No abstract

Although rapid advances in machine learning have made it increasingly applicable to expert decision-making, the delivery of accurate algorithmic predictions alone is insufficient for effective human-AI collaboration. In this work, we investigate the key types of information medical experts desire when they are first introduced to a diagnostic AI assistant. In a qualitative lab study, we interviewed 21 pathologists before, during, and after being presented deep neural network (DNN) predictions for prostate cancer diagnosis, to learn the types of information that they desired about the AI assistant. Our findings reveal that, far beyond understanding the local, case-specific reasoning behind any model decision, clinicians desired upfront information about basic, global properties of the model, such as its known strengths and limitations, its subjective point-of-view, and its overall design objective-what it's designed to be optimized for. Participants compared these information needs to the collaborative mental models they develop of their medical colleagues when seeking a second opinion: the medical perspectives and standards that those colleagues embody, and the compatibility of those perspectives with their own diagnostic patterns. These findings broaden and enrich discussions surrounding AI transparency for collaborative decision-making, providing a richer understanding of what experts find important in their introduction to AI assistants before integrating them into routine practice. CCS Concepts: • Human-centered computing → Human computer interaction (HCI).

Background

Inpatient medication-tracking tools, when designed to meet patients' needs, can play an important role in fostering patient participation in their own care and patient-provider communication during a hospital stay.

Designing Patient-Centric Information Displays for Hospitals ABSTRACTElectronic medical records are increasingly comprehensive, and this vast repository of information has already contributed to medical efficiency and hospital procedure. However, this information is not typically accessible to patients, who are frequently under-informed and unclear about their own hospital courses. In this paper, we propose a design for in-room, patient-centric information displays, based on iterative design with physicians. We use this as the basis for a Wizard-of-Oz study in an emergency department, to assess patient and provider responses to in-room information displays. 18 patients were presented with real-time information displays based on their medical records. Semi-structured interviews with patients, family members, and hospital staff reveal that subjective response to in-room displays was overwhelmingly positive, and through these interviews we elicited guidelines regarding specific information types, privacy, use cases, and information presentation techniques. We describe these findings, and we discuss the feasibility of a fully-automatic implementation of our design.

SummaryObjective: To investigate patients' experience using an inpatient personal health record (PHR) on a tablet computer to increase engagement in their hospital care. Methods: We performed observations and conducted semi-structured interviews with 14 post-operative cardiac surgical patients and their family members who received an inpatient PHR. Themes were identified using an inductive coding scheme. Results: All participants responded favorably to having access to view their clinical information. A majority (85.7%) of participants used the application following an initial training session. Patients reported high satisfaction with being able to view their hospital medications and access educational materials related to their medical conditions. Patients reported a desire to view daily progress reports about their hospital stay and have access to educational information about their postacute recovery. In addition, patients expressed a common desire to view their diagnoses, laboratory test results, radiology reports, and procedure notes in language that is patient-friendly. Conclusion:Patients have unmet information needs in the hospital setting. Our findings suggest that for some inpatients and their family members, providing personalized health information through a tablet computer may improve satisfaction, decrease anxiety, increase understanding of their health conditions, and improve safety and quality of care. BackgroundBeing a patient in the hospital is an anxiety-inducing experience. Poor communication and lack of access to information can have detrimental effects on a patient's psychological wellbeing and coping abilities [1][2][3][4][5]. Policymakers [6, 7] and patient advocates [8,9] are increasingly focusing on this problem. This study investigates how an inpatient personal health record (PHR) may help address the information needs of patients and improve their engagement and experience in the hospital.Provision of medical information and education about care can allay a patient's uncertainty and stress [10][11][12][13][14][15]. Further, sharing information has been shown to reduce patient requests for clinicians' time, foster a sense of control and empowerment while promoting self-efficacy and ownership of illness [16][17][18], and lead to increased participation as an informed partner in making health decisions [19][20][21][22]. Previous research suggests that patients want to use PHRs and believe that they will be valuable [23]. Moreover, patients believe that their adherence to treatment regimens will improve if they have the opportunity to read and understand their health information [24,25]. However, patients are not typically given the opportunity to review their health information in the hospital. For example, in a survey of hospitalized patients conducted by Cumbler and colleagues, 90% of respondents said they wanted to review their hospital medication list for accuracy, but only 28% said they were given the opportunity to do so [26]. Without access to a documented care plan, patients ar...

In the absence of universally accepted standards, medical organizations typically undergo an arduous decision-making process to develop teen portal policies, weighing legal, economic, social, clinical, and technological factors. As a result, portal access policies are highly inconsistent across the United States and within individual states.

Background Evidence for the effectiveness of treatments in early-onset psychosis is sparse. Current guidance for the treatment of early-onset psychosis is mostly extrapolated from trials in adult populations. The UK National Institute for Health and Care Excellence has recommended evaluation of the clinical effectiveness and cost-effectiveness of antipsychotic drugs versus psychological intervention (cognitive behavioural therapy [CBT] and family intervention) versus the combination of these treatments for early-onset psychosis. The aim of this study was to establish the feasibility of a randomised controlled trial of antipsychotic monotherapy, psychological intervention monotherapy, and antipsychotics plus psychological intervention in adolescents with first-episode psychosis.Methods We did a multicentre pilot and feasibility trial according to a randomised, single-blind, three-arm, controlled design. We recruited participants from seven UK National Health Service Trust sites. Participants were aged 14-18 years; help-seeking; had presented with first-episode psychosis in the past year; were under the care of a psychiatrist; were showing current psychotic symptoms; and met ICD-10 criteria for schizophrenia, schizoaffective disorder, or delusional disorder, or met the entry criteria for an early intervention for psychosis service. Participants were assigned (1:1:1) to antipsychotics, psychological intervention (CBT with optional family intervention), or antipsychotics plus psychological intervention. Randomisation was via a web-based randomisation system, with permuted blocks of random size, stratified by centre and family contact. CBT incorporated up to 26 sessions over 6 months plus up to four booster sessions, and family intervention incorporated up to six sessions over 6 months. Choice and dose of antipsychotic were at the discretion of the treating consultant psychiatrist. Participants were followed up for a maximum of 12 months. The primary outcome was feasibility (ie, data on trial referral and recruitment, session attendance or medication adherence, retention, and treatment acceptability) and the proposed primary efficacy outcome was total score on the Positive and Negative Syndrome Scale (PANSS) at 6 months. Primary outcomes were analysed by intention to treat. Safety outcomes were reported according to as-treated status, for all patients who had received at least one session of CBT or family intervention, or at least one dose of antipsychotics. The study was prospectively registered with ISRCTN, ISRCTN80567433. Findings Of 101 patients referred to the study, 61 patients (mean age 16•3 years [SD 1•3]) were recruited fromApril 10, 2017, to Oct 31, 2018, 18 of whom were randomly assigned to psychological intervention, 22 to antipsychotics, and 21 to antipsychotics plus psychological intervention. The trial recruitment rate was 68% of our target sample size of 90 participants. The study had a low referral to recruitment ratio (around 2:1), a high rate of retention (51 [84%] participants retained at the 6-mon...