Exposure to occupational risk factors is associated with the severity and progression of chronic obstructive pulmonary disease

Chronic obstructive pulmonary disease (COPD) results from a complex interaction between genes and the environment, and occupational exposures are an underappreciated risk factor. Until now, little research attention has been paid to the potential impact of occupational risk factor exposure on the COPD in China. The aim of this retrospective study was to analyze the role of occupational risk factor exposure on the severity and progression of COPD for exploring new prevention strategies for this disease. This study adopted a random cluster-sampling method. Five grade-A tertiary hospitals that met the inclusion criteria were selected as the survey sites, and patients with COPD hospitalized in these hospitals from January 1, 2019, to December 31, 2019, were selected as the research subjects. Data of the patients diagnosed with COPD met the Global Initiative for Chronic Obstructive Lung Disease (2019) criteria and were collected from the computerized medical record databases. Among 4082 investigated COPD patients, 1063 (26%) were found to have occupational risk factor exposure history. The top 3 industries with a large COPD case number and a history of occupational risk factor exposure ranked in the order of agriculture (including farming, forestry, animal husbandry, and fishery), manufacturing, and mining. Further multivariate logistic regression analysis indicated that when setting a low exposure level as a reference, medium and high exposure levels were correlated with the severity of COPD (odds ratio values were 2.837 and 6.201, respectively, P < .05). Linear regression analysis showed that cumulative exposure to occupational risk factors was negatively correlated with the forced expiratory volume in 1-second percentage of COPD patients, with a correlation coefficient of 0.68. Our results indicated that occupational risk factor exposure levels were related to the severity of COPD significantly. The incubation period of COPD in the exposure group was significantly shorter than that in the non-exposure group. To prevent worked-related COPD, special attention and control efforts should be taken to reduce the level of occupational risk factors such as organic dust, irritating chemicals, etc in the work environments, especially in the industries of agriculture, forestry, animal husbandry and fishery, manufacturing, and mining.

Conversion from paper to electronic acute care chemotherapy orders

PURPOSE

UNC Medical Center converted to an electronic health record (EHR) in 2014. This conversion allowed for the transition of paper chemotherapy orders to be managed electronically. This article describes the process for converting inpatient paper chemotherapy orders into the new EHR in a safe and effective manner.

SUMMARY

A collaborative interdisciplinary approach to the EHR transition enabled our organization to move from using paper chemotherapy orders to fully electronic chemotherapy treatment plans in both ambulatory and acute care areas. Active chemotherapy orders for acute care inpatients were reviewed and transcribed by two oncology pharmacists in the cancer hospital prior to being signed by an attending physician. The newly input orders were independently verified by two pharmacists in the cancer hospital inpatient pharmacy. Nurse review of the signed and verified treatment plans, along with reconciliation of the medication administration record ensured a safe transition to the new EHR workflow. Providers benefit from the ability to review treatment plans remotely, track changes, and include supportive medications in one consolidated location. The coordinated team effort allowed for a smooth transition with minimal interruptions to patient care.

CONCLUSION

The pharmacist-led, multidisciplinary conversion to electronic chemotherapy orders was safe, accurate, and occurred ahead of schedule for the EHR go-live. Advance communication and planning around scheduled inpatient admissions helped to minimize the impact of the transition from paper to electronic treatment plans. Both pharmacist and physician engagement were necessary to ensure a smooth transition for active inpatient treatment plans.

Evaluating Performance and Interpretability of Machine Learning Methods for Predicting Delirium in Gerontopsychiatric Patients

Delirium is an acute mental disturbance that particularly occurs during hospital stay. Current clinical assessment instruments include the Delirium Observation Screening Scale (DOSS) or the Confusion Assessment Method (CAM). The aim of this work is to analyze the performance of machine learning approaches to detect delirium based on DOSS and CAM information obtained from two geropsychiatric wards in Tyrol. From a machine learning perspective, the questions of these two assessment instruments represent the features and the ICD 10 diagnoses of delirium (yes/no) is the corresponding class variable. We compare seven popular classification methods and analyze the performance and interpretability of the learning models. As our dataset is highly imbalanced, we also evaluate the effect of common sampling methods including down- and up-sampling methods as well as hybrid methods. Our results indicate a high predictive ability of advanced methods such as Random Forest that can handle even unbalanced datasets. Overall, combining a good performance of a prediction model with the ability of users to understand the prediction is challenging. However, for clinical application in fully electronic settings, a good performance seems to be more important than an easy interpretation of the prediction by the user. On the other hand, explanations of decisions are often needed to assess other criteria such as safety.

Analysis of Primary Care Computerised Medical Records with Deep Learning

The analysis of primary care data plays an important role in understanding health at an individual and population level. Currently the utilization of computerized medical records is low due to the complexities, heterogeneities and veracity associated with these data. We present a deep learning methodology that clusters 11,000 records in an unsupervised manner identifying non-linear patterns in the data. This provides a useful tool for visualization as well as identify features driving the formation of clusters. Further analysis reveal the features that differentiate sub-groups that can aid clinical decision making. Our results uncover subsets that contain the highest proportion of missing data, specifically Episode type, as well as the sources that provide the most complete data.

Connecting Medical Records: An Evaluation of Benefits and Challenges for Primary Care Practices

BACKGROUND

Implementation of systems to support health information sharing has lagged other areas of healthcare IT, yet offers a strong possibility for benefit.  Clinical acceptance is a key limiting factor in health IT adoption.

OBJECTIVES

To assess the benefits and challenges experienced by clinicians using a custom-developed health information exchange system, and to show how perceptions of benefits and challenges influence perceptions of productivity and care-related outcomes.

METHODS

We used a mixed methods design with two phases. First, we conducted interviews with stakeholders who were familiar with the health information exchange system to inform the development of a measure of benefits and challenges of the use of this system. Second, using this measure we conducted a survey of current and former users of the health information exchange system using a modified Dillman method.

RESULTS

105 current and former users completed the survey. The results showed information quality, ease of completing tasks and clinical process improvement as key benefits that reduced workload and improved patient care.  Challenges related to system reliability, quality of reports and service quality increased workload and decreased impact on care, though the effect of the challenges was smaller than that of the benefits.

CONCLUSIONS

 Even very limited health information exchange capabilities can improve outcomes for primary care users.  Improving perceptions of benefits may be even more important the removing challenges to use, though it is likely that a threshold of quality must be achieved for this to be true.

Computer literacy of physicians among the hospitals of Makkah region

BACKGROUND AND OBJECTIVES

A confidential inquiry by the Directorate General of Health Affairs, Makkah region, Saudi Arabia, found physicians in different hospitals were reluctant to enter patients' related information in electronic medical record systems. One of the major issues raised was that they didn't have the required computer literacy. Our aim, therefore, was to conduct a survey to highlight the computer literacy among the physicians of Makkah region.

MATERIALS AND METHODS

This cross-sectional survey was performed from May to July 2009. A structured questionnaire of four A4 size paper was distributed among the physicians of the Makkah region working in seven different hospitals. The questionnaire contained questions on background knowledge of computers, i.e., (a) basic computer vocabulary knowledge (BCVK) (10 questions), (b) basic computer skills (BCS) (22 questions), (c) basic communication and internet skills (BCIS) (12 questions).

RESULTS

Response rate of 368, i.e., 81.6% of sample size (n = 451) was attained. The maximum response came from King Abdul Aziz Hospital (Taif), i.e., 79%. Overall BCVK, BCS and BCIS were the highest among the physicians of Alnoor Specialist Hospital, i.e., 71.3%, 91.4%, 87.7%, respectively. All the hospitals had a satisfactory level of BCVK, but levels of BCS and BCIS were above satisfactory except King Abdul Aziz Hospital (Jeddah) that showed a satisfactory level in BCIS.

CONCLUSION

Majority of the physicians had a good or an excellent level of computer background knowledge that gave a prediction toward the issues of their non-promising attitude and beliefs about electronic data entry.

A Java-based electronic healthcare record software for beta-thalassaemia

BACKGROUND

Beta-thalassaemia is a hereditary disease, the prevalence of which is high in persons of Mediterranean, African, and Southeast Asian ancestry. In Greece it constitutes an important public health problem. Beta-thalassaemia necessitates continuous and complicated health care procedures such as daily chelation; biweekly transfusions; and periodic cardiology, endocrinology, and hepatology evaluations. Typically, different care items are offered in different, often-distant, health care units, which leads to increased patient mobility. This is especially true in rural areas. Medical records of patients suffering from beta-thalassaemia are inevitably complex and grow in size very fast. They are currently paper-based, scattered over all units involved in the care process. This hinders communication of information between health care professionals and makes processing of the medical records difficult, thus impeding medical research.

OBJECTIVES

Our objective is to provide an electronic means for recording, communicating, and processing all data produced in the context of the care process of patients suffering from beta-thalassaemia.

METHODS

We have developed - and we present in this paper - Java-based Electronic Healthcare Record (EHCR) software, called JAnaemia. JAnaemia is a general-purpose EHCR application, which can be customized for use in all medical specialties. Customization for beta-thalassaemia has been performed in collaboration with 4 Greek hospitals. To be capable of coping with patient record diversity, JAnaemia has been based on the EHCR architecture proposed in the ENV 13606:1999 standard, published by the CEN/TC251 committee. Compliance with the CEN architecture also ensures that several additional requirements are fulfilled in relation to clinical comprehensiveness; to record sharing and communication; and to ethical, medico-legal, and computational issues. Special care has been taken to provide a user-friendly, form-based interface for data entry and processing.

RESULTS

The experience gained through the use of JAnaemia in 4 Greek hospitals reveals a significant contribution towards (1) improvement of the quality of the data being recorded, since data entry is guided by appropriate forms, (2) easier cooperation between physicians, who share a common information repository, and (3) increased processing capabilities, which facilitate medical research.

CONCLUSIONS

JAnaemia appears to be a useful tool, which can improve the quality of care offered to beta-thalassaemic patients in Greece.