cellular senescence. In vivo technology is used to monitor these processes. To this end, we discuss new materials for developing in vivo biosensors and drug delivery systems. Such in vivo biosensors will define the diagnostic platform of the future ICU in vivo interacting with theragnostic drugs. In addition to pharmacological therapeutic options, placement and control of artificial organs to support or replace failing organs will be central in the ICU in vivo of the future. Remote monitoring and control of these biosensors and artificial organs will be made using adaptive physiological mathematical modeling of the critically ill patient. The current state of these developments is discussed.

Thinking forward: promising but unproven ideas for future intensive care

Progress toward determining the true worth of ongoing practices or value of recent innovations can be glacially slow when we insist on following the conventional stepwise scientific pathway. Moreover, a widely accepted but flawed conceptual paradigm often proves difficult to challenge, modify or reject. Yet, most experienced clinicians, educators and clinical scientists privately entertain untested ideas about how care could or should be improved, even if the supporting evidence base is currently thin or non-existent. This symposium encouraged experts to share such intriguing but unproven concepts, each based upon what the speaker considered a logical but unproven rationale. Such free interchange invited dialog that pointed toward new or neglected lines of research needed to improve care of the critically ill. In this summary of those presentations, a brief background outlines the rationale for each novel and deliberately provocative unconfirmed idea endorsed by the presenter.

Comparison of two continuous non-invasive haemodynamic monitoring techniques in the perioperative setting

BACKGROUND

The aim of the study was to identify the accuracy of and agreement between two non-invasive haemodynamic monitoring techniques in the perioperative setting - thoracic electrical bioimpedance (TEB) and Edwards Lifesciences ClearSight system (CS).

MATERIALS AND METHODS

The study included ten patients. Parametric quantitative data were expressed as mean ± SD. The Shapiro-Wilk test was used to test the normality of the distributions. A linear regression model was used to measure the strength of the linear relationship between TEB and CS. Bland-Altman analysis was performed to assess the mean difference, precision, and the limits of agreements (LOA). The Critchley and Critchley method was used to calculate the percentage error (PE), and if <30%, it was considered clinically acceptable.

RESULTS

Ten patients were involved in our study. The mean cardiac output (CO) with TEB was 6.15 ± 1.14 L/min vs. 4.78 ± 1.40 L/min with CS (p < 0.01). The relationship was significant (n = 144; r 2 = 0.7; p < 0.01). The mean bias, LOA, and PE were 1.37 ± 1.01 L/min, 3.35 L/min and -0.61 L/min and 36.22%, respectively. The mean stroke volume index (SVI) with TEB was 48.64 ± 9.8 ml/beat/m2 vs. 37.12 ± 9.14 ml/beat/m2 with CS (p < 0.01). The relationship was significant (n = 144; r 2 = 0.65; p < 0.01). The mean bias, LOA, and PE were 11.52 ± 7.92 ml/beat/m2, 27.04 ml/beat/m2 and -4 ml/beat/m2 and 36.19%.

CONCLUSIONS

The two methods of non-invasive haemodynamic monitoring are not compatible in the perioperative setting. However, the CS system has more advantages in terms of continuity and simplicity of monitoring, while measurements of TEB are interrupted by electrocautery.