Hospital Doctors Research Articles

The Path of a Cardiac Patient-From the First Symptoms to Diagnosis to Treatment: Experiences from the Tertiary Care Center in Poland.

Cardiovascular diseases (CVDs) are major concerns in the healthcare system. An individual diagnostic approach and personalized therapy are key areas of an effective therapeutic process. The major aims of this study were: (1) to assess leading patient problems related to symptoms, diagnosis, and treatment of CVDs, (2) to examine patients’ opinions about the healthcare system in Poland, and (3) to provide a proposal of practical solutions. The 27-point author’s questionnaire was distributed in the Cardiology Department of the Tertiary Care Centre between 2nd September–13th November 2021. A total of 132 patients were recruited, and 82 (62.12%; nmale = 37, 45.12%; nfemale = 45, 54.88%) was finally included. The most common CVDs were arrhythmias and hypertension (both n = 43, 52.44%). 23 (28.05%) patients had an online appointment. Of the patients, 66 (80.49%) positively assessed and obtained treatment, while 11 (13.41%) patients declared they received a missed therapy. The participants identified: (1) waiting time (n = 31; 37.80%), (2) diagnostic process (n = 18; 21.95%), and (3) high price with limited availability of drugs (n = 12; 14.63%) as the areas that needed the strongest improvement. Younger patients more often negatively assessed doctor visits (30–40 yr.; p = 0.02) and hospital interventions (40–50 yr.; p = 0.008). Older patients (50–60 years old) less often negatively assessed the therapeutic process (p = 0.01). The knowledge of the factors determining patient adherence to treatment and satisfaction by Medical Professionals is crucial in providing effective treatment. Areas that require the strongest improvement are: (1) waiting time for an appointment and diagnosis, (2) limited availability and price of drugs, and (3) prolonged, complicated diagnostic process. Providing practical solutions is a crucial aspect of improving CVDs therapy.

Expanded prenatal syphilis screening in Manitoba, Canada: a direct short-term cost-avoidance analysis in an outbreak context.

The objective of this study is to provide a direct short-term cost-avoidance analysis of expanded three-time prenatal syphilis screening in the context of Manitoba's ongoing outbreak. A conservative modelling approach increased all financial costs of prenatal screening and minimized the direct costs of congenital syphilis treatment. The cost of syphilis screening was calculated using instrument, reagent and consumable costs as well as laboratory overhead and labour costs as documented by Cadham Provincial Laboratory. The short-term direct costs of treating congenital syphilis were calculated using hospital costs and doctor's billing fees. All costs were calculated in 2021 Canadian dollars. These numbers were applied to Manitoba's 2021 congenital syphilis statistics to provide a pragmatic cost-avoidance analysis. The cost of applying three-time prenatal syphilis screening to all 16,800 yearly pregnancies in Manitoba equalled CAD $139,608.00 per year. The direct short-term cost of treating one uncomplicated case of congenital syphilis was $18,151.40. As 81 cases of congenital syphilis were treated in Manitoba in 2021, the short-term direct cost of treating congenital syphilis in Manitoba in 2021 was $1,470,263.40. Applying screening costs to the 125 adequately prevented cases of congenital syphilis in 2021, the screening program is associated with a cost-avoidance ratio of 16.25. If no prenatal syphilis program existed in Manitoba, an expanded screening program would be associated with a cost-avoidance ratio of 26.8. Expanding prenatal syphilis screening is highly cost-avoidant in Manitoba. The 81 cases of congenital syphilis treated in Manitoba in 2021 highlight the need for novel community-based approaches to increase accessibility and engagement with prenatal care.

Increased Rate of Spontaneous Pneumothorax in Infants of COVID-19 Positive Mothers

Abstract Objective The epidemiological and clinical characteristics of neonates born to women infected with coronavirus disease 2019 (COVID-19) during pregnancy were assessed, and the correlation between this infection and spontaneous pneumothorax in neonates born to mothers with COVID-19 was evaluated in the present study. Methods Records of 14 neonates in the neonatal intensive care unit with pneumothorax were collected and analyzed. Pregnant women were routinely screened for COVID-19 before birth. This study only included the neonates of mothers positive for severe acute respiratory syndrome coronavirus 2 immunoglobulin Mand immunoglobulin G and developing spontaneous pneumothorax. Antenatal, natal and postnatal risk factors, data related to demographic, epidemiological and clinical characteristics, treatment strategies, and breastfeeding history were obtained from medical records. Results The gestational age of the 14 neonates was 30 to 38 weeks. One male infant was born by normal spontaneous vaginal delivery, while all other infants were born by C-section. Though the mothers did not have a diagnosis of COVID-19 in their charts, they all reported one or more symptoms when interviewed. No mother had received a COVID-19 vaccination before or during pregnancy. No mother had undergone a hospital visit or doctor examination due to suspicion of COVID and COVID polymerase chain reaction test. COVID antibody titers were present during admission to hospital before birth. Conclusion The infants of pregnant cases with symptomatic or asymptomatic COVID-19 may develop respiratory distress and pneumothorax. Observational data obtained from case series similar to what is presented here may be accepted as a potential first step to producing hypotheses to test with preclinical or clinical models if it can be expanded in larger cohorts.

35126 Education to improve general medical doctors’ dermatology referrals

General hospital doctors often find it challenging to correctly diagnose and appropriately refer common benign and malignant skin lesions. A series of dermatology images of melanoma, nonmelanoma malignancies, actinic keratosis and benign lesions was presented in a quiz format to general medical doctors in a model 3 hospital. Dermatology experience, confidence in lesion recognition and decision for dermatology referral was surveyed pre-teaching. A teaching session with follow-up quiz and self-assessed confidence of lesion recognition and diagnosis was surveyed. Comparison pre and post quiz scores were analyzed. Twenty-four medical doctors ranging from intern to consultant participated in this study. 96% (n = 23) had no prior dermatology experience. Following teaching, 61% (n = 14) expressed feeling confident in their diagnosis of presented images, compared with 17% (n = 4) preteaching. The follow-up quiz showed a global 24% increase in lesion recognition. Correct referral of actinic keratosis improved from 79% to 100%, acral melanoma improved from 75% to 90%, melanoma referral improved from 77% to 93% and BCC referral improved from 88% to 100%. 91% (n = 21) found the teaching session helpful for future practice. The teaching session improved the ability to correctly identify features of common benign, premalignant and malignant skin lesions. The follow-up quiz demonstrated improvement in appropriate referrals for premalignant and malignant lesions. Regular dermatology teaching with images and self-assessment quizzes should improve the confidence of general hospital doctors to correctly recognize and refer to dermatology services. This study demonstrates the need for dermatology teaching to general medical doctors to improve the accurate diagnosis and referral of common skin lesions.

Navigating Through a Struggling Health System; the Staggering Experience of a Struggling Family

Born at 28 weeks of gestation and weighing 800g at birth, her father preferred a public health facility where the cost of neonatal intensive care is less prohibitive. At the same time, her mother suffered wound dehiscence and was re-admitted for a prolonged period. Incidentally, resident doctors in public hospitals were three weeks into a nationwide industrial action at the time. With no one available to help out with household chores, the father had to combine the care of two children, and the logistics of two hospitals. The kids at home soon dropped out of school when the financial burden became unbearable. Even though the family’s long and onerous journey eventually ended, its impact is a large ‘wound’ that may take a while to heal.

Factors Related To The Implementation Of Communication With The Sisbar Method ( Salam Introduction Situation Background Assessment Recommendation ) At Medical-Surgical Wards In Santosa Hospital Bandung Central

This study focus on is there any connection between factors ( age , gender , length of work and origin room ) with implementation communication with the SISBAR (Salam Introduction Situation Background Assessment Recommendation) method. This Study use cross sectional design. Sample of this study is the total sample nurse in charge who implementation SISBAR communication (West Safir , East Safir , West Berlian and Mutiara wards) in Santosa Hospital Bandung Central that fulfills inclusion criteria sample totaling 44 nurses.The method used total sampling technique that whole population made sample on this research. Analysis bivariate used for seeing connection between 2 variables (independent and dependent). Analysis is conducted for see meaningful relationship by statistics, use statistical test Chi Square with level 95% confidence (?=0.05).Analysis test results statistics using the Chi Square test obtained p-Value: 0.048 (variable age ), 0.004 (variable education ) and 0.011 (variable length of work ), while the other two factors are not connection with p value for each of these factors is 1,000 (variable type gender ) and 0.791 ( original variable room ). It means there is connection between the variables of age , education and length of work, whereas variable gender and origin room is no relationship with implementation communication effective with SISBAR method between nurses and doctors.SISBAR communication can be developed and enhanced for effective communication between nurses and doctors in other hospitals in Indonesia with pay attention to the factors that influence it.

Application of X-ray examinations in General practice for the diagnosis of lung damage in patients suspected of COVID-19 infection

General practitioners who have access to diagnostic investigations from primary health care and clear referral guidelines to follow can utilize these resources as efficiently as hospital physicians and doctors from secondary health care [1-3]. More complex imaging methodologies such as magnetic resonance imaging (MRI) and X-ray computed tomography (CT) cannot be used in Bulgarian General Practice yet and they are subject to restrictions by the National Health Insurance Fund. The most readily available imaging method that general physicians can apply in the diagnosis of COVID-19 patients is convectional chest radiography. This is a first-line test for detecting lung pathology and it is helpful for evaluation of patients with a high pre-test probability of overt COVID-19 pneumonia, clinical follow up, and for the evaluation of potential complications [4].

SHUBHCHINTAK: An efficient remote health monitoring approach for elderly people.

With the proliferation of IoT technology, it is anticipated that healthcare services, particularly for the elderly persons, will become a major thrust area of research in the coming days. Aim of this work is to design a fit-band containing multiple sensors to provide remote healthcare services for the elderly persons. An application has been designed to capture health data from the fit-band, pre-process the data and then send them to cloud for further analysis. A wireless Bluetooth enabled connection is proposed to establish communications between sensors and the application for data transmission. In the proposed application, there are three different front-end interfaces for three different users: system administrator, patient and doctor. The data collected from the patient’s fit-band are sent to a cloud data storage, where the data will be analyzed to detect anomaly (e.g., heart attack, sleep apnea, etc.). A Convolution Neural Network (CNN) model is proposed for anomaly detection. For the classification of anomaly, a Long Short Term Memory (LSTM) model is proposed. In the presence of anomaly, the system immediately connects a doctor through a phone call. A prototype system termed as Shubhchintak has been developed in Android/IOS environment and tested with a number of users. The fit-band provides data tracking with an overall accuracy of 99%; the system provides a response with 3000 requests in less than 100 ms. Also, Shubhchintak provides a real-time feedback with an accuracy of 97%. Shubhchintak is also tested by patients and doctors of a nearby hospital. Shubhchintak is shown to be a simple to use, cost effective, comfortable, and efficient system compared to the existing state of the art solutions.

Sharing is Caring & Giving is Winning

The COVID-19 pandemic has been the defining health crisis of our generation. In the UK healthcare industry, where pre-pandemic surveys already demonstrated high levels of stress, it is imperative that actions are taken to support the mental wellbeing of staff from its expected psychological fallout. Feasible, low cost and time efficient interventions are warranted. Rewards-based incentives may carry promise. Our group distributed 129 free wellbeing packages to junior doctors in a busy London Hospital. Open-ended and anonymised surveys were used to gather qualitative data on their effect. Data was analysed thematically and collated into 5 core themes: Emotional Response, Reaction to Initiative, Reaction to Product Choice, Gratitude and Feeling Valued. Overall, the significant majority of respondents (n=50, 96%) were highly appreciative of the intervention, deeming it both useful and relevant to supporting their mental health. This study bears useful findings for other organisations looking to implement similar low-cost wellbeing strategies.

WE6.10 Gender Balance at Surgical Meetings in Ireland

Abstract Aim To assess the genders of lead authors and primary investigators in major surgical research meetings over a 10-year period in Ireland. Method We gathered data from the 3 main surgical conferences in Ireland. We looked at the abstracts of each of the plenary sessions over the last 10 year. We used the Irish Medical Council, previous published research from these authors and ResearchGate to help identify the gender of the author. We complied and analysed the data using Excel. Results We analysed 306 papers over the last 10 years. We found that the primary investigator was male in 78% of the papers and female in 20%. The primary author was male in 52% and was female in 46% of the papers. There has been little change over each 5-year interval for who was the primary investigator. In 2010–2015, it was 77% male and 23% female while from 2016–2020, it was 82% male and 18% female. Furthermore, in relation to the primary author, it has shifted from being relatively equal to becoming more male dominant. In 2010–2015, it was 52% female and 48% female while from 2016–2020, it was 57% male and 43% female. Conclusion The gender gap has appeared to have widened at the non-consultant hospital doctor level and it is very apparent that there is a large inequality at consultant level regarding surgical research in Ireland.

Juridical Analysis of Patients’ Rights to Information Disease and Action Medical by Doctor in Hospital

This study analyzed juridical analysis of patients’ rights to disease information and medical action by doctors in hospitals. The method used is a legal research method that aims to find solutions to legal issues and problems that arise from them. The results of the study show that the legal implications of regulating the right to information on diseases and medical actions given to patients by doctors in hospitals have an impact on the patient’s right to receive disease information openly and transparently from doctors related to diseases experienced by patients and patients have the right to be served maximally in obtaining medical treatment (Health services) by doctors at the hospital so that patients have the right to file claims if these rights are not fulfilled. Then, the presence of new health law, namely Law Number 36 of 2009, gives patients the right to refuse actions taken against themselves and to end treatment and care for their own responsibilities after obtaining clear information about their disease. In conclusion, the emergence of the Prita Mulyasari case was based on the non-fulfilment of the patient’s right to medical information. It was due to the absence of adequate and accurate communication between the doctor and the patient. Conflicts can be avoided if all parties, in this case, the doctor, patient and hospital, negotiate through deliberation and consensus by considering their respective rights and obligations.

The Moderating Role of Career Commitment on Medicals Doctors’ Turnover Intention in Algeria

This conceptual paper is developed to determine the effects of job design and self-efficacy on turnover intention among doctors in Algerian public hospitals. Additionally, this conceptual paper proposes to test career commitment as a moderator between the relationship between job design and self-efficacy towards turnover intention among doctors in Algeria due to the inconsistent findings of the relationship between job design and self-efficacy towards turnover intention. These inconsistent findings based on the empirical evidence do not permit such information to the existing literature; thereby, requiring further empirical exploration. This study refers to the Social Exchange Theory (SET) and Social Cognitive Theory (SCT) to explain the relationship among all variables. Empirical evidence reported a significant effect of job design on employees’ turnover intention. Also, past authors presented significant effects of another variable such as self-efficacy on turnover intention. Not only that, the role of career commitment as a moderator is expected can enhance the relationship between the predictors (e.g., job design and self-efficacy) and the criterion (e.g., turnover intention) in this study. Furthermore, SET has been referred to explain the relationship between job design and turnover intention. Meanwhile, SCT has been used as a theory to explain the relationship between self-efficacy and turnover intention. At the end of this study, several actions can be proposed in order to let doctors can be retained the Algerian healthcare sector. By taking the appropriate actions in the aspects of job design and self-efficacy the level of turnover intention among the Algerian doctor can be decreased. Thus, this may help to solve the shortage of medical doctors in the country.

Prevalence And Risk Factors of Fear of Fall Among Old Age Population of Lahore, Pakistan

Falls are one of the most common problems that older people face, and they are a major contributor to their higher morbidity and mortality rates. Anxiety over falling, whether actual or perceived, is the most common description of this condition. Objective: To assess prevalence and risk factors of fear of falling among old population in Lahore, Pakistan Methods: A cross-sectional study was conducted on 139 old age population. The data was collected on the spot from the University of Lahore teaching hospital and doctor hospital. Data was collected using a non-probability convenient sampling technique. Fall efficacy scale 1 and self-administered questionnaire were used for data collection. Results: 64% of the 139 participants were female, while 39.6% were male; 19 (13.7%) were over 80 years old, while 36 (24.9%) were 60 to 69 years old; BMI of 71 (51%) was below normal; and 62 (44.6%) had a history of falling. Fear of falling was expressed by 62.6% of the older population, and it was linked to all risk factors. Conclusion: Fear of falling is very common in the old population of Lahore, Pakistan Furthermore age, BMI, and past fall experience were all connected to fear of falling.

Doctors' Communication Skills in Military Hospitals–A Critical Analysis

Objective: To assess the level of communication skills of doctors in military hospitals and compare their own and patient perceptions. We also aimed to determine factors affecting doctors' communication skills and suggest recommendations for improving doctors' communication skills.
 Study Design: Cross-sectional study.
 Place and Duration of Study: CMH Lahore, CMH Gujranwala and CMH Chunian and Armed Forces Institute of Cardiology, Rawalpindi, from Oct 2016 to Jun 2017.
 Methodology: Through non-probability consecutive sampling, questionnaires were distributed to 100 physicians and 100 patients inquiring about various aspects of doctors' communication skills and factors affecting them.
 Results: Doctors were asked to judge the overall level of their communication skills, and more than half of them (53%) opined that their communication skills were very good. However, the perception of doctors' communication skills was better by doctors themselves compared to patients' perception. More than half of the doctors strongly agreed that increased workload, use of the hospital management system and extra commitments were major impediments to effective communication skills.
 Conclusion: The perception about the communication skills of doctors is not as high as that of the doctors themselves. There is a striking disparity between the physicians' and patient responses. The communication skills of doctors can be improved by formal training of physicians in the form of workshops. In addition, the workload on doctors should be reduced by minimizing extra commitments.

Feature Extraction Approach for Speaker Verification to Support Healthcare System Using Blockchain Security for Data Privacy.

Speech is one form of biometric that combines both physiological and behavioral features. It is beneficial for remote-access transactions over telecommunication networks. Presently, this task is the most challenging one for researchers. People's mental status in the form of emotions is quite complex, and its complexity depends upon internal behavior. Emotion and facial behavior are essential characteristics through which human internal thought can be predicted. Speech is one of the mechanisms through which human's various internal reflections can be expected and extracted by focusing on the vocal track, the flow of voice, voice frequency, etc. Human voice specimens of different ages can be emotions that can be predicted through a deep learning approach using feature removal behavior prediction that will help build a step intelligent healthcare system strong and provide data to various doctors of medical institutes and hospitals to understand the physiological behavior of humans. Healthcare is a clinical area with data concentrated where many details are accessed, generated, and circulated periodically. Healthcare systems with many existing approaches like tracing and tracking continuously disclose the system's constraints in controlling patient data privacy and security. In the healthcare system, majority of the work involves swapping or using decisively confidential and personal data. A key issue is the modeling of approaches that guarantee the value of health-related data while protecting privacy and observing high behavioral standards. This will encourage large-scale perception, especially as healthcare information collection is expected to continue far off this current ongoing pandemic. So, the research section is looking for a privacy-preserving, secure, and sustainable system by using a technology called Blockchain. Data related to healthcare and distribution among institutions is a very challenging task. Storage of facts in the centralized form is a targeted choice for cyber hackers and initiates an accordant sight of patients' facts which will cause a problem in sharing information over a network. So, this research paper's approach based on Blockchain for sharing sufferer data in a secured manner is presented. Finally, the proposed model for extracting optimum value in error rate and accuracy was analyzed using different feature removal approaches to determine which feature removal performs better with different voice specimen variations. The proposed method increases the rate of correct evidence collection and minimizes the loss and authentication issues and using feature extraction based on text validation increases the sustainability of the healthcare system.

Remote Analysis of Respiratory Sounds in Patients With COVID-19: Development of Fast Fourier Transform-Based Computer-Assisted Diagnostic Methods.

BackgroundRespiratory sounds have been recognized as a possible indicator of behavior and health. Computer analysis of these sounds can indicate characteristic sound changes caused by COVID-19 and can be used for diagnostics of this illness.ObjectiveThe aim of the study is to develop 2 fast, remote computer-assisted diagnostic methods for specific acoustic phenomena associated with COVID-19 based on analysis of respiratory sounds.MethodsFast Fourier transform (FFT) was applied for computer analysis of respiratory sound recordings produced by hospital doctors near the mouths of 14 patients with COVID-19 (aged 18-80 years) and 17 healthy volunteers (aged 5-48 years). Recordings for 30 patients and 26 healthy persons (aged 11-67 years, 34, 60%, women), who agreed to be tested at home, were made by the individuals themselves using a mobile telephone; the records were passed for analysis using WhatsApp. For hospitalized patients, the illness was diagnosed using a set of medical methods; for outpatients, polymerase chain reaction (PCR) was used. The sampling rate of the recordings was from 44 to 96 kHz. Unlike usual computer-assisted diagnostic methods for illnesses based on respiratory sound analysis, we proposed to test the high-frequency part of the FFT spectrum (2000-6000 Hz).ResultsComparing the FFT spectra of the respiratory sounds of patients and volunteers, we developed 2 computer-assisted methods of COVID-19 diagnostics and determined numerical healthy-ill criteria. These criteria were independent of gender and age of the tested person.ConclusionsThe 2 proposed computer-assisted diagnostic methods, based on the analysis of the respiratory sound FFT spectra of patients and volunteers, allow one to automatically diagnose specific acoustic phenomena associated with COVID-19 with sufficiently high diagnostic values. These methods can be applied to develop noninvasive screening self-testing kits for COVID-19.

The Role of Social Responsibility of the Egyptian Private Hospitals in Overcoming the COVID-19 Pandemic

With the increase risks associated to COVID-19 all over the world, many firms in different sectors have participated by providing immediate assistance to relief the pandemic’s negative effects, this paper explores the role of Egyptian private hospitals’ social responsibilities in comfort undesirable impacts of the COVID-19. Based on the collected data from 303 workers in private hospitals (doctors, nursing staff, and administrative staff), the results show that Egyptian private hospitals that are socially committed to their employees are likely to apply the activities of overcoming COVID-19 compared with those activities applied to their patients and the external parties (government, community, and the environment). This requires increasing private hospitals’ attention to their societal role towards patients and other external parties that deal with them.

Awareness of Cardiopulmonary Resuscitation amongst Interns and Resident Doctors: A Cross Sectional Analysis in a Tertiary Care Hospital in Northern India

Background: Knowledge of basic and advanced cardiac life support is of paramount significance amongst health care professionals to attain higher survival rate of patients suffering from sudden cardiac death. Objectives: To determine the awareness and knowledge for performing high quality CPR amongst junior resident doctors in a tertiary care hospital. Methods: In a prospective cross-sectional study, 220 preformed questionnaires were distributed amongst the interns, postgraduate and non-postgraduate junior resident and senior resident doctors, with a response rate of 69% (n-152). Data on the responders awareness of cardipulmonary resuscitation (CPR), core knowledge of basic life supoort (BLS) and advanced cardiac life supoort (ACLS) were collected. Data was subjected to descriptive and inferential statistical analyses using SPSS version 23.0 and was expressed as mean ± standard deviation or in percentage. A p-value ≤ 0.05 was considered as significant level. Results: Among the 152 responders, 31(20%) were interns, 74(49%) were postgraduate course junior residents (PG JR), 7(5%) were non- post-graduate course (Non-PG JR) and 40 (26%) were senior resident (SR) doctors. Only 24% (n-36) of doctors have done previous certified CPR training course. The awareness of resuscitation amongst all doctors was 71% and observed highest amongst the PG JRs 73%. The core knowledge of BLS and ACLS was only 47% and 44% respectively, amongst all doctors. Conclusion: Majority of resident doctors have limited knowledge of basic concept of BLS and ACLS guidelines. A well structured and evidence based format of CPR training should be incorporated in training modules for better outcome.

Job Satisfaction among Resident Doctors of a Tertiary Care Hospital in South Delhi.

Doctors' job satisfaction is crucial to the health service to ensure commitment, effective training, service provision, and retention. Job satisfaction matters to doctors for their happiness, fulfilment, service to patients, and duty to employers. The quality of performance in the health sector to a large extent depends on whether healthcare providers are job-satisfied or dissatisfied. This study assessed the level and factors determining job satisfaction among resident doctors in a federal tertiary institution. A cross-sectional study was conducted among the resident doctors of a government tertiary care hospital. Data were collected using a self-reported questionnaire consisting of 49 items under seven domains of job satisfaction, where higher values indicated a higher level of satisfaction. The average scores of items were computed to construct factor scores for each individual. A Chi-square test was applied. The proportion of job satisfaction among resident doctors was found to be 80.9%. On adjustment, the odds of being satisfied were found to be higher in the older age groups, among males, and doctors posted in clinical departments. Most respondents in this study were satisfied with their jobs with minorities satisfied with their monetary and infrastructure facilities. There is a need to address these issues to enhance healthcare quality, especially in the public sector.

An intelligent prediagnosis system for disease prediction and examination recommendation based on electronic medical record and a medical-semantic-aware convolution neural network (MSCNN) for pediatric chronic cough.

BackgroundDue to the phenotypic similarities among different pediatric respiratory diseases with chronic cough, primary doctors often misdiagnose and the misuse of examinations is prevalent. In the pre-diagnosis stage, the patients' chief complaints and other information in the electronic medical record (EMR) provide a powerful reference for respiratory experts to make preliminary disease judgment and examination plan. In this paper, we proposed an intelligent prediagnosis system to predict disease diagnosis and recommend examinations based on EMR text.MethodsWe examined the clinical notes of 178,293 children with chronic cough symptoms from retrospective EMR data. The dataset is split into 7:3 for training and testing. From the testing set, we also extract 5% of samples for validation. We proposed a medical-semantic-aware convolution neural network (MSCNN) framework that can accomplish two downstream tasks from the same medical language model through transfer learning. First, a medical language model based on the word2vec algorithm was built to generate embeddings for the text data. Then, text convolutional neural network (TextCNN) was used to build models for disease prediction and examination recommendation.ResultsWe implemented 5 algorithms for disease prediction. In the disease prediction task, our algorithm outperformed the baseline methods on all metrics, with a top-1 accuracy (AC) of 0.68 and a top-3 AC of 0.923 on the testing set. By adding data enhancement, the top-3 AC reached 0.926. In the examination recommendation task, the overall AC on the testing set was 0.93 and the macro average (MA) F1-score was 0.88. The average area under the curve (AUC) on the training set was 0.97 while on the testing set it was 0.86.ConclusionsWe constructed an intelligent prediagnosis system with an MSCNN framework that can predict diseases and make examination recommendations based on EMR data. Our approach achieved good results on a retrospective clinical dataset and thus has great potential for the application of automated diagnosis assist in clinical practice during pre-diagnosis stage, which will provide help for primary level doctors or doctors in basic-level hospitals. Due to the generality of the proposed framework, it can be straight forwardly extended to prediagnosis for other diseases.