Machine learning algorithms may radically improve our ability to diagnose and treat disease. For moral, legal, and scientific reasons, it is essential that doctors and patients be able to understand and explain the predictions of these models. Scalable, customisable, and ethical solutions can be achieved by working together with relevant stakeholders, including patients, data scientists, and policy makers.

Machine intelligence already helps medical staff with a number of tasks. Ethical decision-making, however, has not been handed over to computers. In this proof-of-concept study, we show how an algorithm based on Beauchamp and Childress’ prima-facie principles could be employed to advise on a range of moral dilemma situations that occur in medical institutions. We explain why we chose fuzzy cognitive maps to set up the advisory system and how we utilized machine learning to train it. We report on the (...) difficult task of operationalizing the principles of beneficence, non-maleficence and patient autonomy, and describe how we selected suitable input parameters that we extracted from a training dataset of clinical cases. The first performance results are promising, but an algorithmic approach to ethics also comes with several weaknesses and limitations. Should one really entrust the sensitive domain of clinical ethics to machine intelligence? (shrink)

Magnetoencephalography is increasingly used for presurgical planning in people with medically refractory focal epilepsy. Localization of interictal epileptiform activity, a surrogate for the seizure onset zone whose removal may prevent seizures, is challenging and depends on the use of multiple complementary techniques. Accurate and reliable localization of epileptiform activity from spontaneous MEG data has been an elusive goal. One approach toward this goal is to use a novel Bayesian inference algorithm—the Champagne algorithm with noise learning—which has shown tremendous success in (...) source reconstruction, especially for focal brain sources. In this study, we localized sources of manually identified MEG spikes using the Champagne algorithm in a cohort of 16 patients with medically refractory epilepsy collected in two consecutive series. To evaluate the reliability of this approach, we compared the performance to equivalent current dipole modeling, a conventional source localization technique that is commonly used in clinical practice. Results suggest that Champagne may be a robust, automated, alternative to manual parametric dipole fitting methods for localization of interictal MEG spikes, in addition to its previously described clinical and research applications. (shrink)

Machine learning algorithms are expected to improve referral decisions. In this article I discuss the legitimacy of deferring referral decisions in primary care to recommendations from such algorithms. The standard justification for introducing algorithmic decision procedures to make referral decisions is that they are more accurate than the available practitioners. The improvement in accuracy will ensure more efficient use of scarce health resources and improve patient care. In this article I introduce a proceduralist framework for discussing the legitimacy (...) of algorithmic referral decisions and I argue that in the context of referral decisions the legitimacy of an algorithmic decision procedure can be fully accounted for in terms of the instrumental values of accuracy and fairness. I end by considering how my discussion of procedural algorithmic legitimacy relates to the debate on algorithmic fairness. (shrink)

State prescription drug monitoring programs (PDMPs) use proprietary, predictive software platforms that deploy algorithms to determine whether a patient is at risk for drug misuse, drug diversion, doctor shopping, or substance use disorder (SUD). Clinical overreliance on PDMP algorithm‐generated information and risk scores motivates clinicians to refuse to treat—or to inappropriately treat—vulnerable people based on actual, perceived, or past SUDs, chronic pain conditions, or other disabilities. This essay provides a framework for challenging PDMP algorithmic discrimination as disability discrimination (...) under federal antidiscrimination laws, including a new proposed rule interpreting section 1557 of the Affordable Care Act. (shrink)

The application of machine-learning technologies to medical practice promises to enhance the capabilities of healthcare professionals in the assessment, diagnosis, and treatment, of medical conditions. However, there is growing concern that algorithmic bias may perpetuate or exacerbate existing health inequalities. Hence, it matters that we make precise the different respects in which algorithmic bias can arise in medicine, and also make clear the normative relevance of these different kinds of algorithmic bias for broader questions about justice and fairness in healthcare. (...) In this paper, we provide the building blocks for an account of algorithmic bias and its normative relevance in medicine. (shrink)

While principle-based ethics is well known and widely accepted in psychiatry, much less is known about how decisions are made in clinical practice, which case scenarios exist, and which challenges exist for decision-making. Protocols of the central ethics committee responsible for four psychiatric hospitals over 7 years (N=17) were analysed. While four cases concerned suicide risk in the case of intended hospital discharge, the vast majority (N=13) concerned questions of whether the responsible physician should or should not initiate the (...) use of coercion in patients lacking mental capacity. The committee’s recommendations were non-uniform. Forced feeding and electroconvulsive therapy were endorsed in each one case. In two cases of intermittent loss of capacity due to heavy drinking or intermittent severe suicidal ideation, a self-binding contract was recommended and the use of coercion was considered as justified for a very limited period. In all other cases, most of which involved involuntary treatment, the use of coercion was not endorsed. Without exception, the recommendations were accepted with relief by the physicians and their treatment teams, who feared liability in the event of harm to the patient. Eventually, a model of a decision algorithm was derived from the ethical arguments in the protocols. (shrink)

The robustness of a health system can often be assessed by its response to unpredictable circumstances that demand resourcefulness and resilience. The ongoing COVID-19 pandemic has similarly challe...

Qualitative evidence concerning the relationship between QoL and a wide range of disabilities suggests that subjective judgments regarding other people’s QoL are wrong more often than not and that such judgments by medical practitioners in particular can be biased. Guided by their desire to do good and avoid harm, surgeons often rely on "the eyeball test" to decide whether a patient will or will not benefit from surgery. But the eyeball test can easily harbor a range of implicit judgments and (...) biases against patients with disabilities, including erroneous assumptions about QoL. We critique the use of the "eyeball" test and offer suggestions to reduce bias and ensure that patients’ values are more consistently prioritized in surgical decision-making. (shrink)

Can machine intelligence do clinical ethics? And if so, would applying it to actual medical cases be desirable? In a recent target article (Meier et al. 2022), we described the piloting of our advisory algorithm METHAD. Here, we reply to commentaries published in response to our project. The commentaries fall into two broad categories: concrete criticism that concerns the development of METHAD; and the more general question as to whether one should employ decision-support systems of this kind—the debate we (...) set out to ignite with our target article. (shrink)

In their paper “Algorithms for Ethical Decision-Making in the Clinic: A Proof of Concept,” Meier et al. present the design and preliminary results of a proof-of-concept clinical ethics algor...

Artificial Intelligence (AI) often outperforms human doctors in terms of decisional speed. For some diseases, the expected benefit of a fast but less accurate decision exceeds the benefit of a slow but more accurate one. In such cases, we argue, it is often justified to rely on a medical AI to maximise decision speed – even if the AI is less accurate than human doctors.

BackgroundSystems medicine is the name for an assemblage of scientific strategies and practices that include bioinformatics approaches to human biology ; “big data” statistical analysis; and medical informatics tools. Whereas personalized and precision medicine involve similar analytical methods applied to genomic and medical record data, systems medicine draws on these as well as other sources of data. Given this distinction, the clinical translation of systems medicine poses a number of important ethical and epistemological challenges for researchers working to generate (...) systems medicine knowledge and clinicians working to apply it.DiscussionThis article focuses on three key challenges: First, we will discuss the conflicts in decision-making that can arise when healthcare providers committed to principles of experimental medicine or evidence-based medicine encounter individualized recommendations derived from computer algorithms. We will explore in particular whether controlled experiments, such as comparative effectiveness trials, should mediate the translation of systems medicine, or if instead individualized findings generated through “big data” approaches can be applied directly in clinical decision-making. Second, we will examine the case of the Riyadh Intensive Care Program Mortality Prediction Algorithm, pejoratively referred to as the “death computer,” to demonstrate the ethical challenges that can arise when big-data-driven scoring systems are applied in clinical contexts. We argue that the uncritical use of predictive clinical algorithms, including those envisioned for systems medicine, challenge basic understandings of the doctor-patient relationship. Third, we will build on the recent discourse on secondary findings in genomics and imaging to draw attention to the important implications of secondary findings derived from the joint analysis of data from diverse sources, including data recorded by patients in an attempt to realize their “quantified self.”SummaryThis paper examines possible ethical challenges that are likely to be raised as systems medicine to be translated into clinical medicine. These include the epistemological challenges for clinical decision-making, the use of scoring systems optimized by big data techniques and the risk that incidental and secondary findings will significantly increase. While some ethical implications remain still hypothetical we should use the opportunity to prospectively identify challenges to avoid making foreseeable mistakes when systems medicine inevitably arrives in routine care. (shrink)

The amount of data available to healthcare practitioners is growing, and the rapid increase in available patient data is becoming a problem for healthcare practitioners, as they are often unable to fully survey and process the data relevant for the treatment or care of a patient. Consequently, there are currently several efforts to develop systems that can aid healthcare practitioners with reading and processing patient data and, in this way, provide them with a better foundation for decision-making about the treatment (...) and care of patients. There are also efforts to develop algorithms that provide suggestions for such decisions. However, the development of these systems and algorithms raises several concerns related to the privacy of patients, the patient–practitioner relationship, and the autonomy of healthcare practitioners. The aim of this article is to provide a foundation for understanding the ethical challenges related to the development of a specific form of data-processing systems, namely clinical algorithms. (shrink)

Machine learning and other forms of artificial intelligence can improve parts of clinical decision making regarding the gathering and analysis of data, the detection of disease, and the provis...

The question of the extent to which one can rationally reconstruct the process of medical diagnosis and reduce it to an algorithm is explored. The act of diagnostic insight is such that a computational program cannot ‘catch on’ in the way that a competent diagnostician can. Clinical diagnostic reasoning in a particular case requires as a necessary condition an extraordinarily complex and rich structure of background knowledge as well as an intuitive element, such as is manifest when one ‘catches (...) on’ to a joke. Computers cannot ‘catch on’ due to their limitations in the computational mode. As a consequence, there can be no computer simulation of an essential element in diagnostic procedures. Keywords: clinical judgment, computer diagnosis, intuition, medical decision-making CiteULike Connotea Del.icio.us What's this? (shrink)

One of the main challenges in medicine is to guarantee an appropriate drug supply according to the real needs of patients. Closed-loop strategies have been widely used to develop automatic solutions based on feedback variables. However, when the variable of interest cannot be directly measured or there is a lack of knowledge behind the process, it turns into a difficult issue to solve. In this research, a novel algorithm to approach this problem is presented. The main objective of this study (...) is to provide a new general algorithm capable of determining the influence of a certain clinical variable in the decision making process for drug supply and then defining an automatic system able to guide the process considering this information. Thus, this new technique will provide a way to validate a given physiological signal as a feedback variable for drug titration. In addition, the result of the algorithm in terms of fuzzy rules and membership functions will define a fuzzy-based decision system for the drug delivery process. The method proposed is based on a Fuzzy Inference System whose structure is obtained through a decision tree algorithm. A four-step methodology is then developed: data collection, preprocessing, Fuzzy Inference System generation, and the validation of results. To test this methodology, the analgesia control scenario was analysed. Specifically, the viability of the Analgesia Nociception Index as a guiding variable for the analgesic process during surgical interventions was studied. Real data was obtained from fifteen patients undergoing cholecystectomy surgery. (shrink)

Artificial intelligence (AI) systems are quickly gaining ground in healthcare and clinical decision-making. However, it is still unclear in what way AI can or should support decision-making that is based on incapacitated patients’ values and goals of care, which often requires input from clinicians and loved ones. Although the use of algorithms to predict patients’ most likely preferred treatment has been discussed in the medical ethics literature, no example has been realised in clinical practice. This is due, (...) arguably, to the lack of a structured approach to the epistemological, ethical and pragmatic challenges arising from the design and use of such algorithms. The present paper offers a new perspective on the problem by suggesting that preference predicting AIs be viewed as sociotechnical systems with distinctive life-cycles. We explore how both known and novel challenges map onto the different stages of development, highlighting interdisciplinary strategies for their resolution. (shrink)

To analyze which ethically relevant biases have been identified by academic literature in artificial intelligence algorithms developed either for patient risk prediction and triage, or for contact tracing to deal with the COVID-19 pandemic. Additionally, to specifically investigate whether the role of social determinants of health have been considered in these AI developments or not. We conducted a scoping review of the literature, which covered publications from March 2020 to April 2021. ​Studies mentioning biases on AI algorithms developed (...) for contact tracing and medical triage or risk prediction regarding COVID-19 were included. From 1054 identified articles, 20 studies were finally included. We propose a typology of biases identified in the literature based on bias, limitations and other ethical issues in both areas of analysis. Results on health disparities and SDOH were classified into five categories: racial disparities, biased data, socio-economic disparities, unequal accessibility and workforce, and information communication. SDOH needs to be considered in the clinical context, where they still seem underestimated. Epidemiological conditions depend on geographic location, so the use of local data in studies to develop international solutions may increase some biases. Gender bias was not specifically addressed in the articles included. The main biases are related to data collection and management. Ethical problems related to privacy, consent, and lack of regulation have been identified in contact tracing while some bias-related health inequalities have been highlighted. There is a need for further research focusing on SDOH and these specific AI apps. (shrink)

Situations in which patients lack medical decision-making (MDM) capacity raise ethical challenges, especially when the patients decline care that their surrogate decision makers and/or clinicians agree is indicated. These patients are a vulnerable population and should receive treatment that is the standard of care, in line with their the values of their authentic self, just as any other patient would. But forcing treatment on patients who refuse it, even though they lack capacity, carries medical and psychological risks to the patients (...) and the hospital staff. It is also often impractical to force some treatments, especially in the long term. For example, independent of the ethical “should” question, how would one force hemodialysis for the rest of a patient’s life, or force a surgery that requires weeks of post-operative physical therapy? In this article we present a novel algorithm that can help clinicians with ethical and practical decision making, with the goals of achieving the best outcomes for patients and reducing moral distress for their caretakers and clinicians. (shrink)

Ataxia is a kind of external characteristics when the human body has poor coordination and balance disorder, it often indicates diseases in certain parts of the body. Many internal factors may causing ataxia; currently, observed external characteristics, combined with Doctor’s personal clinical experience play main roles in diagnosing ataxia. In this situation, different kinds of diseases may be confused, leading to the delay in treatment and recovery. Modern high precision medical instruments would provide better accuracy but the economic cost (...) is a non-negligible factor. In this paper, novel non-contact sensing technique is used to detect and distinguish sensory ataxia and cerebellar ataxia. Firstly, Romberg’s test and gait analysis data are collected by the microwave sensing platform; then, after some preprocessing, some machine learning approaches have been applied to train the models. For Romberg’s test, time domain features are considered, the accuracy of all the three algorithms are higher than 96%; for gait detection, Principal Component Analysis is used for dimensionality reduction, and the accuracies of Back Propagation neural Network, Support Vector Machine, and Random Forest are 97.8, 98.9, and 91.1%, respectively. (shrink)

Allowing algorithms to guide or determine decision-making in ethically complex situations, and eventually satisfying the need for good clinical ethics consultation work, is a philosophically intere...

The aim of this article is to explore the complex forms of knowledge involved in diagnostic and interventional decision making by comparing the processes in medicine and nursing, including nurse practitioners. Many authors assert that the practice of clinical decision making involves the application of theoretical knowledge (acquired in the classroom and textbooks) as well as research evidence, upon concrete particular cases. This approach draws on various universal principles and algorithms to facilitate the task. On the other hand, (...) others argue that this involves an intuitive form of judgement that is difficult to teach, one that is acquired principally through experience. In an exploration of these issues, this article consists of three sections. A clarification of terms commonly used when discussing decision making is provided in the first section. In the second section, an epistemological analysis of decision making is presented by examining several perspectives and comparing them for their use in the nursing and medical literature. Bunge's epistemological framework for decision making (based on scientific realism) is explored for its fit with the aims of medicine and nursing. The final section presents a discussion of knowledge utilization and decision making as it relates to the implications for the education and ongoing development of nurse practitioners. It is concluded that Donald Schön's conception of reflective practice best characterizes the skilful conduct of clinical decision making. (shrink)

Machine Learning (ML) is on the rise in medicine, promising improved diagnostic, therapeutic and prognostic clinical tools. While these technological innovations are bound to transform health care, they also bring new ethical concerns to the forefront. One particularly elusive challenge regards discriminatory algorithmic judgements based on biases inherent in the training data. A common line of reasoning distinguishes between justified differential treatments that mirror true disparities between socially salient groups, and unjustified biases which do not, leading to misdiagnosis and (...) erroneous treatment. In the curation of training data this strategy runs into severe problems though, since distinguishing between the two can be next to impossible. We thus plead for a pragmatist dealing with algorithmic bias in healthcare environments. By recurring to a recent reformulation of William James’s pragmatist understanding of truth, we recommend that, instead of aiming at a supposedly objective truth, outcome-based therapeutic usefulness should serve as the guiding principle for assessing ML applications in medicine. (shrink)

Many clinical and psychological constructs are conceptualized to have multivariate higher-order constructs that give rise to multidimensional lower-order traits. Although recent measurement models and computing algorithms can accommodate item response data with a higher-order structure, there are few measurement models and computing techniques that can be employed in the context of complex research synthesis, such as meta-analysis of individual participant data or integrative data analysis. The current study was aimed at modeling complex item responses that can arise when (...) underlying domain-specific, lower-order traits are hierarchically related to multiple higher-order traits for individual participant data from multiple studies. We formulated a multi-group, multivariate higher-order item response theory (HO-IRT) model from a Bayesian perspective and developed a new Markov chain Monte Carlo (MCMC) algorithm to simultaneously estimate the (a) structural parameters of the first- and second-order latent traits across multiple groups and (b) item parameters of the model. Results from a simulation study support the feasibility of the MCMC algorithm. From the analysis of real data, we found that a bivariate HO-IRT model with different correlation/covariance structures for different studies fit the data best, compared to a univariate HO-IRT model or other alternate models with unreasonable assumptions (i.e., the same means and covariances across studies). Although more work is needed to further develop the method and to disseminate it, the multi-group multivariate HO-IRT model holds promise to derive a common metric for individual participant data from multiple studies in research synthesis studies for robust inference and for new discoveries. (shrink)

In clinical studies, it is important to investigate the effectiveness of different therapeutic designs, especially, multiple treatment groups to one control group. The paper mainly studies homogeneity test of many-to-one risk differences from correlated binary data under optimal algorithms. Under Donner’s model, several algorithms are compared in order to obtain global and constrained MLEs in terms of accuracy and efficiency. Further, likelihood ratio, score, and Wald-type statistics are proposed to test whether many-to-one risk differences are equal based (...) on optimal algorithms. Monte Carlo simulations show the performance of these algorithms through the total averaged estimation error, SD, MSE, and convergence rate. Score statistic is more robust and has satisfactory power. Two real examples are given to illustrate our proposed methods. (shrink)

Driven by the use cases of PubChemRDF and SCAIView, we have developed a first community-based clinical trial ontology (CTO) by following the OBO Foundry principles. CTO uses the Basic Formal Ontology (BFO) as the top level ontology and reuses many terms from existing ontologies. CTO has also defined many clinical trial-specific terms. The general CTO design pattern is based on the PICO framework together with two applications. First, the PubChemRDF use case demonstrates how a drug Gleevec is linked (...) to multiple clinical trials investigating Gleevec’s related chemical compounds. Second, the SCAIView text mining engine shows how the use of CTO terms in its search algorithm can identify publications referring to COVID-19-related clinical trials. Future opportunities and challenges are discussed. (shrink)

Bioethics, Volume 36, Issue 2, Page 134-142, February 2022.

Although there is wide agreement that ethics consults are at risk for conflicts of interest, ethics consultants have limited guidance with regard to how to identify and approach COIs. We aim to address these concerns and provide practical guidance. We will define and consider four categories of COIs: consult type, team composition, dual clinical roles and other concerns. We will define and consider six actions available for ECs to take in response to COIs: no action, disclosure only, obtaining a (...) second opinion, referring to another EC, referring to an institutional ethics committee or seeking an outside consult. We will then propose a points-based algorithm for ECs to use to determine the appropriate response to COI. Finally, we will discuss the strengths and limitations of our proposed algorithm. (shrink)

This article analyzes local algorithmic practices resulting from the increased use of time-lapse (TL) imaging in fertility treatment. The data produced by TL technologies are expected to help professionals pick the best embryo for implantation. The emergence of TL has been characterized by promissory discourses of deeper embryo knowledge and expanded selection standardization, despite professionals having no conclusive evidence that TL improves pregnancy rates. Our research explores the use of TL tools in embryology labs. We pay special attention to standardization (...) efforts and knowledge-creation facilitated through TL and its incorporated algorithms. Using ethnographic data from five UK clinical sites, we argue that knowledge generated through TL is contingent upon complex human–machine interactions that produce local uncertainties. Thus, algorithms do not simply add medical knowledge. Rather, they rearrange professional practice and expertise. Firstly, we show how TL changes lab routines and training needs. Secondly, we show that the human input TL requires renders the algorithm itself an uncertain and situated practice. This, in turn, raises professional questions about the algorithm’s authority in embryo selection. The article demonstrates the embedded nature of algorithmic knowledge production, thus pointing to the need for STS scholarship to further explore the locality of algorithms and AI. (shrink)

In this paper, we examine the qualitative moral impact of machine learning-based clinical decision support systems in the process of medical diagnosis. To date, discussions about machine learning in this context have focused on problems that can be measured and assessed quantitatively, such as by estimating the extent of potential harm or calculating incurred risks. We maintain that such discussions neglect the qualitative moral impact of these technologies. Drawing on the philosophical approaches of technomoral change and technological mediation theory, (...) which explore the interplay between technologies and morality, we present an analysis of concerns related to the adoption of machine learning-aided medical diagnosis. We analyze anticipated moral issues that machine learning systems pose for different stakeholders, such as bias and opacity in the way that models are trained to produce diagnoses, changes to how health care providers, patients, and developers understand their roles and professions, and challenges to existing forms of medical legislation. Albeit preliminary in nature, the insights offered by the technomoral change and the technological mediation approaches expand and enrich the current discussion about machine learning in diagnostic practices, bringing distinct and currently underexplored areas of concern to the forefront. These insights can contribute to a more encompassing and better informed decision-making process when adapting machine learning techniques to medical diagnosis, while acknowledging the interests of multiple stakeholders and the active role that technologies play in generating, perpetuating, and modifying ethical concerns in health care. (shrink)

BackgroundAs the use of AI becomes more pervasive, and computerised systems are used in clinical decision-making, the role of trust in, and the trustworthiness of, AI tools will need to be addressed. Using the case of computational phenotyping to support the diagnosis of rare disease in dysmorphology, this paper explores under what conditions we could place trust in medical AI tools, which employ machine learning.MethodsSemi-structured qualitative interviews with stakeholders who design and/or work with computational phenotyping systems. The method of (...) constant comparison was used to analyse the interview data.ResultsInterviewees emphasized the importance of establishing trust in the use of CP technology in identifying rare diseases. Trust was formulated in two interrelated ways in these data. First, interviewees talked about the importance of using CP tools within the context of a trust relationship; arguing that patients will need to trust clinicians who use AI tools and that clinicians will need to trust AI developers, if they are to adopt this technology. Second, they described a need to establish trust in the technology itself, or in the knowledge it provides—epistemic trust. Interviewees suggested CP tools used for the diagnosis of rare diseases might be perceived as more trustworthy if the user is able to vouchsafe for the technology’s reliability and accuracy and the person using/developing them is trusted.ConclusionThis study suggests we need to take deliberate and meticulous steps to design reliable or confidence-worthy AI systems for use in healthcare. In addition, we need to devise reliable or confidence-worthy processes that would give rise to reliable systems; these could take the form of RCTs and/or systems of accountability transparency and responsibility that would signify the epistemic trustworthiness of these tools. words 294. (shrink)

McCradden et al. propose to close the “AI chasm” between algorithms and clinically meaningful application using the norms of evidence-based medicine and clinical research, with the rat...

Aims: The Research Diagnostic Criteria for Temporomandi¬bular Disorders (RDC/TMD) Axis I diagnostic algorithms were demonstrated to be reliable but below target sensitivity and specificity. Empirical data supported Axis I algorithm revisions that were valid. Axis II instruments were shown to be both reliable and valid. An international consensus workshop was convened to obtain recommendations and finalization of new Axis I diagnostic algorithms and new Axis II instruments. Methods: A comprehensive search of published TMD diagnostic literature was followed by (...) review and consensus via a formal structured process by a panel of experts for revision of the RDC/TMD. Results: The recommended Diagnostic Criteria for TMD (DC/TMD) Axis I protocol includes both a valid screener for pain diagnoses and valid criteria for the most common pain-related TMDs and for one intra-articular disorder. The Axis II protocol retains selected RDC/TMD screening instruments augmented with new instruments to better assess the interactions between pain and psychosocial functioning. A comprehensive classification system is also presented. Conclusion: The recommended evidence-based DC/TMD protocol is appropriate for use in both the clinical and research settings. Simple Axis I and II screening tests augmented by validated Axis I and Axis II instruments allow for identification of simple to complex TMD patients. (shrink)

In this article I consider two pertinent questions that practitioners must consider when they deploy an algorithmic system as support in clinical shared decision‐making. The first question concerns how to interpret and assess the significance of different performance measures for clinical decision‐making. The second question concerns the professional obligations that practitioners have to communicate information about the quality of an algorithm's output to patients in light of the principles of autonomy, beneficence, and justice. In the article I review (...) the four standard performance measures used to evaluate and validate algorithms, outline their role in the discussion of algorithmic fairness, and discuss the professional responsibilities that practitioners face when communicating information about these measures to patients. (shrink)

Statistics play a critical role in biological and clinical research. However, most reports of scientific results in the published literature make it difficult for the reader to reproduce the statistical analyses performed in achieving those results because they provide inadequate documentation of the statistical tests and algorithms applied. The Ontology of Biological and Clinical Statistics (OBCS) is put forward here as a step towards solving this problem. Terms in OBCS, including ‘data collection’, ‘data transformation in statistics’, ‘data (...) visualization’, ‘statistical data analysis’, and ‘drawing a conclusion based on data’, cover the major types of statistical processes used in basic biological research and clinical outcome studies. OBCS is aligned with the Basic Formal Ontology (BFO) and extends the Ontology of Biomedical Investigations (OBI), an OBO (Open Biological and Biomedical Ontologies) Foundry ontology supported by over 20 research communities. We discuss two examples illustrating how the ontology is being applied. In the first (biological) use case, we describe how OBCS was applied to represent the high throughput microarray data analysis of immunological transcriptional profiles in human subjects vaccinated with an influenza vaccine. In the second (clinical outcomes) use case, we applied OBCS to represent the processing of electronic health care data to determine the associations between hospital staffing levels and patient mortality. Our case studies were designed to show how OBCS can be used for the consistent representation of statistical analysis pipelines under two different research paradigms. By representing statistics-related terms and their relations in a rigorous fashion, OBCS facilitates standard data analysis and integration, and supports reproducible biological and clinical research. (shrink)

Bilingualism has been identified as a potential cognitive factor linked to delayed onset of dementia as well as boosting executive functions in healthy individuals. However, more recently, this claim has been called into question following several failed replications. It remains unclear whether these contradictory findings reflect how bilingualism is defined between studies, or methodological limitations when measuring the bilingual effect. One key issue is that despite the claims that bilingualism yields general protection to cognitive processes, studies reporting putative bilingual differences (...) are often focused on domain specific experimental paradigms. This study chose a broader approach, by considering the consequences of bilingualism on a wide range of cognitive functions within individuals. We utilised 19 measures of different cognitive functions commonly associated with bilingual effects, to form a “cognitive profile” for 215 non-clinical participants. We recruited Welsh speakers, who as a group of bilinguals were highly homogeneous, as means of isolating the bilingualism criterion. We sought to determine if such analyses would independently classify bilingual/monolingual participant groups based on emergent patterns driven by collected cognitive profiles, such that population differences would emerge. Multiple predictive models were trained to independently recognise the cognitive profiles of bilinguals, older adults and higher education attainment. Despite managing to successfully classify cognitive profiles based on age and education, the model failed to differentiate between bilingual and monolingual cognitive ability at a rate greater than that of chance. Repeated modelling using alternative definitions of bilingualism, and just the older adults, yielded similar results. In all cases then, using our “bottom–up” analytical approach, there was no evidence that bilingualism as a variable indicated differential cognitive performance – as a consequence, we conclude that bilinguals are not cognitively different from their monolingual counterparts, even in older demographics. We suggest that studies that have reported a bilingual advantage could well have confounded other key variables that may be driving reported advantages. We recommend that future research refine the machine learning methods used in this study to further investigate the complex relationship between bilingualism and cognition. (shrink)

Recent developments in pattern analysis research have made this methodology suitable for the study of the processes that are set in motion in psychological interventions. Outcome research, based on the comparison between clinical results from treatment and control groups, has leveraged our empirical knowledge about the efficacy of psychological interventions. However, these methods of research are not precise enough for the analysis of these processes. On the contrary, pattern analysis could be a powerful tool to study moment-to-moment interactions typical (...) of psychological interventions. This is methodology is relevant because clinical psychology is experiencing a paradigm shift from a protocol for syndrome perspective to a principle-based and person-centered intervention. This evidence-based, theory-grounded, and process-oriented paradigm of clinical intervention needs new research methods to thrive. The analysis of the therapeutic relationship built into the verbal interaction between the clinician and the client is one of the cornerstones of this new era of research. So, the purpose of this article is three-fold: to discuss the role of the verbal interaction pattern analysis in the clinical context to the development of the principle-based clinical psychology, to analyze the patterns of verbal interaction in a clinical case, and to compare the results using two different methods. To reach these purposes, using the observational methodology, we have coded the verbal interaction of 16 clinical sessions with a person diagnosed with a borderline personality disorder. We have analyzed the data using sequential analysis and pattern recognition algorithms. We have been able to detect typical patterns during different phases of psychological intervention. Finally, the conceptual, methodological, and empirical implications of this study will be discussed within the realms of pattern analysis research and principle-based clinical psychology. (shrink)

The application of machine learning and artificial intelligence in healthcare domains has received much attention in recent years, yet significant questions remain about how these new tools integrate into frontline user workflow, and how their design will impact implementation. Lack of acceptance among clinicians is a major barrier to the translation of healthcare innovations into clinical practice. In this systematic review, we examine when and how clinicians are consulted about their needs and desires for clinical AI tools. Forty-five (...) articles met criteria for inclusion, of which 24 were considered design studies. The design studies used a variety of methods to solicit and gather user feedback, with interviews, surveys, and user evaluations. Our findings show that tool designers consult clinicians at various but inconsistent points during the design process, and most typically at later stages in the design cycle. We also observed a smaller amount of studies adopting a human-centered approach and where clinician input was solicited throughout the design process. A third of all studies reported on clinician trust in clinical AI algorithms and tools. The surveyed articles did not universally report validation against the “gold standard” of clinical expertise or provide detailed descriptions of the algorithms or computational methods used in their work. To realize the full potential of AI tools within healthcare settings, our review suggests there are opportunities to more thoroughly integrate frontline users’ needs and feedback in the design process. (shrink)