Communicating exploratory unsupervised machine learning analysis in age clustering for paediatric disease.

BACKGROUND: Despite the increasing availability of electronic healthcare record (EHR) data and wide availability of plug-and-play machine learning (ML) Application Programming Interfaces, the adoption of data-driven decision-making within routine hospital workflows thus far, has remained limited. Through the lens of deriving clusters of diagnoses by age, this study investigated the type of ML analysis that can be performed using EHR data and how results could be communicated to lay stakeholders. METHODS: Observational EHR data from a tertiary paediatric hospital, containing 61 522 unique patients and 3315 unique ICD-10 diagnosis codes was used, after preprocessing. K-means clustering was applied to identify age distributions of patient diagnoses. The final model was selected using quantitative metrics and expert assessment of the clinical validity of the clusters. Additionally, uncertainty over preprocessing decisions was analysed. FINDINGS: Four age clusters of diseases were identified, broadly aligning to ages between: 0 and 1; 1 and 5; 5 and 13; 13 and 18. Diagnoses, within the clusters, aligned to existing knowledge regarding the propensity of presentation at different ages, and sequential clusters presented known disease progressions. The results validated similar methodologies within the literature. The impact of uncertainty induced by preprocessing decisions was large at the individual diagnoses but not at a population level. Strategies for mitigating, or communicating, this uncertainty were successfully demonstrated. CONCLUSION: Unsupervised ML applied to EHR data identifies clinically relevant age distributions of diagnoses which can augment existing decision making. However, biases within healthcare datasets dramatically impact results if not appropriately mitigated or communicated.

Risk factors for situs defects and congenital heart disease in primary ciliary dyskinesia.

Primary ciliary dyskinesia (PCD) is associated with abnormal organ positioning (situs) and congenital heart disease (CHD). This study investigated genotype-phenotype associations in PCD to facilitate risk predictions for cardiac and laterality defects. This retrospective cohort study of 389 UK patients with PCD found 51% had abnormal situs and 25% had CHD and/or laterality defects other than situs inversus totalis. Patients with biallelic mutations in a subset of nine PCD genes had normal situs. Patients with consanguineous parents had higher odds of situs abnormalities than patients with non-consanguineous parents. Patients with abnormal situs had higher odds of CHD and/or laterality defects.

Home-based early intervention in infants and young children with visual impairment using the Developmental Journal: longitudinal cohort study.

AIM: To investigate the effects of home-based early intervention in children with severe visual impairment (SVI) using the Developmental Journal for babies and young children with visual impairment (DJVI). METHOD: A longitudinal observational study was undertaken with a national cohort (OPTIMUM) of infants with congenital disorders of the peripheral visual system (CDPVS) and profound-SVI; and followed up after 12 months and 24 months. Intervention was categorized according to the practitioner diary records of their usual practice over 12 months from baseline comparing those receiving the DJVI and those receiving 'Other Support'. Outcome measures of cognition and language, behaviour difficulties, parenting stress, and satisfaction with parent-practitioner partnership were collected. RESULTS: In the 54 children (26 males, 28 females, baseline mean age 13.5mo, SD 2.3mo, range 8-17mo) with 'total' CDPVS (including 16 'complex' and 38 'simple' with or without known brain disorder respectively), linear mixed effects pointed towards acceleration in sensorimotor understanding and expressive language especially in the 'simple' subsample (11.72 developmental quotient, 95% confidence interval -1.17 to 24.61, p>0.05) in those receiving the DJVI. Vision level also predicted outcomes (p<0.05). The DJVI group showed improvements in behavioural withdrawal (η2 =0.20, p=0.02, 'simple') and parenting stress (d=0.78, d=0.92, p=0.02 total and 'simple' respectively) and perceived practitioner-parent relationship (η2 =0.16, p=0.01). INTERPRETATION: Infants and young children with visual impairment receiving home-based early intervention using the DJVI with a structured developmental approach had better outcomes than those receiving 'other' home-based early interventions. Moderate to large effect improvements were found in child cognition and language, behaviour and parenting stress and the perceived practitioner-parent relationship, although cognition did not reach 5% significance level. WHAT THIS PAPER ADDS: Early intervention using the Developmental Journal for babies and young children with visual impairment was associated with enhanced developmental outcomes compared to other approaches. Improvements were also found in child behaviour, parenting stress, and perceived parent practitioner outcomes. Type and complexity of visual impairment also influenced outcomes.

INTERVENCIÓN TEMPRANA DOMICILIARIA EN LACTANTES Y NIÑOS PEQUEÑOS CON DISCAPACIDAD VISUAL USANDO EL DIARIO DE DESARROLLO: ESTUDIO LONGITUDINAL DE COHORTE: OBJETIVO: Investigar los efectos de la intervención temprana en el hogar en niños con discapacidad visual grave utilizando el Diario de Desarrollo para bebés y niños pequeños con discapacidad visual (DJVI). MÉTODO: Se realizó un estudio observacional longitudinal con una cohorte nacional (OPTIMUM) de bebés con trastornos congénitos del sistema visual periférico (CDPVS) y discapacidad visual profunda-severa; y seguimiento después de 12 meses y 24 meses. La intervención se categorizó de acuerdo con los registros del diario de desarrollo del médico en su práctica habitual más de 12 meses desde el inicio, comparando los que recibieron el DJVI y los que recibieron "otro apoyo". Se recopilaron las medidas de resultado de la cognición y el lenguaje, las dificultades de comportamiento, el estrés de los padres y la satisfacción con la asociación entre padres y profesionales. RESULTADOS: En los 54 niños (26 varones, 28 mujeres, edad media de referencia 13,5 meses, DS 2,3 meses, rango 8-17 meses) con CDPVS 'total' (incluidos 16 'complejo' y 38 'simple' con o sin trastorno cerebral conocido respectivamente), los efectos mixtos lineales apuntan hacia la aceleración en la comprensión sensoriomotora y el lenguaje expresivo, especialmente en la submuestra "simple" (cociente de desarrollo 11,72, intervalo de confianza del 95% -1,17 a 24,61, p>0,05) en los que recibieron el DJVI. El nivel de visión también predijo resultados (p <0,05). El grupo DJVI mostró mejoras en la abstinencia conductual (η2 =0,20, p=0,02, 'simple') y el estrés parental (d=0,78 − d=0,92, p=0,02 total y 'simple' respectivamente) y la relación percibida entre el médico y el padre (η2 =0,16, p=0,01). INTERPRETACIÓN: Los bebés y niños pequeños con discapacidad visual que recibieron una intervención temprana en el hogar utilizando el DJVI, con un enfoque de desarrollo estructurado, tuvieron mejores resultados que los que recibieron "otras" intervenciones tempranas en el hogar. Se encontraron mejoras de efecto moderado a grande en la cognición infantil y el lenguaje, el comportamiento y el estrés parental y la relación percibida entre el médico y el padre, aunque la cognición no alcanzó el nivel de significación del 5%.

INTERVENÇÃO PRECOCE DOMICILIAR EM LACTENTES E CRIANÇAS JOVENS COM DEFICIÊNCIA VISUAL USANDO O DEVELOPMENTAL JOURNAL: ESTUDO DE COORTE LONGITUDINAL: OBJETIVO: Investigar os efeitos da intervenção precoce domiciliar em crianças com deficiência visual severa usando o Developmental Journal para lactentes e crianças jovens com deficiência visual (DJDV). METODO: Um estudo observacional longitudinal foi realizado com uma coorte nacional (OPTIMUM) de crianças com distúrbios congênitos do sistema visual periférico (DCSVP) e deficiência visual grave-profunda, estes foram acompanhados após 12 meses e 24 meses. A intervenção foi categorizada de acordo com os registros diários do profissional de sua prática habitual ao longo de 12 meses, a partir de uma linha de base, comparando aqueles que receberam a DJDV e os que receberam "outro suporte". Resultados dos testes de cognição e linguagem, dificuldades de comportamento, estresse parental e satisfação com a parceria entre pais e profissionais, foram coletados. RESULTADOS: Nas 54 crianças (26 do sexo masculino e 28 do feminino, média de idade na linha de base de 13,5 meses; DP 2,3 meses; variação de 8 a 17 meses) com DCSVP total (incluindo 16 'complexos' e 38 'simples' com ou sem distúrbio cerebral conhecido, respectivamente), efeitos mistos lineares apontaram para um avanço na compreensão sensório-motora e de linguagem expressiva, especialmente, no subgrupo 'simples' (11,72 quociente de desenvolvimento, IC 95% -1,17 a 24,61; p>0,05) naqueles que receberam o DJDV. Nível visual também foi preditivo dos desfechos (p<0,05). O grupo DJDV apresentou melhora no comportamento de retraimento social (η2 =0,20; p=0,02; 'simples'), no estresse parental (d=0,78 − d=0,92; p=0,02 total e 'simples', respectivamente) e na percepção do relacionamento profissional-pais (η2 =0,16; p=0,01). INTERPRETAÇÃO: Lactentes e crianças jovens com deficiência visual que recebem intervenção domiciliar precoce usando a DJVI com uma abordagem de desenvolvimento estruturado tiveram resultados melhores do que aqueles que receberam "outras" intervenções precoces em casa. Melhorias com efeito de moderado a grande foram encontradas na cognição e linguagem, no comportamento infantil e estresse parental, e no relacionamento percebido entre pais e profissionais, embora a cognição não tenha alcançado nível de significância de 5%.

Cognitive behaviour treatment of co-occurring depression and generalised anxiety in routine clinical practice.

BACKGROUND: Anxiety and depression are closely associated. However, they are typically treated separately and there is a dearth of information on tackling them together. AIMS: The study's purpose was to establish how best to treat co-occurring anxiety and depression in a routine clinical service-specifically, to compare cognitive behaviour therapy (CBT) focusing only on depression (CBT-D) to a broader CBT focusing on both depression and anxiety (CBT-DA). METHOD: Case notes of 69 patients with equally severe clinical levels of depression and anxiety seen in a routine clinical service were randomly selected to review from a pool of 990 patients. The mean age was 44.61 years (SD = 12.97). 65% of the sample were female and 88% reported their ethnicity white. The content of electronic records reporting techniques used and scores on a measure of depression (The Patient Health Questionnaire) and anxiety (The Generalized Anxiety Disorder Assessment) were reviewed to categorise therapy as CBT-D or CBT-DA. RESULTS: Results indicated significant overall improvement with CBT; 70% and 77% of the sample met criteria for reliable improvement on The Patient Health Questionnaire and The Generalized Anxiety Disorder Assessment respectively. Fewer patients who received CBT-DA met The Generalized Anxiety Disorder Assessment recovery criteria at the end of treatment than those who received CBT-D. Mean post treatment PHQ-9 and GAD-7 scores remained above threshold for those receiving CBT_DA but not those receiving CBT-D. There was no evidence suggesting CBT-DA was superior to CBT-D. CONCLUSIONS: In patients with equally severe clinical levels of depression and anxiety, a broader treatment addressing both anxiety and depression does not appear to be associated with improved outcomes compared to treatment focused on depression.

Risk factors for sudden cardiac death in childhood hypertrophic cardiomyopathy: A systematic review and meta-analysis.

Aims To perform a systematic literature review and meta-analysis of clinical risk factors for sudden cardiac death (SCD) in childhood hypertrophic cardiomyopathy. Methods Medline and PubMed databases were searched for original articles published in English from 1963 through to December 2015 that included patients under 18 years of age with a primary or secondary end-point of either SCD or SCD-equivalent events (aborted cardiac arrest or appropriate implantable cardioverter-defibrillator discharge) or cardiovascular death (CVD). Results Twenty-five studies (3394 patients) met the inclusion criteria. We identified four conventional major risk factors that were evaluated in at least four studies and that we found to be statistically associated with an increased risk of death in at least two studies: previous adverse cardiac event (pooled hazard ratio [HR] 5.4, 95% confidence interval [CI] 3.67-7.95, p < 0.001); non-sustained ventricular tachycardia (pooled HR 2.13, 95% CI 1.21-3.74, p = 0.009); unexplained syncope (pooled HR 1.89, 95% CI 0.69-5.16, p = 0.22); and extreme left ventricular hypertrophy (pooled HR 1.80, 95% CI 0.75-4.32, p = 0.19). Left atrial diameter did not meet the major risk factor criteria; however, this is likely to be an additional significant risk factor. 'Minor' risk factors included a family history of SCD, gender, age, symptoms, electrocardiogram changes, abnormal blood pressure response to exercise and left ventricular outflow tract obstruction. Conclusions A lack of well-designed, large, population-based studies in childhood hypertrophic cardiomyopathy means that the evidence base for individual risk factors is not robust. We have identified four clinical parameters that are likely to be associated with increased risk of SCD, SCD-equivalent events or CVD. Multi-centre prospective studies are needed in order to further determine the relevance of these factors in predicting SCD in childhood hypertrophic cardiomyopathy and to identify novel risk markers. Condensed abstract A systematic review and meta-analysis of clinical risk factors predicting sudden cardiac death in childhood hypertrophic cardiomyopathy was performed, identifying four 'major' factors: previous adverse cardiac event; non-sustained ventricular tachycardia; syncope; and extreme left ventricular hypertrophy. Well-designed multi-centre studies are required in the future in order to confirm these findings.