Predicting patient acuity from electronic patient records.

BACKGROUND: The ability to predict acuity (patients' care needs), would provide a powerful tool for health care managers to allocate resources. Such estimations and predictions for the care process can be produced from the vast amounts of healthcare data using information technology and computational intelligence techniques. Tactical decision-making and resource allocation may also be supported with different mathematical optimization models. METHODS: This study was conducted with a data set comprising electronic nursing narratives and the associated Oulu Patient Classification (OPCq) acuity. A mathematical model for the automated assignment of patient acuity scores was utilized and evaluated with the pre-processed data from 23,528 electronic patient records. The methods to predict patient's acuity were based on linguistic pre-processing, vector-space text modeling, and regularized least-squares regression. RESULTS: The experimental results show that it is possible to obtain accurate predictions about patient acuity scores for the coming day based on the assigned scores and nursing notes from the previous day. Making same-day predictions leads to even better results, as access to the nursing notes for the same day boosts the predictive performance. Furthermore, textual nursing notes allow for more accurate predictions than previous acuity scores. The best results are achieved by combining both of these information sources. The developed model achieves a concordance index of 0.821 when predicting the patient acuity scores for the following day, given the scores and text recorded on the previous day. CONCLUSIONS: By applying language technology to electronic patient documents it is possible to accurately predict the value of the acuity scores of the coming day based on the previous daýs assigned scores and nursing notes.

The impact of an empowering Internet-based Breast Cancer Patient Pathway program on breast cancer patients' clinical outcomes: a randomised controlled trial.

AIMS AND OBJECTIVES: To evaluate the effect of the Breast Cancer Patient Pathway program on breast cancer patient's empowerment process. BACKGROUND: The results of earlier studies indicate that the use of tailored Internet-based patient education programs increased patient's knowledge level; however, other outcome measures differed. DESIGN: This randomised control trial studied the effect of the Internet-based patient educational program on breast cancer patients' empowerment. In this study, we measured the quality of life, anxiety and managing with treatment-related side effects as the outcomes of breast cancer patients' empowering process. METHODS: Breast cancer patients who were Internet users in one Finnish university hospital during 2008-2010 were randomised to the control group (n=43) and the intervention group (n=47). Baseline data were collected first in the hospital and the following data seven times during the treatment process, the last time one year after breast cancer diagnosis. RESULTS: There were no statistically significant differences in the quality of life, anxiety or side effects of treatment between the groups. The amount of treatment-related side effects was connected to both physical and psychological well-being. CONCLUSIONS: In this study, the Breast Cancer Patient Pathway program did not decrease anxiety level or treatment-related side effects among breast cancer patients or improve subscales of quality of life when compared with controls. RELEVANCE TO CLINICAL PRACTICE: There is a need to relieve the side effects caused by patients' care with the help of patient education. Internet-based patient education programs need more focus when developing new patient education methods.

National survey focusing on the crucial information needs of intensive care charge nurses and intensivists: same goal, different demands.

BACKGROUND: Although information technology adequately supports clinical care in many intensive care units (ICUs), it provides much poorer support for the managerial information needed to coordinate multi-professional care. To gain a general view of the most crucial multi-professional information needs of ICU shift leaders a national survey was conducted, focusing on the information needs of charge nurses and intensivists. METHODS: Based on our previous observation study an online survey was developed, containing 122 information need statements related to the decision-making of ICU shift leaders. Information need statements were divided into six dimensions: patient admission, organisation and management of work, allocation of staff and material resources, special treatments, and patient discharge. This survey involved all ICU shift leaders (n = 738) who worked in any of the 17 highest level ICUs for adults in university hospitals in Finland during the autumn of 2009. Both charge nurses' and intensivists' crucial information needs for care coordination were evaluated. RESULTS: Two hundred and fifty-seven (50%) charge nurses and 96 (43%) intensivists responded to the survey. The consistency of the survey was found to be good (Cronbach's α scores between .87-.97, with a total explanatory power of 64.53%). Altogether, 57 crucial information needs for care coordination were found; 22 of which were shared between shift leaders. The most crucial of these information needs were related to organisation and management, patient admission, and allocation of staff resources. The associations between working experience, or shift leader acting frequencies, and crucial information needs were not statistically significant. However, a statistically significant difference was found between the number of ICU beds and the ICU experience of charge nurses with information needs, under the dimension of organisation and management of work. The information needs of charge nurses and intensivists differed. Charge nurses' information needs related to care coordination, were more varied, and concerned issues at a unit level, whereas intensivists focused on direct patient care. CONCLUSIONS: The reliability and validity of our survey was found to be good. Our study findings show that care coordination at an ICU is a collaborative process among ICU shift leaders with multiprofessional information needs related to organisation and management, patient admission, and allocation of staff resources. Study findings can be used to identify the most crucial information needs of ICU shift leaders when new information technology is developed to support managerial decision-making during care coordination.

Information utilization in tactical decision making of middle management health managers.

Healthcare is an information-intensive field, as information is needed to make strategic, tactical, and operational decisions. The purpose of this study was to identify the tactical decisions that middle management healthcare managers make, the information that is available, and the necessary information that is missing using the cardiac care process as an example. Data were collected through focused interviews of nurses and physicians who work in middle management in a secondary healthcare field. The interviews were coded and analyzed using the thematic content analysis method. We identified two main categories of tactical decisions: those concerning the process of care and those concerning the resources for the care. We termed the categories "process decisions" and "resource decisions." The availability of information varied. Much of the necessary information was created and processed manually. Our results show that the collection, mining, and systematic use of information are difficult because of the existence of many types of information systems and their varying abilities to produce and report information. Finally, much of the important information is missing. In conclusion, the information management process in healthcare settings needs to be improved, and a new generation of information system is needed to support tactical decision making in middle management.

The impact of an empowering Internet-based Breast Cancer Patient Pathway programme on breast cancer patients' knowledge: a randomised control trial.

OBJECTIVE: The aim of this study was to analyse the effect of Breast Cancer Patient Pathway program. METHODS: In one Finnish university hospital during 2008-10 newly diagnosed breast cancer patients were randomised to the intervention (n = 50) and the control groups (n = 48). The breast cancer patient's knowledge expectations and perception of received knowledge, knowledge, the source of information and satisfaction in received patient education were measured. Baseline and one year follow up data collection was conducted. RESULTS: No differences were found in knowledge expectations between the groups at baseline. Patients in the control group evaluated their perception of received knowledge to be higher and they were more satisfied with the patient education they received from the hospital staff. However, the Intervention group's knowledge level was higher. The most important source of information was the healthcare professionals in both groups. CONCLUSION: The results of study indicate that when patient education increases, patients' knowledge expectations increase as well, while their perceptions of received knowledge decrease. Future research is needed to examine the relationship between patients' knowledge expectations and perception of received knowledge as patients' knowledge level increases. PRACTICE IMPLICATIONS: Patient education has to be individually adjusted, taking patients' expectations into account.

Internet based patient pathway as an educational tool for breast cancer patients.

OBJECTIVE: The aim of this paper was to describe the process of developing an Internet-based empowering patient education program for breast cancer patients and to evaluate the quality of the program from the perspective of patients. In this program, the patient pathway was used as an educational tool. METHODS: The Breast Cancer Patient Pathway (BCPP) was developed and tested at one Finnish university hospital in 2005-2007. Thirty-eight newly diagnosed breast cancer patients used the program during their treatment process until the end of all treatments (average 9 months) in 2008-2010. After the treatments the patients evaluated the content, language and structure, instructiveness, external appearance and technical characteristics of the web site as subcategories with the Evaluating Internet Pages of Patient Education instrument, which is a 37-item Likert scale (1-4) questionnaire. Comparison between the subcategories was done with Friedman's test. Dependencies between demographic variables and evaluation values were tested with Pearson correlation coefficients. RESULTS: The mean value of all evaluation criteria was 3.40. However, patients' evaluations between different subcategories varied, being the highest in language and structure (mean 3.48) and lowest in content (mean 3.13). Language and structure, external appearance and technical characteristics were significantly better than content, and language and structure better than instructiveness. Significant correlations were not found between demographic variables and evaluation values. CONCLUSIONS: Patients evaluated the quality of the BCPP to be best in language and structure and weakest in content. In terms of future development of the BCPP, the most improvement is needed in content and instructiveness. There is also a need for further development and study of Internet-based patient education.

Managing daily intensive care activities: an observational study concerning ad hoc decision making of charge nurses and intensivists.

INTRODUCTION: Management of daily activities in ICUs is challenging. ICU shift leaders, charge nurses and intensivists have to make several immediate ad hoc decisions to enable the fluent flow of ICU activities. Even though the management of ICU activities is quite well delineated by international consensus guidelines, we know only a little about the content of the real clinical decision making of ICU shift leaders. METHODS: We conducted an observational study with the think-aloud technique to describe the ad hoc decision making of ICU shift leaders. The study was performed in two university-affiliated hospital ICUs. Twelve charge nurses and eight intensivists were recruited. Observations were recorded and transcribed for qualitative content analysis using the protocol analysis method. The software program NVivo 7 was used to manage the data. The interrater agreement was assessed with percentages and by Cohen's κ. RESULTS: We identified 463 ad hoc decisions made by the charge nurses and 444 made by the intensivists. During our data collection time, this breaks down to over 230 immediately made decisions per day (24 hours). We divided the ad hoc decision making of ICU shift leaders into two types: process-focused and situation-focused. Process-focused decision making included more permanent information, such as human resources, know-how and material resources, whereas situation-focused decision making included decisions about single events, such as patient admission. We named eight different categories for ICU ad hoc decision making: (1) adverse events, (2) diagnostics, (3) human resources and know-how, (4) material resources, (5) patient admission, (6) patient discharge, (7) patient information and vital signs and (8) special treatments. CONCLUSIONS: ICU shift leaders make a great number of complex ad hoc decisions throughout the day. Often this decision making involves both intensivists and charge nurses. It forms a bundle that requires versatile, immediate information for a successful outcome. In the future, we need to investigate which information is crucial for ad hoc decision making. These challenges should also be emphasised when information technology programs for ICU care management are developed.

PERFECT preterm infant study.

INTRODUCTION: This article summarizes the main findings of the preterm infant sub-study of the Performance, Effectiveness and Costs of Treatment episodes (PERFECT) study. We studied effects of birth hospital level and time of birth on mortality and morbidity and cost-effectiveness of care of very low gestational age (VLGA)/very low birth weight (VLBW) infants. MATERIAL AND METHODS: The study included all infants born below 32 weeks or 1501 g in Finland in 2000-2007. Different cohorts were used depending on the time point. RESULTS: The one-year mortality of live-born VLBW/VLGA infants was higher if born in level II versus level III hospitals, or if born during out-of-office hours in level II versus office hours in level III hospitals. Two out of three VLGA/VLBW subjects did not have any of the prematurity-related morbidities studied. The average cost of quality-adjusted life years was €19,245 by four years of age; the cost was higher in VLGA/VLBW infants with long-term morbidities. DISCUSSION: Birth in a level III hospital improved survival of VLGA/VLBW infants. Results suggest inadequate overnight competence in small hospitals. Despite high initial costs, care of VLGA/VLBW infants was already cost-effective by four years of age. Cost-effectiveness can be improved by reducing long-term morbidities.

Critical incidents and important information in the care processes of patients with cardiac symptoms.

AIM: To describe important information in the care processes of patients with cardiac symptoms. BACKGROUND: Process-based work-flow models are increasingly being used in healthcare. At the same time, developments in information systems offer the possibility of supporting improvements in process and information management in healthcare. To better utilize these possibilities we need to understand more about important information content and flow during treatment processes. METHOD: A qualitative approach involving the critical incident technique was used. Critical incidents were collected using a semi-structured questionnaire (50 respondents) and interviews (n=10). RESULTS: Three incident categories of important information were identified: (1) process-related incidents, (2) managerial incidents and (3) clinical incidents. Process-related incidents focused on agreed-care practices and the importance of the care environment. Managerial incidents focused on human and material resources. Clinical incidents focused on medical and nursing care and the importance of patient education. CONCLUSIONS: Information content, information flow and the timing of such information should be modelled further in order to improve the management of care processes. IMPLICATIONS FOR NURSING MANAGEMENT: Increasing knowledge about essential points of information as part of nursing management is important.

Development and behaviour of 5-year-old very low birthweight infants.

The place and time of birth influence the mortality of premature infants. We studied the effect of prematurity, time of birth, birth hospital level and district on the development and behaviour in a national cohort of 5-year-old Finnish very low birthweight infants (VLBWI). All surviving VLBWI (gestational age <32 weeks or birthweight

The effects of Internet or interactive computer-based patient education in the field of breast cancer: a systematic literature review.

OBJECTIVE: The aim of this systematic review was to analyze what kind of Internet or interactive computer-based patient education programs have been developed and to analyze the effectiveness of these programs in the field of breast cancer patient education. Patient education for breast cancer patients is an important intervention to empower the patient. However, we know very little about the effects and potential of Internet-based patient education in the empowerment of breast cancer patients. METHODS: Complete databases were searched covering the period from the beginning of each database to November 2008. Studies were included if they concerned patient education for breast cancer patients with Internet or interactive computer programs and were based on randomized controlled, on clinical trials or quasi-experimental studies. RESULTS: We identified 14 articles involving 2374 participants. The design was randomized controlled trial in nine papers, in two papers clinical trial and in three quasi-experimental. Seven of the studies were randomized to experimental and control groups, in two papers participants were grouped by ethnic and racial differences and by mode of Internet use and three studies measured the same group pre- and post-tests after using a computer program. The interventions used were described as interactive computer or multimedia programs and use of the Internet. The methodological solutions of the studies varied. The effects of the studies were diverse except for knowledge-related issues. Internet or interactive computer-based patient education programs in the care of breast cancer patients may have positive effect increasing breast cancer knowledge. CONCLUSION: The results suggest a positive relationship between the Internet or computer-based patient education program use and the knowledge level of patients with breast cancer but a diverse relationship between patient's participation and other outcome measures. PRACTICE IMPLICATIONS: There is need to develop and research more Internet-based patient education.

Key elements of successful care process of patients with heart symptoms in an emergency care - could an ERP system help?

The aim of the study was to identify key elements of successful care process of patients with heart symptoms from the nursing management viewpoint in an emergency care. Through these descriptions, we aimed at identifying possibilities for using enterprise resource planning (ERP) systems to support decision making in emergency care. Hospitals are increasingly moving to process-based workings and at the same time new information system in healthcare are developed and therefore it is essential to understand the strengths and weaknesses of current processes better. A qualitative descriptive design using critical incident technique was employed. Critical Incidents were collected with an open-ended questionnaire. The sample (n=50), 13 head nurses and 37 registered nurses, was purposeful selected from three acute hospitals in southern Finland. The process of patients with heart symptoms in emergency care was described. We identified three competence categories where special focus should be placed to achieve successful process of patients with heart symptoms: process-oriented competencies, personal/management competencies and logistics oriented competencies. Improvement of decision making requires that the care processes are defined and modeled. The research showed that there are several happenings in emergency care where an ERP system could help and support decision making. These happenings can be categorized in two groups: 1) administrative related happenings and 2) patient processes related happenings.

Health-related quality of life in 5-year-old very low birth weight infants.

OBJECTIVE: To investigate the effect of preterm birth, the time of birth, and birth hospital level and district on health-related quality of life (HRQoL) and quality-adjusted life years (QALYs). STUDY DESIGN: This national study included all very low birth weight infants (VLBWIs; birth weight

Differences in the length of initial hospital stay in very preterm infants.

AIM: To investigate the effect of maternal, infant and birth hospital district related factors on the length of initial hospital stay in very preterm infants. In addition, rehospitalization rate within the first year from the initial discharge was studied. METHODS: A register study covering all very preterm infants (gestational age < 32 weeks or birthweight < 1501 g) born alive in Finland between years 2000 and 2003 (N = 2148). Factors affecting length of stay (LOS) were studied using generalized linear model (GLM). RESULTS: The proportion of very preterm infants born in a level III unit varied in the hospital districts from 53% to 94%. Median LOS was 53 days (interquartile range: 38-76). There were large regional differences in the LOS, the difference being up to 10.5 days among the hospital districts (p < 0.0001). Rehospitalization rate was 47.2% within the first year from the initial discharge, and the absence of rehospitalization was associated with a 4.1 days shorter initial LOS (p < 0.0001). CONCLUSION: Our study showed large regional variation in LOS of very preterm infants despite similar case mix. We speculate that the variation depends on differences in treatment practices and discharge criteria.

Production flow analysis: a tool for designing a lean hospital.

Production flow analysis (PFA) was used in the planning process for a new acute care hospital. The PFA demonstrated that functional organisation--for example, with centralised medical imaging-- generates a lot of back and forth patient transfers between functional units. This to-and-fro patient flow increases lead times of care processes and also exposes the patients to unnecessary complications. PFA produced an ideal patient flow model and layout model for the acute care hospital. Thus, PFA revealed information for use in proximity ranking of different units of the hospital; the planning team then decided which units should be placed next to each other. Medical imaging should be essentially ubiquitous, to achieve simple, high-velocity patient flow. Thus, a modern decentralized layout model for medical imaging was planned. Furthermore, PFA enables optimizing transfer routes for patients and also, e.g., lift capacity in the hospital.

The effect of birth in secondary- or tertiary-level hospitals in Finland on mortality in very preterm infants: a birth-register study.

OBJECTIVE: Our goal was to test the hypothesis that the level of the delivery hospital affects 1-year mortality of very preterm infants in Finland. PATIENTS AND METHODS: This retrospective national medical birth-register study included 2291 very preterm infants (gestational age of < 32 weeks at birth or birth weight of < or = 1500 g) born in 14 level II (central) and 5 level III (university) hospitals in 2000-2003. The main outcome measures were adjusted total mortality (including stillbirths) and mortality of live-born infants until the age of 1 year. RESULTS: Both the total 1-year mortality and the 1-year mortality of live-born infants were higher in level II hospitals compared with level III hospitals. Total mortality was higher in very preterm infants who were not born during office hours. In theory, delivery of all very preterm infants in level III instead of level II hospitals translates into an annual prevention of 69 of the 170 total deaths and prevention of 18 of the 45 deaths of live-born infants. CONCLUSIONS: Resources in neonatal intensive care should be increased, especially during non-office hours, to have an equally distributed service through the 24-hour day. More efficient regionalization of very preterm deliveries may improve 1-year survival of very preterm infants in Finland.

Interactive skills of infants with their high-risk mothers.

In this pilot study, the interactive skills of infants with their high-risk, substance-dependent mothers were explored in residential treatment from pregnancy until the infant was 6 months of age. Fourteen mother-infant pairs were videotaped in feeding and free play situations at 6 months after birth. A comparison, low-risk group consisted of 12 ordinary Finnish mother-infant pairs with minimal clinical risks. The findings show significantly higher levels of dyadic interactive deficiencies among the high-risk mother-infant pairs compared to the low-risk pairs, displayed especially in the feeding situation as lack of mutuality and flat, empty, constricted affective tone of interaction. Also, more interactive deficiencies were found among the high-risk infants compared to the low-risk infants, but the differences were not significant. In this study, this finding might reflect the reduced amount of somatic complications and the benefits of treatment, the impacts of which were not explored. The differences between the high- and low-risk infants were displayed as more withdrawal, depressed mood and avoiding behavior and as less alertness and attentional abilities, robustness and focus on parent's emotional state among the high-risk group.

Low plasma cholecystokinin levels in colicky infants.

OBJECTIVES: Cholecystokinin (CCK) plays an important role in postprandial gallbladder contraction and may also have pacifying behavioral effects, such as inducing satiety and calming in infants. The authors hypothesized that colicky infants have impaired CCK secretion, which contributes to their gallbladder hypocontractility (reported earlier) and excessive crying. METHODS: Cholecystokinin levels of 40 colicky and 37 control infants were evaluated at a mean of age 5 weeks. Plasma CCK levels were drawn before, immediately after, and 1 hour after a regular milk feeding and analyzed using radioimmunoassay (RIA). The contraction of the gallbladder was calculated using ultrasound measurements before and 1 hour after the feeding. The two-tail t test for independent samples was used to test continuous data. RESULTS: The preprandial and 1-hour postprandial plasma levels of CCK were lower in the colicky infants than in the control subjects (P < 0.05). The immediate postprandial CCK levels were also lower in the colicky infants, although this difference did not reach a statistical significance. The proportion of gallbladder contractions did not differ between the study groups. CONCLUSIONS: The authors conclude that low CCK levels in colicky infants may predispose them to excessive crying in the absence of the calming effect of CCK.