Pre-hospital prediction of adverse outcomes in patients with suspected COVID-19: Development, application and comparison of machine learning and deep learning methods.

BACKGROUND: COVID-19 infected millions of people and increased mortality worldwide. Patients with suspected COVID-19 utilised emergency medical services (EMS) and attended emergency departments, resulting in increased pressures and waiting times. Rapid and accurate decision-making is required to identify patients at high-risk of clinical deterioration following COVID-19 infection, whilst also avoiding unnecessary hospital admissions. Our study aimed to develop artificial intelligence models to predict adverse outcomes in suspected COVID-19 patients attended by EMS clinicians. METHOD: Linked ambulance service data were obtained for 7,549 adult patients with suspected COVID-19 infection attended by EMS clinicians in the Yorkshire and Humber region (England) from 18-03-2020 to 29-06-2020. We used support vector machines (SVM), extreme gradient boosting, artificial neural network (ANN) models, ensemble learning methods and logistic regression to predict the primary outcome (death or need for organ support within 30 days). Models were compared with two baselines: the decision made by EMS clinicians to convey patients to hospital, and the PRIEST clinical severity score. RESULTS: Of the 7,549 patients attended by EMS clinicians, 1,330 (17.6%) experienced the primary outcome. Machine Learning methods showed slight improvements in sensitivity over baseline results. Further improvements were obtained using stacking ensemble methods, the best geometric mean (GM) results were obtained using SVM and ANN as base learners when maximising sensitivity and specificity. CONCLUSIONS: These methods could potentially reduce the numbers of patients conveyed to hospital without a concomitant increase in adverse outcomes. Further work is required to test the models externally and develop an automated system for use in clinical settings.

Evaluation of websites that contain information relating to malaria in pregnancy.

OBJECTIVES: The study identified available websites on malaria in pregnancy on the World Wide Web and sought to evaluate their readability and information quality. STUDY DESIGN: A purposeful sample of websites were selected which provided information on Malaria in pregnancy. METHODS: A total of 31 websites were identified from searches using Google, Yahoo and Bing search engines. Two generic tools (Discern and HON), one specific tool designed to assess information quality of malaria in pregnancy and readability tests (Flesch Reading Ease and Flesh-Kincaid Grade level) were used to evaluate the websites. RESULTS: Most of the websites scored below 50% with the HON Code tool, with most lacking information on the symptoms. One website scored over 70 with the reading ease with two (2) achieving a score of 7 for the reading level test. The readability of the websites was too advanced for an ordinary consumer. CONCLUSION: The results of this study indicated that the information quality of malaria in pregnancy websites varied from fair to medium. It was also found that the readability of the websites was too advanced for an ordinary consumer. These findings suggest that most websites are not comprehensive in addressing all the relevant aspects of malaria in pregnancy.

Can comprehensive specialised end-of-life care be provided at home? Lessons from a study of an innovative consultant-led community service in the UK.

The Midhurst Macmillan Specialist Palliative Care Service (MMSPCS) is a UK, medical consultant-led, multidisciplinary team aiming to provide round-the-clock advice and care, including specialist interventions, in the home, community hospitals and care homes. Of 389 referrals in 2010/11, about 85% were for cancer, from a population of about 155 000. Using a mixed method approach, the evaluation comprised: a retrospective analysis of secondary-care use in the last year of life; financial evaluation of the MMSPCS using an Activity Based Costing approach; qualitative interviews with patients, carers, health and social care staff and MMSPCS staff and volunteers; a postal survey of General Practices; and a postal survey of bereaved caregivers using the MMSPCS. The mean cost is about 3000 GBP (3461 EUR) per patient with mean cost of interventions for cancer patients in the last year of life 1900 GBP (2192 EUR). Post-referral, overall costs to the system are similar for MMSPCS and hospice-led models; however, earlier referral avoided around 20% of total costs in the last year of life. Patients and carers reported positive experiences of support, linked to the flexible way the service worked. Seventy-one per cent of patients died at home. This model may have application elsewhere.

A study on the use of Gumbel approximation with the Bernoulli spatial scan statistic.

The Bernoulli version of the spatial scan statistic is a well established method of detecting localised spatial clusters in binary labelled point data, a typical application being the epidemiological case-control study. A recent study suggests the inferential accuracy of several versions of the spatial scan statistic (principally the Poisson version) can be improved, at little computational cost, by using the Gumbel distribution, a method now available in SaTScan(TM) (www.satscan.org). We study in detail the effect of this technique when applied to the Bernoulli version and demonstrate that it is highly effective, albeit with some increase in false alarm rates at certain significance thresholds. We explain how this increase is due to the discrete nature of the Bernoulli spatial scan statistic and demonstrate that it can affect even small p-values. Despite this, we argue that the Gumbel method is actually preferable for very small p-values. Furthermore, we extend previous research by running benchmark trials on 12 000 synthetic datasets, thus demonstrating that the overall detection capability of the Bernoulli version (i.e. ratio of power to false alarm rate) is not noticeably affected by the use of the Gumbel method. We also provide an example application of the Gumbel method using data on hospital admissions for chronic obstructive pulmonary disease.

Clinical and neuropsychological aspects of non-fatal self-harm in schizophrenia.

PURPOSE: To investigate demographic, clinical and neuropsychological aspects of self-harm in schizophrenia and identify which are independently predictive of and therefore the most relevant to clinical intervention. SUBJECTS AND METHODS: Eighty-seven patients with schizophrenia were interviewed regarding substance misuse, depression, hopelessness, negative/positive symptoms and illness insight. Neuropsychological assessment included premorbid IQ, continuous performance test, cognitive-motor and trait impulsivity. A prospective three-month review of medical records was also undertaken. RESULTS: Fifty-nine patients (68%) reported past self-harm (including attempted suicide). Those with past self-harm, compared to those without, were significantly more likely to report depression, hopelessness, impulsivity, a family history of self-harm, polysubstance abuse and had higher premorbid IQ. Logistic regression revealed that depression, higher premorbid IQ and polysubstance abuse were independently linked to self-harm. Five participants attempted self-harm during the 3-month prospective follow-up period. These all had a history of past self-harm and were significantly more likely to have been depressed at the initial interview than those who did not go on to self-harm. DISCUSSION AND CONCLUSIONS: Independent predictors of self-harm in schizophrenia are premorbid IQ and polysubstance abuse. In addition, depression was both independently associated with past self-harm and predictive of self-harm in the follow-up period.

Analytic Hierarchy Process (AHP) for examining healthcare professionals' assessments of risk factors. The relative importance of risk factors for falls in community-dwelling older people.

BACKGROUND: A gap exists between evidence-based medicine and clinical-practice. Every day, healthcare professionals (HCPs) combine empirical evidence and subjective experience in order to maximize the effectiveness of interventions. Consequently, it is important to understand how HCPs interpret the research evidence and apply it in everyday practice. We focused on the prevention of falls, a common cause of injury-related morbidity and mortality in later life, for which there is a wide range of known risk factors. OBJECTIVES: To use the Analytic Hierarchy Process (AHP) to investigate the opinions of HCPs in prioritizing risk factors for preventing falls. METHODS: We used the AHP to develop a hierarchy of risk factors for falls based on the knowledge and experience of experts. We submitted electronic questionnaires via the web, in order to reach a wider number of respondents. With a web service, we pooled the results and weighted the coherence and the experience of respondents. RESULTS: Overall, 232 respondents participated in the study: 32 in the technical pilot study, nine in the scientific pilot study and 191 respondents in the main study. We identified a hierarchy of 35 risk factors, organized in two categories and six sub-categories. CONCLUSIONS: The hierarchy of risk factors provides further insights into clinicians' perceptions of risk factors for falls. This hierarchy helps understand the relative importance that clinicians place on risk factors for falls in older people and why evidence-based guidelines are not always followed. This information may be helpful in improving intervention programs and in understanding how clinicians prioritize multiple risk factors in individual patients. The AHP method allows the opinions of HCPs to be investigated, giving appropriate weight to their coherence, background and experience.

Assessing quality of care from hospital case notes: comparison of reliability of two methods.

OBJECTIVES: To determine which of the two methods of case note review provide the most useful and reliable information for reviewing quality of care. DESIGN: Retrospective, multiple reviews of 692 case notes were undertaken using both holistic (implicit) and criterion-based (explicit) review methods. Quality measures were evidence-based review criteria and a quality of care rating scale. SETTING: Nine randomly selected acute hospitals in England. PARTICIPANTS: Sixteen doctors, 11 specialist nurses and three clinically trained audit staff, and eight non-clinical audit staff. ANALYSIS METHODS: Intrarater consistency, inter-rater reliability between pairs of staff using intraclass correlation coefficients (ICCs), completeness of criterion data capture and between-staff group comparison. RESULTS: A total of 1473 holistic reviews and 1389 criterion-based reviews were undertaken. When the three same staff types reviewed the same record, holistic scale score inter-rater reliability was moderate within each group (ICC 0.46 to 0.52). Inter-rater reliability for criterion-based scores was moderate to good (ICC 0.61 to 0.88). Comparison of holistic review score and criterion-based score of case notes reviewed by doctors and by non-clinical audit staff showed a reasonable level of agreement between the two methods. CONCLUSIONS: Using a holistic approach to review case notes, same staff groups can achieve reasonable repeatability within their professional groups. When the same clinical record was reviewed twice by the doctors, and by the non-clinical audit staff, using both holistic and criterion-based methods, there are close similarities between the quality of care scores generated by the two methods. When using retrospective review of case notes to examine quality of care, a clear view is required of the purpose and the expected outputs of the project.

Comparison of case note review methods for evaluating quality and safety in health care.

OBJECTIVES: To determine which of two methods of case note review--holistic (implicit) and criterion-based (explicit)--provides the most useful and reliable information for quality and safety of care, and the level of agreement within and between groups of health-care professionals when they use the two methods to review the same record. To explore the process-outcome relationship between holistic and criterion-based quality-of-care measures and hospital-level outcome indicators. DATA SOURCES: Case notes of patients at randomly selected hospitals in England. REVIEW METHODS: In the first part of the study, retrospective multiple reviews of 684 case notes were undertaken at nine acute hospitals using both holistic and criterion-based review methods. Quality-of-care measures included evidence-based review criteria and a quality-of-care rating scale. Textual commentary on the quality of care was provided as a component of holistic review. Review teams comprised combinations of: doctors (n = 16), specialist nurses (n = 10) and clinically trained audit staff (n = 3) and non-clinical audit staff (n = 9). In the second part of the study, process (quality and safety) of care data were collected from the case notes of 1565 people with either chronic obstructive pulmonary disease (COPD) or heart failure in 20 hospitals. Doctors collected criterion-based data from case notes and used implicit review methods to derive textual comments on the quality of care provided and score the care overall. Data were analysed for intrarater consistency, inter-rater reliability between pairs of staff using intraclass correlation coefficients (ICCs) and completeness of criterion data capture, and comparisons were made within and between staff groups and between review methods. To explore the process-outcome relationship, a range of publicly available health-care indicator data were used as proxy outcomes in a multilevel analysis. RESULTS: Overall, 1473 holistic and 1389 criterion-based reviews were undertaken in the first part of the study. When same staff-type reviewer pairs/groups reviewed the same record, holistic scale score inter-rater reliability was moderate within each of the three staff groups [intraclass correlation coefficient (ICC) 0.46-0.52], and inter-rater reliability for criterion-based scores was moderate to good (ICC 0.61-0.88). When different staff-type pairs/groups reviewed the same record, agreement between the reviewer pairs/groups was weak to moderate for overall care (ICC 0.24-0.43). Comparison of holistic review score and criterion-based score of case notes reviewed by doctors and by non-clinical audit staff showed a reasonable level of agreement (p-values for difference 0.406 and 0.223, respectively), although results from all three staff types showed no overall level of agreement (p-value for difference 0.057). Detailed qualitative analysis of the textual data indicated that the three staff types tended to provide different forms of commentary on quality of care, although there was some overlap between some groups. In the process-outcome study there generally were high criterion-based scores for all hospitals, whereas there was more interhospital variation between the holistic review overall scale scores. Textual commentary on the quality of care verified the holistic scale scores. Differences among hospitals with regard to the relationship between mortality and quality of care were not statistically significant. CONCLUSIONS: Using the holistic approach, the three groups of staff appeared to interpret the recorded care differently when they each reviewed the same record. When the same clinical record was reviewed by doctors and non-clinical audit staff, there was no significant difference between the assessments of quality of care generated by the two groups. All three staff groups performed reasonably well when using criterion-based review, although the quality and type of information provided by doctors was of greater value. Therefore, when measuring quality of care from case notes, consideration needs to be given to the method of review, the type of staff undertaking the review, and the methods of analysis available to the review team. Review can be enhanced using a combination of both criterion-based and structured holistic methods with textual commentary, and variation in quality of care can best be identified from a combination of holistic scale scores and textual data review.

Accessibility versus confidentiality of information in the emergency department.

INTRODUCTION: In the emergency department (ED), clinicians can benefit greatly from having access to information at the point of care. It has been suggested that using computerised information systems could improve the accessibility of information. However, making information accessible, while maintaining confidentiality, is one of the main challenges of implementing information systems. This article presents the ED staff perspectives about the accessibility and confidentiality of information in the ED. METHOD: The authors undertook a qualitative study in March-April 2007. Data were collected using in-depth semi-structured interviews with the ED staff of an ED located in Northern England. In total, 34 interviews were conducted and transcribed verbatim. Data were analysed using framework analysis. RESULTS: The results showed that the ED staff had role-based access to the current information systems, and these systems met only a small part of their information needs. As a result, different sources were used to get access to the needed information. Although the ED staff believed that improving the accessibility of information could be helpful in emergency care services, there were concerns about the confidentiality of information. The confidentiality of information could be threatened--for example, by sharing passwords, misusing patient information or by unauthorised staff having access to patient information. CONCLUSION: To design a system, the accessibility and confidentiality of information should be addressed in parallel. A balance between these two is needed, as the failure of each of these may negatively influence the use of the system.

The development of a clinically useful tool for predicting the development of psychological disorder following injury.

OBJECTIVES: To identify factors significantly associated with post-traumatic stress disorder (PTSD), anxiety, and depression at 3 months post-injury; to develop a generic model to predict the occurrence of PTSD, anxiety, and depression at 3 months post-injury; and to validate this model in a test data set of patients. DESIGN: Prospective cohort study. METHODS: Participants were 823 patients attending an emergency department (ED) following accidental injury. Baseline questionnaires were completed, with 1 and 3 months postal follow-ups. Predictor variables demonstrating significant associations with two of the three outcome measures (3-month HAD anxiety and depression scores and PTSD symptoms) were included in multivariate regression models for each outcome. Non-significant predictor variables were removed until all remaining independent variables made the most significant contribution to each of the three models. Models were validated using a test dataset. RESULTS: Previous history of mental health problems, neuroticism score and having PTSD symptoms at 1 month predicted adverse outcomes at 3 months. When used on the test datasets, the areas under the receiver operating curve (ROC) curve for the models predicting outcomes at 3 months were: PTSD=0.91 (sensitivity=88.5%); anxiety=0.87 (sensitivity=93.7%); and depression=0.87 (sensitivity=96.7%). CONCLUSIONS: The final model performed moderately well across the three outcomes and may be useful clinically as a generic rule-out tool to identify those who will not require follow up, watchful waiting or intervention.

Health information needs of visually impaired people: a systematic review of the literature.

Access to, and provision of, information is key to reducing health inequalities in health and social care. However, information is not always accessible and does not always meet the needs of specific groups. One such group is people who are visually impaired. The aim of the present study was to identify the health information needs of visually impaired people, and highlight major gaps in the literature. A systematic review of the literature was undertaken following, where possible, the NHS Centre for Reviews and Dissemination framework. Modifications included the sources searched, the critical appraisal checklist used (Critical Skills Training in Appraisal for Librarians) and the method of data synthesis. Out of the 1114 references identified, only 16 met the inclusion criteria. Quality of reporting of the literature was poor, and this must be taken into consideration when interpreting the findings of this review. The majority of studies were concerned with information for healthy living (e.g. health promotion). The focus of the remaining studies was on information about visual impairment or coping with visual impairment, and about accessing health services (e.g. medication labels and appointment letters). The majority of studies conducted to date have concentrated on the format of information. There are surprisingly few empirical studies which have examined the health information needs of this group. A number of gaps in the literature have been identified. These relate to the types of health information, non-format aspects of information (e.g. content and timing), sources of health and social care information, treating visually impaired people as a heterogeneous group, and recognising the value of actively involving visually impaired people in the research process. Although this review has identified a number of implications for practice, the paucity of evidence places a heavier onus on future research. Visually impaired people are likely to have unique health and social care information needs which are worthy of exploration in their own right.

The role of the information specialist in the systematic review process: a health information case study.

There is an increasing body of literature on the information specialist's role in supporting evidence-based health care. In particular, the information component in systematic reviews has received considerable attention in recent years. Information professionals have evolved from simply acting as 'evidence locators' and 'resource providers' to being quality literature filterers, critical appraisers, educators, disseminators, and even change managers. This paper describes ten possible roles for information professionals in the systematic review process, using a case study of a review of the health information needs of visually impaired people carried out by the Centre for Health Information Management Research (CHIMR) at the University of Sheffield. This health information review was undertaken entirely by a team of information professionals. The ten roles identified are: project leader, project manager, literature searcher, reference manager, document supplier, critical appraiser, data extractor, data synthesiser, report writer and disseminator. This review has also identified an eleventh possible role for information professionals; that of primary researcher. Finally, the implications for evidence-based health care and evidence-based health informatics are discussed.

The maternity information concerns of Somali women in the United Kingdom.

AIMS: The aims of the study were to explore the maternity information concerns of a group of Somali women in a Northern English city and to investigate the relationships of these women with maternity health professionals. BACKGROUND: The Somali community is one of the most established ethnic minorities in the United Kingdom (UK). The health needs of this group and in particular, the information needs of Somali women with respect to pregnancy, childbirth and post-natal care are poorly understood. To facilitate information provision to birthing mothers and to support maternal decision-making among minority ethnic women, research is required to understand and identify their information needs. METHODS: A user-centred study utilizing a focus group and semi-structured interviews with English-speaking and non-English speaking Somali women was conducted in a large English city. Discussions were audiotaped, translated, transcribed and then analysed using a variation of the constant comparative METHOD: Themes and categories were identified across transcripts during data collection and analysis and appropriate quotations are used to illustrate all themes. FINDINGS: Major findings that emerged from the analysis related to contact with health professionals, language support and information and satisfaction with health professionals. The findings indicate key maternity information concerns of Somali women with regard to maternity issues and have a number of implications for midwifery and nursing practice. CONCLUSIONS: Poor communication between the non-English speaking Somali women and health workers was perceived as an underlying problem in seeking information. Fears about misinterpretation and confidentiality, limit the usefulness of interpreters. The Somali women perceived that they were denied information due to punitive attitudes and prejudiced views among health professionals.

Information-seeking behaviors of women with breast cancer.

PURPOSE/OBJECTIVES: To explore the information-seeking behaviors of women with breast cancer. DESIGN: Sequential, between-methods triangulation. SETTING: Community-based. SAMPLE: 156 women with breast cancer took part in a mailed survey, and 30 women with breast cancer participated in three focus group discussions (n = 11, 12, and 7). METHODS: Women with breast cancer completed the Miller Behavioral Style Scale (MBSS). Other women with breast cancer participated in one of three age-stratified focus group discussions. MAIN RESEARCH VARIABLE: Information-seeking behaviors of women with breast cancer. FINDINGS: The information-seeking behaviors of women with breast cancer, as measured by the monitoring subscale of MBSS, were not significantly associated with their demographic (e.g., age, socioeconomic class) and illness-related characteristics (e.g., months since diagnosis, surgery, therapeutic regimens). The focus group discussions suggested that the information-seeking behaviors of women with breast cancer were highly individualistic. Although some women actively sought information, others avoided information. In addition, women sometimes fluctuated between seeking and avoiding information. Women sought information to cope with breast cancer, regain a sense of control, increase their feelings of confidence, and help facilitate the decision-making process. Women avoided information to escape from worry, fear, and feelings of negativity and depression. CONCLUSIONS: The information-seeking behaviors of women with breast cancer are highly individualistic and are not related to demographic or disease-related characteristics. IMPLICATIONS FOR NURSING PRACTICE: Breast-care nurses need to be sensitive to the information-seeking behaviors of women with breast cancer. Information seekers should be given maximum information, and information avoiders should be given minimum information. In addition, more research needs to be conducted into the information-seeking behaviors of women with the disease.

The use of between-methods triangulation in cancer nursing research: a case study examining information sources for partners of women with breast cancer.

This article describes between-methods triangulation-the combination of research strategies using different methods--and illustrates its use in cancer nursing research by outlining a case study, which identified the information sources for partners of women with breast cancer. By combining both qualitative and quantitative data, the study was found to possess good convergent validity. Between-methods triangulation also provided a more complete picture of the topic of inquiry than that supplied by either method alone. It is a useful strategy for identifying the information sources for partners of women with breast cancer and its use is encouraged in cancer nursing research.

Geriatric assessment in primary care: formulating best practice.

Comprehensive geriatric assessment (CGA) is a structured approach to measuring physical, mental and social functioning of older people to identify needs and to plan care. Meta-analysis of trials of CGA suggest that it is cost-effective, but there is no agreed approach to its implementation in primary care. Our aim was to develop a best-practice model for geriatric assessment in primary care. We took an iterative approach to development, combining expert and local stakeholder opinion, and using semi-structured interviews to assess patient and practitioner experience in nine general practices in Sheffield. Patients were aged 75 and over, living at home. The best-practice model was the use of a standardized instrument (EASY-Care) to unselected patients aged 75 years and over living at home or in residential care, administered by a practice nurse in the context of an over-75s health check. There was high patient and practitioner acceptability, and significant cost savings were noted. Key beneficial features were the assessment of mental health and sources of support; goal-setting; generation of a disability score; and high patient satisfaction from contact with nursing staff. We conclude that geriatric assessment in primary care is feasible, economical and beneficial to patients and practitioners. Nursing staff are central to successful implementation of geriatric assessment in primary care.

Exploring the information flow: partners of women with breast cancer, patients, and healthcare professionals.

PURPOSE/OBJECTIVES: To explore the information flow between partners of women with breast cancer and patients and between partners and healthcare professionals (HCPs). DESIGN: Descriptive. SETTING: Community-based. SAMPLE: 109 partners of women with breast cancer. METHODS: Subjects completed a 30-item, self-administered questionnaire that was designed to identify the informational flow between them and their information providers. Subjects also completed the Miller Behavioral Style Scale to determine the informational coping styles of individuals under threat. MAIN RESEARCH VARIABLE: Informational flow between partners and patients and partners and HCPs. FINDINGS: The majority of partners received information from patients and were satisfied with the amount of time they spent discussing breast cancer topics. Few partners thought that patients avoided giving them information. A significant association existed between the informational coping styles of partners and the communication flow between partners and patients. The majority of partners sought information from other sources. In addition, the majority of partners accompanied patients to their medical consultations and received information from HCPs. The communication flow among partners, patients, and HCPs largely depended on the amount of communication desired by the woman with breast cancer. CONCLUSIONS: This study provides new evidence on the information flow and communication patterns between partners and patients and between partners and HCPs. IMPLICATIONS FOR NURSING PRACTICE: Partners may have informational needs that are not met by patients. Therefore, nurses need to provide them with information to help satisfy their needs. In addition, nurses can help satisfy the informational needs of partners by encouraging good two-way communication and informational exchange between partners and patients.

The psychometric properties of the Miller Behavioural Style Scale with adult daughters of women with early breast cancer: a literature review and empirical study.

Several researchers have suggested that the information-seeking behaviours of patients need to be taken into consideration when assessing their information needs. This study reviews published evidence of the psychometric properties of the Miller Behavioural Style Scale, a tool commonly used to identify the information-seeking behaviours of individuals under threat, and examines its reliability and validity with adult daughters of women with early breast cancer. Ninety-seven adult daughters completed the MBSS and a 30-item, self-administered questionnaire, a tool designed to explore the information needs of adult daughters of women with breast cancer. The internal consistency of the monitoring and blunting sub-scales of the MBSS was alpha = 0.65 and 0.41 respectively. The blunting sub-scale fell substantially below acceptable limits and was discarded from subsequent analyses. The monitoring sub-scale possessed good test-retest reliability (n = 17) with a 5-week time interval (r= 0.71, P < 0.005), as measured using a Pearson's correlation coefficient. Furthermore, the majority (73.4%) of monitoring items possessed moderate or substantial test-retest reliability, as indicated by kappa coefficients. Finally, the monitoring sub-scale possessed good construct validity, both discriminant and convergent validity, as measured by the univariate associations between monitoring behaviour and selected items from the information questionnaire and a demographic questionnaire. In conclusion, adequate support exists for the psychometric properties of the monitoring sub-scale of the MBSS and its use with adult daughters of women with early breast cancer in future research. These findings have a number of implications for nursing research and these are discussed in this paper.

The information needs and source preferences of women with breast cancer and their family members: a review of the literature published between 1988 and 1998.

A comprehensive and critical literature review was conducted to examine the information needs and source preferences of women with breast cancer and their family members. Relevant papers published between 1988 and 1998 were reviewed and despite their having several methodological weaknesses, a number of conclusions can still be drawn. First, women with breast cancer have distinct needs for information throughout their breast cancer journeys, indicating that information needs change with time since diagnosis and with treatment-related events. Second, family members of women with breast cancer also have substantial needs for information. Third, women with breast cancer and their family members often prefer verbal forms of information from health care professionals (HCPs), particularly around the time of diagnosis. Women with breast cancer, however, are often dissatisfied with the information they receive from HCPs. Further, the family members of women with breast cancer often perceive their information needs to be ignored by HCPs. Finally, few studies have focused specifically on the information needs and source preferences of family members of women with breast cancer. These findings have a number of implications for nursing, both for clinical practice and nursing research, and these are discussed in the review.

New approach to risk determination: development of risk profile for new falls among community-dwelling older people by use of a Genetic Algorithm Neural Network (GANN).

BACKGROUND: Falls risk in older people is multifactorial and complex. There is uncertainty about the importance of specific risk factors. Genetic algorithm neural networks (GANNs) can examine all available data and select the best nonlinear combination of variables for predicting falls. The aim of this work was to develop a risk profile for operationally defined new falls in a random sample of older people by use of a GANN approach. METHODS: A random sample of 1042 community-dwelling people aged 65 and older, living in Nottingham, England, were interviewed at baseline (1985) and survivors reinterviewed at a 4-year follow-up (n = 690). The at-risk group (n = 435) was defined as those survivors who had not fallen in the year before the baseline interview. A GANN was used to examine all available attributes and, from these, to select the best nonlinear combination of variables that predicted those people who fell 4 years later. RESULTS: The GANN selected a combination of 16 from a potential 253 variables and correctly predicted 35/114 new fallers (sensitivity = 31%; positive predictive value = 57%) and 295/321 nonfallers (specificity = 92%; negative predictive value = 79%); total correct = 76%. The variables selected by the GANN related to personal health, opportunity, and personal circumstances. CONCLUSIONS: This study demonstrates the capacity of GANNs to examine all available data and then to identify the best 16 variables for predicting falls. The risk profile complements risk factors in the current literature identified by use of standard and conventional statistical methods. Additional data about environmental factors might enhance the sensitivity of the GANN approach and help identify those older people who are at risk of falling.