Narrative Review of Decision-Making Processes in Critical Care

AI in medical diagnosis: AI prediction & human judgment

AI has long been regarded as a panacea for decision-making and many other aspects of knowledge work; as something that will help humans get rid of their shortcomings. We believe that AI can be a useful asset to support decision-makers, but not that it should replace decision-makers. Decision-making uses algorithmic analysis, but it is not solely algorithmic analysis; it also involves other factors, many of which are very human, such as creativity, intuition, emotions, feelings, and value judgments. We have conducted semi-structured open-ended research interviews with 17 dermatologists to understand what they expect from an AI application to deliver to medical diagnosis. We have found four aggregate dimensions along which the thinking of dermatologists can be described: the ways in which our participants chose to interact with AI, responsibility, 'explainability', and the new way of thinking (mindset) needed for working with AI. We believe that our findings will help physicians who might consider using AI in their diagnosis to understand how to use AI beneficially. It will also be useful for AI vendors in improving their understanding of how medics want to use AI in diagnosis. Further research will be needed to examine if our findings have relevance in the wider medical field and beyond.

Presentation of ethical criteria during medical decision-making for critically ill patients: a mixed methods study

Background

Every medical decision is based on balancing medical knowledge, ethical considerations, and patient preferences. Previous surveys have mainly covered the ethical knowledge of medical staff. The aim of this study is to evaluate the feasibility of an innovative concept regarding how ethical criteria are applied to clinical decision-making during critical illness.

Methods

An online survey including a short case vignette was carried out at a university hospital among physicians specialising in intensive care medicine in Germany. After free text responses regarding further required case information, the participants were asked to rank decision criteria during the course of the case vignette. A qualitative evaluation was performed by two independent investigators, based on a transcription into categories. This was followed by a quantitative analysis of ranked criteria.

Results

Our analysis has shown that doctors are initially inclined to consider medical information when making treatment decisions. When complications occur, ethical values are more often included in the decision-making. The qualitative evaluation reveiled that the patient's will was consistently regarded as the leading criterion for decision-making. In the quantitative evaluation, patient's well-being, quality of life, and patient autonomy were rated as the most important decision criteria. Economic factors were ranked least important.

Conclusion

A mixed methods approach is able to reflect the complexity of ethical reasoning within the medical decision-making process, suggesting the feasibility of this concept.

Clinical trial registration

The study was registered under DRKS-ID: DKRS00011905 (April 2017).

Prioritization of healthcare systems during pandemics using Cronbach's measure based fuzzy WASPAS approach

Pandemics are well-known as epidemics that spread globally and cause many illnesses and mortality. Because of globalization, the accelerated occurrence and circulation of new microbes, the infection has emerged and the incidence and movement of new microbes have sped up. Using technological devices to minimize the visit durations, specifying days for handling chronic diseases, subsidy for the staff are the alternatives that can help prevent healthcare systems from collapsing during pandemics. The study aims to define the efficient usage of optimization tools during pandemics to prevent healthcare systems from collapsing. In this study, a new integrated framework with fuzzy information is developed, which attempts to prioritize these alternatives for policymakers. First, rating data are assigned respective fuzzy values using the standard singleton grades. Later, criteria weights are determined by extending Cronbach´s measure to fuzzy context. The measure not only understands data consistency comprehensively, but also takes into consideration the attitudinal characteristics of experts. By this approach, a rational weight vector is obtained for decision-making. Further, an improved Weighted Aggregated Sum Product Assessment (WASPAS) algorithm is put forward for ranking alternatives, which is flexibly considering criteria along with personalized ordering and holistic ordering alternatives. The usefulness of the developed framework is tested with the help of a real case study. Rank values of alternatives when unbiased weights are used is given by 0.741, 0.582, 0.640 with ordering asR 1 ≻ R 3 ≻ R 2 . The sensitivity/comparative analysis reveals the impact of the proposed model as useful in selecting the best alternative for the healthcare systems during pandemics.

Machine Learning and Antibiotic Management

Machine learning and cluster analysis applied to the clinical setting of an intensive care unit can be a valuable aid for clinical management, especially with the increasing complexity of clinical monitoring. Providing a method to measure clinical experience, a proxy for that automatic gestalt evaluation that an experienced clinician sometimes effortlessly, but often only after long, hard consideration and consultation with colleagues, relies upon for decision making, is what we wanted to achieve with the application of machine learning to antibiotic therapy and clinical monitoring in the present work. This is a single-center retrospective analysis proposing methods for evaluation of vitals and antimicrobial therapy in intensive care patients. For each patient included in the present study, duration of antibiotic therapy, consecutive days of treatment and type and combination of antimicrobial agents have been assessed and considered as single unique daily record for analysis. Each parameter, composing a record was normalized using a fuzzy logic approach and assigned to five descriptive categories (fuzzy domain sub-sets ranging from “very low” to “very high”). Clustering of these normalized therapy records was performed, and each patient/day was considered to be a pertaining cluster. The same methodology was used for hourly bed-side monitoring. Changes in patient conditions (monitoring) can lead to a shift of clusters. This can provide an additional tool for assessing progress of complex patients. We used Fuzzy logic normalization to descriptive categories of parameters as a form nearer to human language than raw numbers.

The impact of critical thinking training using critical thinking cards on clinical decision-making of CCU nurses

Introduction

Due to the complexity of the situation and rapid changes in patients' clinical status in intensive care units, it is necessary to teach decision-making skills to nurses, alongside critical thinking. The aim of this study was to evaluate critical thinking training by using critical thinking cards on clinical decision-making of nurses in cardiac care units (CCU).

Methods

In this quasi-experimental study, 74 CCU nurses from the selected hospitals affiliated to Ahvaz and Dezful Universities of Medical Sciences were selected based on the inclusion criteria and were assigned to either the intervention or the control group by using permuted block randomization. The data were entered into SPSS V22 and analyzed.

Results

There was no statistically significant difference between the demographic characteristics of the two groups (P < 0.05). The mean total score of nurses' clinical decision-making before training sessions in the intervention group was calculated to be 141.59 ± 10.76, which was lower compared to a score of 148.56 ± 10.95 in the control group (P = 0.011). Therefore, covariance analysis was used to modify the results. The mean total score of nurses' clinical decision-making after the training in the intervention group was calculated as 163.82 ± 8.83, indicating a significant increase compared to a score of 154.50 ± 11.25 in the control group (P < 0.001).

Conclusion

The findings of the present study show that the education of critical thinking by using the critical card tool leads to improved clinical decision-making in CCU nurses.

Long-Term Abnormalities of Lipid Profile After a Single Episode of Sepsis

Background: Acute disturbances of the lipid profile are commonplace during acute sepsis episode. However, their long-term persistence has not to be investigated despite pivotal role of dyslipidemia in several comorbidities excessively noted in sepsis survivors (stroke, cardiomyopathy).

Methods: A total of 9,861 individuals hospitalized for a singular episode of sepsis between 2009 and 2019 were identified from electronic medical records. Lab measurements of total cholesterol (Tchol), high-density lipoprotein (HDL-c), low-density lipoprotein (LDL-c), very low-density lipoprotein (VLDL), triglycerides (TG), lipoprotein(a) [Lp (a)], apolipoprotein B (ApoB), and C-reactive protein (CRP). The data were examined as baseline values before sepsis, during hospitalization, and <3 months, 3–6 months, 6–12 months, 1–2 years, and more than 2 years from initial sepsis.

Results: Significant reductions in HDL-c (HDL_baseline = 44.06 vs. HDL_sepsis = 28.2; U = −37.79, p < 0.0001, Cohen's d = 0.22) and LDL-c serum levels were observed during and up to three months post sepsis, with females much less affected. In contrast, male subjects had derangement in HDL present for up to two years after a singular septic episode. Total cholesterol levels were slightly yet significantly elevated for up to two years after sepsis. TG were elevated up to one year [TG_baseline = 128.26 vs. TG_sepsis = 170.27, t(8255) = −21.33, p < 0.0001, Cohen's d = 0.49] and normalized. Lp(a) was elevated up to two years after initial episode [Lp(a)_baseline = 24.6 ± 16.06; Lp(a)_{sepsis−2year} = 8.25 ± 5.17; Lp(a)_{morethan2years} = 61.4 ± 40.1; ANOVA F_{(2, 24)} = 7.39; p = 0.0032]. Response to statin therapy was blunted in sepsis survivors for several years after sepsis resolution. Significant drop-out in prescription of statins and niacin after sepsis was observed. Serum high sensitivity C-reactive protein was elevated for up to five years after sepsis resolution (H [6;1685] = 502.2; p < 0.0001).

Discussion: Lipid abnormalities persisted long after the initial septic insult suggesting potential role in accelerating atherosclerosis and other abnormalities. In addition, sepsis seems to blunt statin effectiveness. Additionally, a significant and unexplained drop in statin use was seen in post-septic period.

Conclusions: Our study suggests that persistent derangements of lipid profile components for up to two years after sepsis may be associated with altered risk of atherosclerosis-related events among sepsis survivors.

Examination of Electrolyte Replacements in the ICU Utilizing MIMIC-III Dataset Demonstrates Redundant Replacement Patterns

Electrolyte repletion in the ICU is one of the most ubiquitous tasks in critical care, involving significant resources while having an unclear risk/benefit ratio. Prior data indicate most replacements are administered while electrolytes are within or above reference ranges with little effect on serum post-replacement levels and potential harm. ICU electrolyte replacement patterns were analyzed using the MIMIC-III database to determine the threshold governing replacement decisions and their efficiency. The data of serum values for potassium, magnesium, and phosphate before and after repletion events were evaluated. Thresholds for when repletion was administered and temporal patterns in the repletion behaviors of ICU healthcare providers were identified. Most electrolyte replacements happened when levels were below or within reference ranges. Of the lab orders placed, a minuscule number of them were followed by repletion. Electrolyte repletion resulted in negligible (phosphate), small (potassium), and modest (magnesium) post-replacement changes in electrolyte serum levels. The repletion pattern followed hospital routine work and was anchored around shift changes. A subset of providers conducting over-repletion in the absence of clinical indication was also identified. This pattern of behavior found in this study supports previous studies and may allude to a universal pattern of over-repletion in the ICU setting.

Competence in Decision Making: Setting Performance Standards for Critical Care

BACKGROUND

Health care professionals must be able to make frequent and timely decisions that can alter the illness trajectory of intensive care patients. A competence standard for this ability is difficult to establish yet assuring practitioners can make appropriate judgments is an important step in advancing patient safety. We hypothesized that simulation can be used effectively to assess decision-making competence. To test our hypothesis, we used a "standard-setting" method to derive cut scores (standards) for 16 simulated ICU scenarios targeted at decision-making skills and applied them to a cohort of critical care trainees.

METHODS

Panelists (critical care experts) reviewed digital audio-video performances of critical care trainees managing simulated critical care scenarios. Based on their collectively agreed-upon definition of "readiness" to make decisions in an ICU setting, each panelist made an independent judgment (ready, not ready) for a large number of recorded performances. The association between the panelists' judgments and the assessment scores was used to derive scenario-specific performance standards.

RESULTS

For all 16 scenarios, the aggregate panelists' ratings (ready/not ready for independent decision making) were positively associated with the performance scores, permitting derivation of performance standards for each scenario.

CONCLUSIONS

Minimum competence standards for high-stakes decision making can be established through standard-setting techniques. We effectively identified "front-line" providers who are, or are not, ready to make independent decisions in an ICU setting. Our approach may be used to assure stakeholders that clinicians are competent to make appropriate judgments. Further work is needed to determine whether our approach is effective in simulation-based assessments in other domains.

Future Medical Artificial Intelligence Application Requirements and Expectations of Physicians in German University Hospitals: Web-Based Survey

BACKGROUND

The increasing development of artificial intelligence (AI) systems in medicine driven by researchers and entrepreneurs goes along with enormous expectations for medical care advancement. AI might change the clinical practice of physicians from almost all medical disciplines and in most areas of health care. While expectations for AI in medicine are high, practical implementations of AI for clinical practice are still scarce in Germany. Moreover, physicians' requirements and expectations of AI in medicine and their opinion on the usage of anonymized patient data for clinical and biomedical research have not been investigated widely in German university hospitals.

OBJECTIVE

This study aimed to evaluate physicians' requirements and expectations of AI in medicine and their opinion on the secondary usage of patient data for (bio)medical research (eg, for the development of machine learning algorithms) in university hospitals in Germany.

METHODS

A web-based survey was conducted addressing physicians of all medical disciplines in 8 German university hospitals. Answers were given using Likert scales and general demographic responses. Physicians were asked to participate locally via email in the respective hospitals.

RESULTS

The online survey was completed by 303 physicians (female: 121/303, 39.9%; male: 173/303, 57.1%; no response: 9/303, 3.0%) from a wide range of medical disciplines and work experience levels. Most respondents either had a positive (130/303, 42.9%) or a very positive attitude (82/303, 27.1%) towards AI in medicine. There was a significant association between the personal rating of AI in medicine and the self-reported technical affinity level (H4=48.3, P<.001). A vast majority of physicians expected the future of medicine to be a mix of human and artificial intelligence (273/303, 90.1%) but also requested a scientific evaluation before the routine implementation of AI-based systems (276/303, 91.1%). Physicians were most optimistic that AI applications would identify drug interactions (280/303, 92.4%) to improve patient care substantially but were quite reserved regarding AI-supported diagnosis of psychiatric diseases (62/303, 20.5%). Of the respondents, 82.5% (250/303) agreed that there should be open access to anonymized patient databases for medical and biomedical research.

CONCLUSIONS

Physicians in stationary patient care in German university hospitals show a generally positive attitude towards using most AI applications in medicine. Along with this optimism comes several expectations and hopes that AI will assist physicians in clinical decision making. Especially in fields of medicine where huge amounts of data are processed (eg, imaging procedures in radiology and pathology) or data are collected continuously (eg, cardiology and intensive care medicine), physicians' expectations of AI to substantially improve future patient care are high. In the study, the greatest potential was seen in the application of AI for the identification of drug interactions, assumedly due to the rising complexity of drug administration to polymorbid, polypharmacy patients. However, for the practical usage of AI in health care, regulatory and organizational challenges still have to be mastered.