Conducting a systematic review (SR) of clinical trials is labor-intensive and expensive. However, existing open-source content can be used to develop custom machine learning tools suited to the workflow of individual organizations. This case study details the potential of a bespoke tool developed by York Health Economics Consortium (YHEC) for reducing the time and cost involved in producing an SR.

RESbot is a flexible, stand-alone machine learning tool created using an extensively tested open-source dataset developed by Cochrane. The tool identifies randomized controlled trials (RCTs) from a large corpus of records. It has a user interface and inputs/outputs to fit into the company’s existing workflow at any stage. RESbot has two settings. The “sensitive” setting identifies a higher number of possible RCTs with a lower risk of missing eligible studies, while the “precise” setting is more focused. For both settings, we estimated the reduction in resources required for record screening in two examples of RCT-only reviews.

Scoping searches in MEDLINE were conducted for SRs of RCTs in femoropopliteal artery diseases (FAD) and postpartum depression (PD). The results were run through RESbot. For the FAD SR, 1,444 references were retrieved, with the sensitive and precise RESbot settings reducing the record set by 38 percent and 64 percent, respectively. For the PD SR, a record set of 2,153 records was reduced by 25 percent and 41 percent, respectively. Resource savings offered by RESbot vary depending on subject but may reduce the time taken to screen records by up to 64 percent, with a subsequent reduction in cost to the organization commissioning the SR.

The use of bespoke machine learning tools in SR production has the potential to reduce the time and staff costs involved in producing a review. This case study tested the effect on a small number of records, but for larger reviews retrieving tens of thousands of records, reductions in time and costs can be very significant.

Personalised management of recurrent depression, considering individual patient characteristics, is crucial.

This study evaluates the potentially different mediating role of mindfulness skills in managing recurrent depression using mindfulness-based cognitive therapy (MBCT) among people with varying depression severity.

Data from the Prevention of Depressive Relapse or Recurrence (PREVENT) trial, comparing MBCT (with antidepressant medication (ADM) tapering support, MBCT-tapering support) versus maintenance-ADM, were used. The study included pre, post, 9-, 12-, 18- and 24-month follow-ups. Adults with ≥3 previous major depressive episodes, in full/partial remission (below threshold for a current episode), on ADM, were assessed for eligibility in primary care practices in the UK. People were randomised (1:1) to MBCT-tapering support or maintenance-ADM. We used the Beck Depression Inventory-II to evaluate depressive symptom changes over the six time points. Pre-post treatment, we employed the Five Facets of Mindfulness Questionnaire to gauge mindfulness skills. Baseline symptom and history variables were used to identify individuals with varying severity profiles. We conducted Latent Profile Moderated-Mediation Growth Mixture Models.

A total of 424 people (mean (s.d.) age = 49.44 (12.31) years; with 325 (76.7%) self-identified as female) were included. A mediating effect of mindfulness skills, between trial arm allocation and the linear rate of depressive symptoms change over 24 months, moderated by depression severity, was observed (moderated-mediation index = −0.27, 95% CI = −0.66, −0.03). Conditional indirect effects were −0.42 (95% CI = −0.78, −0.18) for higher severity (expected mean BDI-II reduction = 10 points), and −0.15 (95% CI = −0.35, −0.02) for lower severity (expected mean BDI-II reduction = 3.5 points).

Mindfulness skills constitute a unique mechanism driving change in MBCT (versus maintenance-ADM). Individuals with higher depression severity may benefit most from MBCT-tapering support for residual symptoms. It is unclear if these effects apply to those with a current depressive episode. Future research should investigate individuals who are not on medication. This study provides preliminary evidence for personalised management of recurrent depression.

ISRCTN26666654.

In South Africa, most of the cognitive tests employed for neuropsychological evaluation are those developed in educationally advantaged settings such as the US, but the normative data accompanying the tests are unsuitable for use with South African examinees who have a disadvantaged quality of education, and/or whose primary language is other than English. A recently completed collation of Africa-based normative data (Shuttleworth-Edwards & Truter, 2022) includes a chapter on Performance Validity Tests (PVTs) with proposed cut-off points to assist in the identification of noncredible performance. The aim of this study was to compare the cut-off points established using educationally disadvantaged South African nonclinical normative samples for which only specificity percentages are available, with those established using clinical samples with designated valid and invalid performers for which both specificity and sensitivity data are available. A further aim was to compare the Africa-based cut-off points with age-equivalent cut-off points where available for US-based data on the targeted tests.

The collation of Africa-based studies delineates cut-off scores for invalid test performance based on both nonclinical as well as clinical populations for three stand-alone PVTs especially developed to identify invalid performance including the Dot Counting Test (DCT), the Rey Fifteen Item Test (FIT), and the Test of Memory Malingering (TOMM); and three commonly employed cognitive tests for which there are embedded validity indicators including the Digit Span Age-Corrected Scaled Score (ACSS) and Reliable Digit Span (RDS), the Rey Auditory Verbal Learning Test (RAVLT), and the Trail Making Test A and B (TMT A and B). For studies using nonclinical norming data alone, specificity percentages to derive the cut-off points were set at a minimum of 90%. For studies using clinical samples specificity was set at a minimum of 90%, and the associated sensitivity percentages were reported indicating each test’s ability to correctly identify those with an invalid performance. The studies included participants stratified for both child and adult age groups (age 8 to 79 years) from South African educationally disadvantaged backgrounds. The data were tabled together for descriptive comparison purposes, including a column for the US-base cut-off points for equivalent age stages where available.

There was a high level of compatibility between the proposed cut-off points established for the South African nonclinical normative samples compared with those using clinical samples of designated valid and invalid performers. There was a trend for more lenient cut-offs for younger children and older adults compared to older children and younger adults. Compared with US-based data where available, adjustments towards leniency were called-for on all indicators.

Cut-off scores for invalid cognitive test performance can be verified by perusing data derived from nonclinical norming samples as well as those from clinical samples, although the latter have the advantage of providing the sensitivity data to demonstrate the efficacy of a proposed cut-off score for identifying noncredible test performance. Adjustments towards leniency need to be made for cut-off scores for young children and older adults within an educationally disadvantaged population, and for disadvantaged adult populations compared with US-based educationally advantaged populations.

South Africa has a multi-lingual population where fewer than 10% of the population speak English as a first language. This poses a challenge regarding language usage for a verbal fluency task. This study investigated the difference in number of words produced by independent groups of non-English examinees required to produce words in English, or in their first language, on a category verbal fluency task.

A study on South African non-English first language participants was conducted using the Category Verbal Fluency test (animals) for a sample of nonclinical adults (N = 264) aged 18-60 years with 8-12 years of disadvantaged (poorly resourced) quality of education. Participants either had an African indigenous first language, or Afrikaans (a Dutch derivative) as a first language. The data were derived from one group of either African indigenous or Afrikaans first language participants who were required to use English for word production (Group A English) (n = 159; African indigenous n = 135; Afrikaans n = 24) and another group of participants who were required to use their first language (Group B First Language) (n = 105; African indigenous n = 83; Afrikaans n = 22). The comparative data were stratified for age ranges 18-20, 21-30, 31-40, 41-50 and 51-60 years. Level of education was broadly equivalent across the comparative groups. T-test analyses compared the number of words produced between the English versus indigenous African groups, and English versus Afrikaans first language groups for each age category.

The comparison for the indigenous African first language participants, revealed no significant differences in word production for words produced in English or first language regardless of age. In the comparison for the Afrikaans first language participants there was a highly consistent tendency for better word production in Afrikaans than in English. These results indicate that socio-cultural factors may be influential for English language proficiency on a verbal fluency task, rather than the effect of first language usage “per se”.

Since the dismantling of the Apartheid system in South Africa thirty years ago, English has become the main language used in government and business and is the preferred language of tuition in schools for those speaking English or an African indigenous language, whereas during the Apartheid era, two official languages were used for government, business, and schooling (Afrikaans and English). Currently, many Afrikaans speaking individuals continue to have Afrikaans as the preferred primary language of tuition in the schools and it persists as the preferred language for use in many Afrikaans dominated business arenas. This study attests to a high level of English fluency amongst those South Africans with an indigenous African first language, who clearly are as fluent in word production using English as they are when using their first language, in contrast to the indications for Afrikaans speaking individuals. Practitioners need to be alert to sociocultural factors that can impact on the optimal use of language in test situations, which may not necessarily be the first language.

Adverse effects are a common concern when prescribing and reviewing medication, particularly in vulnerable adults such as older people and those with intellectual disability. This paper describes the development of an app giving information on side-effects, called Medichec, and provides a description of the processes involved in its development and how drugs were rated for each side-effect. Medications with central anticholinergic action, dizziness, drowsiness, hyponatraemia, QTc prolongation, bleeding and constipation were identified using the British National Formulary (BNF) and frequency of occurrence of these effects was determined using the BNF, product information and electronic searches, including PubMed.

Medications were rated using a traffic light system according to how commonly the adverse effect was known to occur or the severity of the effect.

Medichec can facilitate access to side-effects information for multiple medications, aid clinical decision-making, optimise treatment and improve patient safety in vulnerable adults.