As interest grows in applying natural language processing (NLP) techniques to mental health, an expanding body of work explores the automatic detection and classification of cognitive distortions (CDs). CDs are habitual patterns of negatively biased or flawed thinking that distort how people perceive events, judge themselves, and react to the world. Identifying and addressing them is a central goal of therapy. Despite this momentum, the field remains fragmented, with inconsistencies in CD taxonomies, task formulations, and evaluation practices limiting comparability across studies. This survey presents the first comprehensive review of 38 studies spanning two decades, mapping how CDs have been implemented in computational research and evaluating the methods applied. We provide a consolidated CD taxonomy reference, summarise common task setups, and highlight persistent challenges to support more coherent and reproducible research. Alongside our review, we introduce practical resources, including curated evaluation metrics from surveyed papers, a standardised datasheet template, and an ethics flowchart, available online.

BACKGROUND:The field of digital mental health has followed an exponential growth trajectory in recent years. While the evidence base has increased significantly, its adoption within health and care services has been slowed by several challenges, including a lack of knowledge from researchers regarding how to navigate the pathway for mandatory regulatory approval. This paper details the steps that a team must take to achieve the required approvals to carry out a research study using a novel digital mental health intervention. We used a randomised controlled trial of a digital mental health intervention called STOP (Successful Treatment of Paranoia) as a worked example. METHODS:The methods section explains the two main objectives that are required to achieve regulatory approval (MHRA Notification of No Objection) and the detailed steps involved within each, as carried out for the STOP trial. First, the existing safety of digital mental health interventions must be demonstrated. This can refer to literature reviews, any feasibility/pilot safety data, and requires a risk management plan. Second, a detailed plan to further evaluate the safety of the digital mental health intervention is needed. As part of this we describe the STOP study's development of a framework for categorising adverse events and based on this framework, a tool to collect adverse event data. RESULTS:We present literature review results, safety-related feasibility study findings and the full risk management plan for STOP, which addressed 26 possible hazards, and included the 6-point scales developed to quantify the probability and severity of typical risks involved when a psychiatric population receives a digital intervention without the direct support of a therapist. We also present an Adverse Event Category Framework for Digital Therapeutic Devices and the Adverse Events Checklist-which assesses 15 different categories of adverse events-that was constructed from this and used in the STOP trial. CONCLUSIONS:The example shared in this paper serves as a guide for academics and professionals working in the field of digital mental health. It provides insights into the safety assessment requirements of regulatory bodies when a clinical investigation of a digital mental health intervention is proposed. Methods, scales and tools that could easily be adapted for use in other similar research are presented, with the expectation that these will assist other researchers in the field seeking regulatory approval for digital mental health products.

BackgroundRecommender systems help narrow down a large range of items to a smaller, personalized set. NarraGive is a first-in-field hybrid recommender system for mental health recovery narratives, recommending narratives based on their content and narrator characteristics (using content-based filtering) and on narratives beneficially impacting other similar users (using collaborative filtering). NarraGive is integrated into the Narrative Experiences Online (NEON) intervention, a web application providing access to the NEON Collection of recovery narratives. ObjectiveThis study aims to analyze the 3 recommender system algorithms used in NarraGive to inform future interventions using recommender systems for lived experience narratives. MethodsUsing a recently published framework for evaluating recommender systems to structure the analysis, we compared the content-based filtering algorithm and collaborative filtering algorithms by evaluating the accuracy (how close the predicted ratings are to the true ratings), precision (the proportion of the recommended narratives that are relevant), diversity (how diverse the recommended narratives are), coverage (the proportion of all available narratives that can be recommended), and unfairness (whether the algorithms produce less accurate predictions for disadvantaged participants) across gender and ethnicity. We used data from all participants in 2 parallel-group, waitlist control clinical trials of the NEON intervention (NEON trial: N=739; NEON for other [eg, nonpsychosis] mental health problems [NEON-O] trial: N=1023). Both trials included people with self-reported mental health problems who had and had not used statutory mental health services. In addition, NEON trial participants had experienced self-reported psychosis in the previous 5 years. Our evaluation used a database of Likert-scale narrative ratings provided by trial participants in response to validated narrative feedback questions. ResultsParticipants from the NEON and NEON-O trials provided 2288 and 1896 narrative ratings, respectively. Each rated narrative had a median of 3 ratings and 2 ratings, respectively. For the NEON trial, the content-based filtering algorithm performed better for coverage; the collaborative filtering algorithms performed better for accuracy, diversity, and unfairness across both gender and ethnicity; and neither algorithm performed better for precision. For the NEON-O trial, the content-based filtering algorithm did not perform better on any metric; the collaborative filtering algorithms performed better on accuracy and unfairness across both gender and ethnicity; and neither algorithm performed better for precision, diversity, or coverage. ConclusionsClinical population may be associated with recommender system performance. Recommender systems are susceptible to a wide range of undesirable biases. Approaches to mitigating these include providing enough initial data for the recommender system (to prevent overfitting), ensuring that items can be accessed outside the recommender system (to prevent a feedback loop between accessed items and recommended items), and encouraging participants to provide feedback on every narrative they interact with (to prevent participants from only providing feedback when they have strong opinions).

Narratives describing first‐hand experiences of recovery from mental health problems are widely available. Emerging evidence suggests that engaging with mental health recovery narratives can benefit people experiencing mental health problems, but no randomized controlled trial has been conducted as yet. We developed the Narrative Experiences Online (NEON) Intervention, a web application providing self‐guided and recommender systems access to a collection of recorded mental health recovery narratives (n=659). We investigated whether NEON Intervention access benefited adults experiencing non‐psychotic mental health problems by conducting a pragmatic parallel‐group randomized trial, with usual care as control condition. The primary endpoint was quality of life at week 52 assessed by the Manchester Short Assessment (MANSA). Secondary outcomes were psychological distress, hope, self‐efficacy, and meaning in life at week 52. Between March 9, 2020 and March 26, 2021, we recruited 1,023 participants from across England (the target based on power analysis was 994), of whom 827 (80.8%) identified as White British, 811 (79.3%) were female, 586 (57.3%) were employed, and 272 (26.6%) were unemployed. Their mean age was 38.4±13.6 years. Mood and/or anxiety disorders (N=626, 61.2%) and stress‐related disorders (N=152, 14.9%) were the most common mental health problems. At week 52, our intention‐to‐treat analysis found a significant baseline‐adjusted difference of 0.13 (95% CI: 0.01‐0.26, p=0.041) in the MANSA score between the intervention and control groups, corresponding to a mean change of 1.56 scale points per participant, which indicates that the intervention increased quality of life. We also detected a significant baseline‐adjusted difference of 0.22 (95% CI: 0.05‐0.40, p=0.014) between the groups in the score on the “presence of meaning” subscale of the Meaning in Life Questionnaire, corresponding to a mean change of 1.1 scale points per participant. We found an incremental gain of 0.0142 quality‐adjusted life years (QALYs) (95% credible interval: 0.0059 to 0.0226) and a £178 incremental increase in cost (95% credible interval: –£154 to £455) per participant, generating an incremental cost‐effectiveness ratio of £12,526 per QALY compared with usual care. This was lower than the £20,000 per QALY threshold used by the National Health Service in England, indicating that the intervention would be a cost‐effective use of health service resources. In the subgroup analysis including participants who had used specialist mental health services at baseline, the intervention both reduced cost (–£98, 95% credible interval: –£606 to £309) and improved QALYs (0.0165, 95% credible interval: 0.0057 to 0.0273) per participant as compared to usual care. We conclude that the NEON Intervention is an effective and cost‐effective new intervention for people experiencing non‐psychotic mental health problems.

Paranoia, the belief that you are at risk of significant physical or emotional harm from others, is a common difficulty, which causes significant distress and impairment to daily functioning, including in psychosis-spectrum disorders. According to cognitive models of psychosis, paranoia may be partly maintained by cognitive processes, including interpretation biases. Cognitive bias modification for paranoia (CBM-pa) is an intervention targeting the bias towards interpreting ambiguous social scenarios in a way that is personally threatening. This study aims to test the efficacy and safety of a mobile app version of CBM-pa, called STOP (successful treatment of paranoia). The STOP study is a double-blind, superiority, three-arm randomised controlled trial (RCT). People are eligible for the trial if they experience persistent, distressing paranoia, as assessed by the Positive and Negative Syndrome Scales, and show evidence of an interpretation bias towards threat on standardised assessments. Participants are randomised to either STOP (two groups: 6- or 12-session dose) or text-reading control (12 sessions). Treatment as usual will continue for all participants. Sessions are completed weekly and last around 40 min. STOP is completely self-administered with no therapist assistance. STOP involves reading ambiguous social scenarios, all of which could be interpreted in a paranoid way. In each scenario, participants are prompted to consider more helpful alternatives by completing a word and answering a question. Participants are assessed at baseline, after each session, and at 6, 12, 18 and 24 weeks post-randomisation. The primary outcome is the self-reported severity of paranoid symptoms at 24 weeks, measured using the Paranoia Scale. The target sample size is 273 which is powered to detect a 15 https://doi.org/10.1186/ISRCTN17754650 .

Background:The Narrative Experiences Online (NEON) Intervention provides self-managed web-based access to mental health recovery narratives (n = 659). We evaluated effectiveness and cost-effectiveness in improving quality of life for adults resident in England with mental health problems and recent psychosis experience. Methods:Prospectively registered pragmatic parallel-group randomised trial controlling for usual care, recruiting from statutory mental health services and through community engagement activities, with a 52-week primary endpoint (ISRCTN11152837). All trial procedures and the NEON Intervention were delivered by an integrated web-application. Randomisation was through an independently generated list (no stratification). Allocation was masked for statistical staff and the Chief Investigator but not participants. Intervention arm participants received immediate NEON Intervention access. Control arm participants received access after completing primary endpoint questionnaires. The primary outcome was quality of life through the Manchester Short Assessment (MANSA). Serious Adverse Events (SAEs) were collected through web-based safety report forms and identified from health service usage data. The primary analysis was by a prospectively described Intention To Treat principle excluding participants who had registered multiple times, with multiple imputation for missing data. Findings:Between 9 March 2020 and 1 March 2021, 739 participants were randomised (intervention:370; control: 369), providing more than 90% power to detect a baseline-adjusted difference of 0.25 in the MANSA score. Mean age was 34.8 years (standard deviation (SD) 12.0), 561 (75.9%) were white British, 443 (59.9%) were female, 609 (82.4%) had accessed specialist care mental health services, and 698 (94.5%) had accessed primary care mental health services. Mean baseline MANSA score was 3.7 for control and intervention arms (SD 0.9 and 1.0). 565 (76.5%) participants provided primary endpoint MANSA data with a mean score of 4.1 (SD 1.0) for both arms. We found no significant difference in Quality of Life between the two arms at the primary endpoint (baseline-adjusted difference 0.07, 95% CI -0.07 to 0.21, p = 0.35). The incremental cost-effectiveness ratio (£110,501 per quality-adjusted life-year (QALY)) exceeded the prospectively defined cost-effectiveness threshold (£30,000 per QALY). 158 (42.8%) control arm and 194 (52.4%) intervention arm participants accessed narratives outside of the NEON Intervention. There were no related serious adverse events (SAEs). 116 unrelated SAEs were reported by control arm participants, and 107 by intervention arm participants. Interpretation:Our findings do not indicate NEON Intervention access for all people with psychosis experience. Future research should consider a) evaluation with current mental health services users; b) optimisation to enable users to find hope-promoting narratives. Funding:National Institute for Health and Care Research (NIHR).

Background Paranoia is a highly debilitating mental health condition. One novel intervention for paranoia is cognitive bias modification for paranoia (CBM-pa). CBM-pa comes from a class of interventions that focus on manipulating interpretation bias. Here, we aimed to develop and evaluate new therapy content for CBM-pa for later use in a self-administered digital therapeutic for paranoia called STOP (“Successful Treatment of Paranoia”). Objective This study aimed to (1) take a user-centered approach with input from living experts, clinicians, and academics to create and evaluate paranoia-relevant item content to be used in STOP and (2) engage with living experts and the design team from a digital health care solutions company to cocreate and pilot-test the STOP mobile app prototype. Methods We invited 18 people with living or lived experiences of paranoia to create text exemplars of personal, everyday emotionally ambiguous scenarios that could provoke paranoid thoughts. Researchers then adapted 240 suitable exemplars into corresponding intervention items in the format commonly used for CBM training and created 240 control items for the purpose of testing STOP. Each item included newly developed, visually enriching graphics content to increase the engagement and realism of the basic text scenarios. All items were then evaluated for their paranoia severity and readability by living experts (n=8) and clinicians (n=7) and for their item length by the research team. Items were evenly distributed into six 40-item sessions based on these evaluations. Finalized items were presented in the STOP mobile app, which was co-designed with a digital health care solutions company, living or lived experts, and the academic team; user acceptance was evaluated across 2 pilot tests involving living or lived experts. Results All materials reached predefined acceptable thresholds on all rating criteria: paranoia severity (intervention items: ≥1; control items: ≤1, readability: ≥3, and length of the scenarios), and there was no systematic difference between the intervention and control group materials overall or between individual sessions within each group. For item graphics, we also found no systematic differences in users’ ratings of complexity (P=.68), attractiveness (P=.15), and interest (P=.14) between intervention and control group materials. User acceptance testing of the mobile app found that it is easy to use and navigate, interactive, and helpful. Conclusions Material development for any new digital therapeutic requires an iterative and rigorous process of testing involving multiple contributing groups. Appropriate user-centered development can create user-friendly mobile health apps, which may improve face validity and have a greater chance of being engaging and acceptable to the target end users.

BackgroundMental health recovery narratives have been defined as first-person lived experience accounts of recovery from mental health problems which refer to events or actions over a period of time and which include elements of adversity or struggle, and also self-defined strengths, successes or survival. They are readily available in invariant recorded form, including text, audio or video. Previous studies have provided evidence that receiving recorded recovery narratives can provide benefits to recipients.This protocol describes three pragmatic trials that will be conducted by the Narrative Experiences Online (NEON) study using the NEON Intervention, a web application that delivers recorded recovery narratives to its users. The aim of the NEON Trial is to understand whether receiving online recorded recovery narratives through the NEON Intervention benefits people with experience of psychosis. The aim of the NEON-O and NEON-C trials is to evaluate the feasibility of conducting a definitive trial on the use of the NEON Intervention with people experiencing non-psychosis mental health problems and those who care for others experiencing mental health problems respectively.MethodsThe NEON Trial will recruit 683 participants with experience of psychosis. The NEON-O Trial will recruit at least 100 participants with experience of non-psychosis mental health problems. The NEON-C Trial will recruit at least 100 participants with experience of caring for others who have experienced mental health problems. In all three trials, participants will be randomly allocated into one of two arms. Intervention arm participants will receive treatment as usual plus immediate access to the NEON Intervention for 1 year. Control arm participants will receive treatment as usual plus access to the NEON Intervention after 1 year. All participants will complete demographics and outcome measures at baseline, 1week, 12weeks and 52weeks. For the NEON Trial, the primary outcome measure is the Manchester Short Assessment of Quality of Life at 52weeks, and secondary outcome measures are the CORE-10, Herth Hope Index, Mental Health Confidence Scale and Meaning in Life Questionnaire. A cost-effectiveness analysis will be conducted using data collected through the EQ-5D-5L and the Client Service Receipt Inventory.DiscussionNEON Trial analyses will establish both effectiveness and cost-effectiveness of the NEON Intervention for people with experience of psychosis, and hence inform future clinical recommendations for this population.Trial registrationAll trials were prospectively registered with ISRCTN. NEON Trial: ISRCTN11152837. Registered on 13 August 2018. NEON-C Trial: ISRCTN76355273. Registered on 9 January 2020. NEON-O Trial: ISRCTN63197153. Registered on 9 January 2020.

The task of data collection is becoming routine in many disciplines and this results in increased availability of data. This routinely collected data provides a valuable opportunity for analysis with a view to support evidence based decision making. In order to confidently leverage the data in support of decision making the most appropriate statistical method needs to be selected, and this can be difficult for an end user not trained in statistics. This paper outlines an application of argumentation to support the analysis of clinical data, that uses Extended Argumentation Frameworks in order to reason with the metalevel arguments derived from preference contexts relevant to the data and the analysis objective of the end user. We outline a formalisation of the argument scheme for statistical model selection, its critical questions and the structure of the knowledge base required to support the instantiation of the arguments and meta-level arguments through the use of Z notation. This paper also describes the prototype implementation of argumentation for statistical model selection based on the Z specification outlined herein.

Bayesian networks (BNs) are an important modelling technique used to support certain types of decision making in law and forensics. Their value lies in their ability to infer the rational implications of probabilistic knowledge and beliefs, a task that human decision makers struggle with. However, their use is controversial. One of the main obstacles to the more widespread use of BNs is the difficulty to acquire good explanations of the results obtained with BNs. While useful techniques exist to visualise, verbalise or abstract BNs and the inner workings of belief propagation algorithms, these techniques provide generic, one-size-fits-all explanations, that have, thus far, failed to stem the criticism of lack of explainable BN results. Building on the qualified support graph method introduced in earlier work, this paper outlines how a natural language generation system can be constructed to explain Bayesian inference. This constitutes a novel approach to BN explanation that has the potential to produce more focussed and compelling explanations of Bayesian inference as the narratives such a system produces can be tailored to address specific communicative goals and, by extension, the needs of the user.

Norms are a valuable means of establishing coherent cooperative behaviour in decentralised systems in which there is no central authority. Axelrod's seminal model of norm establishment in populations of self-interested individuals provides some insight into the mechanisms needed to support this through the use of metanorms, but considers only limited scenarios and domains. While further developments of Axelrod's model have addressed some of the limitations, there is still only limited consideration of such metanorm models with more realistic topological configurations. In response, this paper tries to address such limitation by considering its application to different topological structures. Our results suggest that norm establishment is achievable in lattices and small worlds, while such establishment is not achievable in scale-free networks, due to the problematic effects of hubs. The paper offers a solution, first by adjusting the model to more appropriately reflect the characteristics of the problem, and second by offering a new dynamic policy adaptation approach to learning the right behaviour. Experimental results demonstrate that this dynamic policy adaptation overcomes the difficulties posed by the asymmetric distribution of links in scale-free networks, leading to an absence of norm violation, and instead to norm emergence.

One of the challenges in dealing with distributed large data is to transfer massive amounts of data from multiple data server(s) to users. Unless data transfers are planned, organized and regulated carefully, they can become a potential bottleneck and may necessitate changes in queries and database design which involves costly maintenance work. This is a pronounced problem in the case of virtual observatories where data is to be brought from multiple astronomical databases from all around the world. In this paper, we present adaptive middle ware caching using sub-query fragmentation. When groups of users working on related projects query multiple databases, often their queries are overlapped only partially. We develop a cooperative cache framework with dynamic maintenance algorithms to capture user query patterns in the workload that adapts itself to provide as much data available from cache units as possible. Initial results in the simulated environment with known query inputs show significant reduction in the data to be transferred in comparison with full query caching.

Innovations in science and technology is increasing the demand on huge data transfers and hence number of data caches. In this paper, we consider the community caching solution, CommCache, where many groups of users are working together on related projects distributed all over the world. We demonstrate the use of proactive caches for data placement problem with the help of multi-agent coordination.

Bayesian models are a useful tool to propagate the rational implications of human beliefs expressed as probabilities. They can yield surprising, counterintuitive and, if based on valid models, useful results. However, human users can be reluctant to accept their results if they are unable to find explanations providing clear reasons for how and why they were arrived at, which existing explanation methods struggle with. This is particularly important in the legal domain where explanatory justifications are as important as the result and where the use of Bayesian models is controversial. This paper presents a novel approach to explain how the outcome of a query of Bayesian network was arrived at. In the process, it augments the recently developed support graph methodology and shows how support graphs can be integrated with qualitative probabilistic reasoning approaches. The usefulness of the approach is illustrated by means of a small case study, demonstrating how a seemingly counterintuitive Bayesian query result can be explained with qualitative arguments.

This paper proposes a mechanism for dealing with the growing variety and volume of digital evidence in a criminal investigation.The challenges posed by this growth have been long recognised and documented. There have been solutions aimed at processing bulk data and others based on event correlation or time lines. Instead we examine if there is an alternate method: to classify digital evidence artefacts in a way that assists selection of the potentially relevant evidence before processing any material. In so doing we wish to avoid generating bulk data and instead start viewing digital evidence from an investigative perspective - not a technological one. This paper details the continuing development of an ontology for this purpose - the Digital Evidence Semantic Ontology (DESO). This provides an index to a repository of known digital evidence artefacts which are classified according to the location that they are found and the information they represent. Further, this paper also demonstrates how DESO can be applied to criminal investigations to assist lines of enquiry. (C) 2015 Elsevier Ltd. All rights reserved.

An important challenge in the field of law is the attribution of responsibility and blame to individuals and organisations for a given harm. Attributing legal responsibility often involves (but is not limited to) assessing to what extent certain parties have caused harm, or could have prevented harm from occurring. This paper presents a causal framework for performing such assessments that is particularly suitable for the analysis of complex legal cases, where the actions of many parties have had a direct or indirect effect on the harm that did occur. This framework is evaluated by means of a case study that applies it to the Baby P. case, a high-profile case of child abuse leading to the death of a child that has been the subject of a number of public inquiries in the UK. The paper concludes with a discussion of the framework, including a roadmap of future work and barriers to adoption.

Caching frequently used data is a common practice to improve query performance in database systems. But traditional algorithms used for cache management prove to be insufficient in distributed environment where groups of users require similar or related data from multiple databases. Repeated data transfers can become a bottleneck leading to long query response time and high resource utilization. Our work focuses on adaptive algorithms to decide on optimal grain of data to be cached and cache refreshment techniques to reduce data transfers. In this paper, we present agent based simulation to investigate and in consequence improve cache management in the distributed database environment. Dynamic grain size and decisions on cache refreshment are made as a result of coordination and interaction between agents. Initial results show better response time and higher data availability compared to traditional caching techniques.

Norms provide a valuable mechanism for establishing coherent cooperative behaviour in decentralised systems in which there is no central authority. One of the most influential formulations of norm emergence was proposed by Axelrod (Am Political Sci Rev 80(4):1095–1111, 1986 ). This paper provides an empirical analysis of aspects of Axelrod’s approach, by exploring some of the key assumptions made in previous evaluations of the model. We explore the dynamics of norm emergence and the occurrence of norm collapse when applying the model over extended durations . It is this phenomenon of norm collapse that can motivate the emergence of a central authority to enforce laws and so preserve the norms, rather than relying on individuals to punish defection. Our findings identify characteristics that significantly influence norm establishment using Axelrod’s formulation, but are likely to be of importance for norm establishment more generally. Moreover, Axelrod’s model suffers from significant limitations in assuming that private strategies of individuals are available to others, and that agents are omniscient in being aware of all norm violations and punishments. Because this is an unreasonable expectation , the approach does not lend itself to modelling real-world systems such as online networks or electronic markets. In response, the paper proposes alternatives to Axelrod’s model, by replacing the evolutionary approach, enabling agents to learn, and by restricting the metapunishment of agents to cases where the original defection is observed, in order to be able to apply the model to real-world domains . This work can also help explain the formation of a “social contract” to legitimate enforcement by a central authority.

The field of digital evidence must contend with an increasing number of devices to be examined paralleled with increasing diversity. Examiners face a battle to understand what artefacts may exist on these devices. Further, many current forensic tools look to comprehensively examine sources of digital evidence which can generate large amounts of, often spurious, data with no easy means of correlation. This paper proposes the use of an ontology - the Digital Evidence Semantic Ontology (DESO) - that allows an examiner to quickly discover what artefacts may be available on a device before time-consuming processes are commenced - preventing the generation of data that may have no practical value for an investigation. The ontology is then used to classify this data so that equivalent artefacts across devices can be compared to make connections. It demonstrates how this ontology can be adapted to keep track of changes in technology and how it can be used in a laboratory environment.

The increase in routine clinical data collection coupled with an expectation to exploit this in support of evidence based decision making creates the requirement for a system to support clinicians in this analysis. This paper looks at applying argumentation to this problem, by collating all the relevant statistical approaches and their assumptions into a statistical knowledge base and then representing the model selection process through argumentation. This will form the foundation for the development of a prototype that will enable clinicians to answer their research questions with no statistics, informatics or administrative support.