Respiratory Health Study: Pulmonary Infection Screening Using Wearable Sensor Data

doi:10.21203/rs.3.rs-1819753/v1

Download PDF

Article

Respiratory Health Study: Pulmonary Infection Screening Using Wearable Sensor Data

https://doi.org/10.21203/rs.3.rs-1819753/v1

This work is licensed under a CC BY 4.0 License

Version 1

posted

You are reading this latest preprint version

Background

The proliferation of smart devices provides the possibility of the early detection of the signs of pulmonary infection. This study validates a smart device-based algorithm to monitor the risk of pulmonary infection.

Methods

An algorithm that runs on Huawei smart devices (Huawei Technologies Co., Ltd., Shenzhen, China) was developed and tested in 87 patients with pulmonary infection and 409 healthy subjects. The algorithm examines heart rate variability, respiratory rate, oxygen saturation, body temperature, and cough sound. It was embedded into the Respiratory Health Study app for a smartwatch to detect the risk of pulmonary infection and was further validated in the hospital. Pulmonary infection was diagnosed by doctors using a clinical evaluation, lab tests, and imaging examination, the gold standard for diagnosis. The accuracy, sensitivity, and specificity of the algorithm predicting pulmonary infection were evaluated.

Results

In all, 80 patients with pulmonary infections and 85 healthy volunteers were recruited to validate the accuracy of the algorithm. The area under the curve of the algorithm for predicting pulmonary infection was 0.86 (95% confidence interval: 0.82–0.91) (P < 0.001). Compared to the gold standard, the overall accuracy of the algorithm was 85.9%, the sensitivity was 81.4%, and the specificity was 90.4%. The algorithm for heart rate, respiratory rate, oxygen saturation, and body temperature had an accuracy of 68.2%, and the accuracy of the algorithm including cough sound was 82.6%.

Conclusion

Our wearable system facilitated the detection of risk of pulmonary infection. Multi-source features were useful for enhancing the performance of the lung infection screening algorithm.

Trial Registration

Chinese Clinical Trial Registry of the International Clinical Trials Registry Platform of the World Health Organization ChiCTR2100050843; http://www.chictr.org.cn/showprojen.aspx?proj=126556

Wearable device

Lung infection

Cough sound analysis

Pneumonia

Lower respiratory tract infection (LRTI), a major category of respiratory disease, is a major health problem and the fourth leading burden of disease in the world [1]. In 2017 alone, an estimated 470 million people worldwide suffered from LRTI, of which 2.56 million died [2]. Due to the aging population and the ensuing increase in health complications in China, the incidence of LRTI will undoubtedly increase over the next decade. Generally, healthy people with a good microbial balance are not prone to LRTI. The LRTI-susceptible population only refers to people with low immunity and young and middle-aged people in an often temporary state of immune imbalance. Clinical studies have consistently demonstrated the need for timely medical intervention; delayed recognition of illness results in adverse outcomes and increased costs [3, 4]. The search for biomarkers for early detection of LRTI will become a new prevention strategy and help timely treatment in susceptible people. Here, biomarkers are not necessarily molecular objects, such as proteins, metabolites, or RNA(Ribonucleic Acid, RNA) transcripts, but can also be digital signals of life. For example, wearable devices are used for the noninvasive and continuous monitoring of vital signs, analysis of high-density data, and detection of deviations between individuals and the baseline to identify LRTI in the early stages and provide targeted early treatment to avoid further harm.

Advances in electrical hardware design and data processing methods have led to the development of technology capable of detecting multiple physiological parameters in a continuous, noninvasive way. For example, changes in heart rate variability (HRV) are easy to evaluate using current commercial technologies. Some studies have used smartwatch technology to detect possible COVID-19 infection through monitoring changes in HRV or resting heart rate compared to baseline [5–8]; others have extended this to identify infection 3 to 4 days before symptoms appear, adding a prediction of the severity of infection as well, using the degree of change in physiological data [9–12]. It has been reported that physiological parameter measurement can predict pneumonia in children, reaching a sensitivity of 96.6% and specificity of 96.4% [13]. Other wearable technologies can also contribute to the diagnosis. For example, Health Care Origins (Rochester, New York) developed a wearable respiratory monitoring device for observation and automatic management of asthma. It has the ability to detect abnormal breathing sounds in real time, from the wheezing usually associated with asthma to the local burst sounds heard in LRTI [14]. Although wearable monitoring technology cannot distinguish between bacterial and viral pathogens, it can warn of disease in advance and allow early detection and treatment to avoid serious illnesses requiring hospitalization.

While most wearable devices detect indicators such as heart rate and rhythm, sleep, and exercise, the monitoring of respiratory diseases, including the monitoring of potentially valuable signals such as blood oxygen saturation, body temperature, cough audio, and respiratory rate is rare. Few studies have reported the diagnostic role of these signals in respiratory tract infection. As the first such study in China, this study monitored the above signals in normal adults and patients with LRTI, established an algorithmic model, and further verified the model in suspected patients with LRTI and healthy people, to prepare for population-level screening of pulmonary infectious diseases.

We designed a “Respiratory Health Study” platform application (Figure 1) that includes the following two parts: 1. smart devices measure physiological parameters including heart rate, blood oxygen, respiratory rate, body temperature, and cough sound; 2. the measured physiological parameters are uploaded to the cloud through the mobile app Respiratory Health Research; the system was designed to seek the deviations among the physiological parameters between pulmonary infections and healthy volunteers. Using this system, we established and verified the algorithm for pulmonary infection screening. All data were uploaded to the given research platform, and outside researchers had no access. The study was approved by the Ethics Committee of Chinese PLA General Hospital, Approval No. S2021-663-01. All participants signed informed consent before beginning the study. Further, this
study was registered in the Chinese Clinical Trial Registry, which was part of the International Clinical Trials Registry Platform of the World Health Organization (ChiCTR2100050843).

Establishment of the Pulmonary Infection Screening Algorithm

We enrolled 137 adult patients with suspected pneumonia hospitalized in the first and eighth medical center of the PLA General Hospital from June 1, 2021, to August 31, 2021, and 409 asymptomatic healthy controls for the training dataset. Data collection was based on a clinical questionnaire (Supplement 1), electronic disease history, and physiological parameter measurement using a wearable device. The smart device (Figure 2A, B) presented to the patients monitored, recorded, and analyzed their heart rate, respiratory rate, body temperature, cough sound, and blood oxygen saturation when worn; these data were used to develop a screening algorithm for pulmonary infection. The pneumonia diagnosis was made simultaneously by two independent physicians with respiratory specializations. Then, 137 patients who were confirmed to have a pneumonia diagnosis were used for the algorithm. Combined with 409 healthy volunteers, 545 sets of wearable data were collected (Figure 3).

Figure 1. Respiratory Health Research App and Huawei Smart Device

Figure 2. Collection of Cough Sound (A) and Physiological Parameters (B)

Validation of the Pulmonary Infection Screening Algorithm

To verify the accuracy of the algorithm, we recruited 75 hospitalized patients with suspected pneumonia and 85 healthy controls to form the validation dataset from the eighth medical center of the PLA General Hospital from September 10 to November 10, 2021. Three algorithms were generated: one only measured the cough sound (Algo-CS); another measured only the physiological parameters apart from the cough (Algo-PP), namely, heart rate, blood oxygen, body temperature, and respiratory rate; and the third combined the other two (Algo-CSPP). The diagnosis of pulmonary infection took the final clinical discharge diagnosis as the gold standard for comparison with the results of monitoring to verify the accuracy, specificity, and sensitivity of the algorithm.

Figure 3. Flow Diagram of the Study

Inclusion, Exclusion, and Diagnostic Criteria for Patients with Pneumonia

Inclusion criteria: 1. age ≥ 18 years; 2. computed tomography (CT) identification of suspected pulmonary lesions; and 3. patient compliance with wearing a smartwatch.

Exclusion criteria: 1. patient not diagnosed with pneumonia; 2. poor sensor signal quality on wearable device; and 3. patient withdrawal before completion of data collection.

The pneumonia diagnostic standard is as follows: 1. recent cough, expectoration, or aggravation of original respiratory disease, with or without sputum production, chest pain, tachypnea, dyspnea, wheezing, or hemoptysis; 2. fever; 3. physical findings such as lung consolidation and/or wet rales; 4. peripheral blood leukocytes > 10 × 10⁹/L or < 4 × 10^9/L, with or without left shift of nucleus; and 5. chest imaging examination via CT that shows new patchy infiltration, consolidation of leaves or segments, ground glass observation, or interstitial changes, with or without pleural effusion. Pneumonia is defined as meeting either criterion 1 or 2 above, which excludes the pathophysiological changes caused by pulmonary edema, atelectasis, pulmonary eosinophilic infiltration, and pulmonary vasculitis.

Physiological Data Acquisition Using the Wearable Device

The acquisition of physiological signals by a wearable device was divided into two parts, and each patient collected the data for each part separately.

The first part was nocturnal monitoring. Patients wore their smart devices in bed to collect data over the entire sleep period, including data on the motion of the body measured using an accelerometer; heart rate, respiratory rate, and blood oxygen data measured via PPG signals; and body temperature data.

The second part involved spontaneous measurement data. Wearing a smart device, patients were asked to take a deep breath and then cough serially and vigorously three times, repeating the entire process twice. Next, they wore the smart device for 1 min to collect physiological data including blood oxygen, respiratory rate, heart rate, and body temperature.

After the data were acquired, the signal data were transferred through the Respiratory Health Research app to the research-specific platform.

Statistical Analysis

Continuous variables were tested for normality using the Kolmogorov–Smirnov test. Data with normal distribution were presented as mean±standard deviation (SD). Data with non-normal distribution were analyzed using the Mann–Whitney U test and presented as median (interquartile range (IQR)). Categorical variables were analyzed using Pearson’s chi-square test or Fisher’s exact test. A two-sided P-value <0.05 was considered statistically significant. Kappa coefficients were obtained, and statistical analysis of variables was performed using IBM SPSS Statistics, version 26.0 (SPSS Inc, Chicago, IL, USA).

The sensitivity and specificity were calculated based on the interpretation of the smart device compared to the physician’s diagnosis. 95% confidence intervals (CIs) were calculated using MedCalc 19.0.4 (MedCalc Software BVBA, Ostend, Belgium). ROC curve was pictured by Python 3.10.5（Python Software Foundation）.

Creation of the pulmonary infection algorithm (training dataset)

In all, 87 patients diagnosed with pneumonia and 409 asymptomatic healthy controls were recruited. Patients’ demographic statistics are presented in Table 1. Their symptoms and complications are presented in Table 2. In the training set, 2 patients reported abdominal distension and chest pain, and 2 patients in the validation set reported stomach ache and dizziness; 17 patients had no symptoms at all.

Table 1 Demographic Data (Training Dataset)

Characteristic	N	Value(Mean±SD)
Pneumonia Patients	87
Male	56
Female	31
Age	87	58.82±11.94
Height (cm)	83	167.07±7.40
Weight (kg)	83	67.46±11.60
BMI (kg/m²)	83	24.06±3.14
Hospital Days	87	13.15±5.64
Healthy Controls	409
Male	219
Female	190
Age	409	46.56±19.21
Height（cm）	379	166.76±9.00
Weight（kg）	376	62.89±10.63
BMI (kg/m²)	425	22.54±2.78

Table 2 Symptoms and Complications in Pneumonia Patients

Symptoms	N=87 (TD)		N=80 (VD)
Fever		10	13
Cough		50	41
Chill		4	6
Tachypnea		17	12
Sore Throat		7	10
Headache		4	5
Inappetence		8	8
Muscle Soreness		2	7
Nausea and Vomiting		4	4
Diarrhea and Stomach ache		0	5
Runny Nose, Sneezing, or Stuffed Nose		1	7
Fatigue		12	10
Sputum		50	44
Affecting Daily Life		54	45
Other symptoms		2	2
Complications		87	80
Lung Cancer		20	15
Obstructive Pulmonary Disease		5	5
Emphysema or Bullae		7	7
Kidney Dysfunction		2	4
Rheumatic Immune Disease		8	5
Bronchiectasis		12	7
Pulmonary Interstitial Disease		14	7
Asthma		3	4
Sleep Apnea		2	0
Nasal Sinusitis		4	4
Cardiovascular Disease		25	14
Hypertension		13	19
Mellitus Diabetes		20	9
Gastroesophageal Reflux		22	13
Leukopenia		11	9
Thrombocytopenia		4	8
Leukemia		1	1

TD: Training Dataset; VD: Validation Dataset

Validation of Pulmonary Infection Algorithm (Validation Dataset)

After the algorithm was developed, it was further validated in 165 newly recruited participants, including 80 patients with pulmonary infection (54 males, 26 females) and 85 healthy volunteers (38 males, 47 females). Among these, 25 were asymptomatic. In some patients (n=60) and healthy volunteers (n=72), we collected physiological data from two smart devices twice. Thus, a total of 297 sets of valid data were collected. The overall accuracy of the cough sound algorithm (Algo-CS) was 82.6%, the sensitivity was 83.57%, and the specificity was 81.53%. The overall accuracy of the physiological parameter algorithm (Algo-PP) was 68.0%, the sensitivity was 37.86%, and the specificity was 98.09%. The overall accuracy of the complete algorithm (Algo-CSPP) was 85.9%, the sensitivity was 81.43%, and the specificity was 90.45% (Figures 4–6, Tables 4–6).

Table 3 Participants’ Demographic Data (Validation Set)

Characteristic	N	Value
Pneumonia Patients	78
Male	52
Female	26
Age	78	53.32±15.82
Height (cm)	74	168.08±7.73
Weight (kg)	74	67.41±9.64
BMI (kg/m²)	76	23.89±3.34
Hospital Days	80	14.00±6.68
Healthy Control	86
Male	38
Female	47
Age	86	36.09±12.06
Height (cm)	86	164.99±7.55
Weight (kg)	86	60.03±9.84
BMI (kg/m²)	86	21.96±2.65

Figure 4 ROC Curve of Algo-CS

Table 4 Criterion Values and Coordinates of the Algo-CS ROC Curve

AUC	95%CI	Sensitivity	95%CI	Specificity	95%CI	Youden Index J	P	Z statistic
0.826	0.777–0.867	83.57%	76.4–89.3	81.53%	74.6–87.3	0.6510	＜0.0001	14.731

Figure 5 ROC Curve for Algo-PP

Table 5 Criterion Values and Coordinates of the Algo-PP ROC Curve

AUC	95%CI	Sensitivity	95%CI	Specificity	95%CI	Youden Index J	P	Z statistic
0.680	0.623–0.732	37.86%	29.8–46.4	98.09%	94.5–99.6	0.3595	＜0.0001	8.443

Figure 6 ROC curve of Algo-CSPP

Table 6 Criterion Values and Coordinates of the Algo-CSPP ROC Curve

AUC	95%CI	Sensitivity	95%CI	Specificity	95%CI	Youden Index J	P	Z statistic
0.859	0.815–0.897	81.43%	74.0–87.5	90.45%	84.7–94.6	0.7187	＜0.0001	17.738

Primary Outcome

To the best of our knowledge, this was the first prospective study in China of screening for adult pulmonary infection based on wearable device data. In our study, the physiological parameters of cough sound, heart rate, HRV, respiratory rate, oxygen saturation, respiratory rate, and body temperature were monitored to detect possible pulmonary infection. We used physiological data collected at night and data measured at a single point during the day to establish and verify the screening algorithm model. The model achieved 85.9% accuracy, 81.43% sensitivity, and 90.45% specificity, indicating sufficient accuracy for screening LTRI. Because the watch is available on the market, we are now recruiting a large-scale population to further verify the accuracy of the screening algorithm.

In our study, 17 patients in the training dataset and 25 patients in the validating dataset lacked symptoms of pulmonary infection, which posed a challenge to the traditional diagnosis of pneumonia. Among symptomatic patients (Table 2), the most common symptoms were cough and expectoration, in 50 cases, followed by dyspnea and fatigue. Few patients had fever in either the training dataset or the validation dataset. This may be due to the features of the immune status of the patients and may have reflected the concealment of pneumonia. Thus, body temperature did not play an important part in our algorithm model.

As cough is among the most important symptoms of LRTI, we used cough sound in an independent algorithm (Algo-CS) and found that its sensitivity and specificity can reach 83.57% and 81.53%, respectively. The results may be due to two facts: the control group in this study were all healthy volunteers, and 50 patients in the training dataset had cough symptoms, as did 41 patients in the validating dataset. The present understanding of cough sound is currently limited by human auditory sensitivity, with distinguishable sound usually falling within the limits of a 20 Hz to 20 kHz range. Cough sound contains important information on the lower respiratory tract. Cough sound power and energy correlate strongly with physiological measures and subjective perception of cough strength [14]. When lung lesions occur, such as in lung consolidation, lung tissue edema, airway obstruction due to increased secretion, and so forth, these factors can affect the ability of the airway to transmit airflow, thus changing the acoustic features of the cough sound in both the time and frequency domains. Children’s cough sound has been identified as very practical for screening pneumonia in children and distinguishing the severity of asthma [15–17]. Cough sound analysis had also been used to distinguish COVID-19 patients [18], COPD, and congestive heart failure [19]. Our study did not exclude patients with pulmonary lesions other than pneumonia, such as tumors or fibrosis, which themselves may impact cough sound. Therefore, the ability to screen cough sounds may be affected and disturbed. Follow-up should be undertaken to further verify other respiratory diseases that have cough characteristics, such as cough variant asthma, chronic obstructive pulmonary disease, pulmonary fibrosis, and so on.

In addition to cough sound, a combination of other physiological parameters is used to screen for disease. Subtle changes in other physiological parameters, such as heart rate, blood oxygen, and respiratory rate, may not be recognized clinically, but wearable devices can help monitor and analyze them. Generally, wearable devices contain an accelerometer, a gyroscope, a photoplethysmography apparatus, a negative temperature coefficient thermistor (which, together, detect activities such as heart rate, oxygen saturation, skin temperature, and so forth), and other tools. The monitoring and analysis of 5700 patients hospitalized for COVID-19 [20] showed the potential value of changes in RHR as early markers of COVID-19 infection: at admission, the proportion of patients with heart rate > 100 BPM (43.1%) was higher than that of patients with fever symptoms (30.7%). In the early stages of the disease, this slight change is likely to move the time of intervention forward to avoid serious disease consequences. In other studies of the early diagnosis of COVID-19 using wearable devices [21], key features included changes in sleep duration, total step count, Galvanic skin response, SpO₂, blood pressure, HR/HRV, respiratory rate, self-reported symptoms, and cough frequency. The accuracy of the algorithmic models used to detect COVID-19 varies greatly (20–88%), but they still show promising prospects. In our study, a separate screening algorithm was established that used only physiological parameters. Although the specificity of screening for pulmonary infection was high, reaching 98.09%, the sensitivity was very poor, at 37.86%. This shows that while the change was significant, its sensitivity in disease identification was insufficient. This may be related to individuals’ specific physiological patterns, such as heart rate and sleep, as has previously been reported [22–23].

This study had numerous limitations. First, the inclusion criteria used to identify pulmonary infection patients were not strict. The patients whose data were used to establish the algorithm generally exhibited more than one complication, most commonly cardiovascular disease, followed by gastroesophageal reflux, lung cancer, and diabetes mellitus. In addition, many patients had interstitial lung disease, bronchiectasis, COPD, and rheumatic immune disease. Previous studies have indicated that complications may be risk factors for pneumonia [24–25]. On the other hand, complications may affect physiological indicators, such as heart rate, blood oxygen, and respiratory rate, eventually causing deviation in the algorithm.

The sample size of patients with pulmonary infection was small. Although we had a larger set of healthy volunteers, the relatively small size of the training dataset may have introduced bias to the algorithm. Furthermore, this study did not incorporate baseline data from the patients; instead, healthy volunteers were used as controls. These are both widely used comparison methods, but the lack of control data for the patient group may have increased the individual bias of this study.

Third, although we collected symptoms of pneumonia patients in a questionnaire because the volunteers were asymptomatic, it might have been better to add symptoms to the algorithm to distinguish pneumonia, as was done in a previous study [26]. In the future, we intend to carry out a validation study on patients with respiratory disease symptoms and improve the ability of the algorithm to identify LRTI in combination with symptoms and physiological parameters.

Finally, all of the patients with pulmonary infection recruited in this study were inpatients, and changes in activities were not included because their activity scopes were restricted to wards or hospitals, which was different from the pattern in daily life. Some studies have reported that behavior changes in patients may also help predict the occurrence of diseases [27].

Future Perspectives

The world and the field of medicine have changed forever due to the repercussions of the COVD-19 pandemic. The vast data provided by smart devices had help us with controlling such epidemic [28–29]. Although wearables cannot replace examination with medical devices, they may provide sufficient accuracy to provide an approximate assessment of an individual’s condition [30]. The technology of wearable devices to measure various physiological parameters has significantly matured in recent years. Through cough sound, artificial intelligence has enabled us with the ability to detect and diagnose different respiratory diseases [31]. Further, they have the potential to help health care providers and patients themselves better track their health outside regularly scheduled clinical visits, aiding rehabilitation and medication regimens. Consequently, screening by wearables may become the first step in the management of diseases. In future work, we plan to further validate the accuracy of the system in a real-world setting and conduct follow-ups with patients. The data provided by such devices will also allow clinicians to provide patients with personalized tools and tailored solutions to improve their health moving forward.

The results of this study indicate the possibility of using wearable devices for the screening and the early identification of lung infection, as distinct from methods of diagnosis of lung infection. The algorithm model developed, which combined cough sounds and physiological parameters, can improve the accuracy of pulmonary infection screening. It can also be used for large-scale screening of respiratory infectious diseases.

Ethical statement

This study was performed according to the Declaration of Helsinki. The study protocol was approved by the Ethics Committee of the Chinese PLA General Hospital (Approval No. S2021-663-01). All participants provided written informed consent.

Acknowledgments

This study was financially supported by the China Key Scientific Grant (Grant No. 2021YFC0122500). HUAWEI (Huawei Device Co., Ltd.) provided the smart device and algorithm model for research purposes.

Authors’ Contributions

YB Chen collected and analyzed the data, and drafted the manuscript. D Li helped with data collection. DY She and YT Guo recruited the patients, conducted the examination, and made the diagnoses. LX Xie supervised the study. WJ Chen and J Li analyzed the data and built the algorithm model. All of the authors read and approved the final version of the manuscript. All authors contributed to the analysis, drafting, and revising of the article, agreed on the journal for submission, gave final approval of the version to be submitted, and agreed to be accountable for all aspects of the work.

Conflict of Interest

The authors declare that there are no conflicts of interest to report.

GBD 2019 Diseases and Injuries Collaborators. Global burden of 369 diseases and injuries in 204 countries and territories, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019. Lancet. 2020 Oct 17;396(10258):1204–1222.
Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980–2017: a systematic analysis for the Global Burden of Disease Study 2017
Judd W.R., Stephens D.M., Kennedy C.A. Clinical and economic impact of a quality improvement initiative to enhance early recognition and treatment of sepsis. Ann Pharmacother. 2014;48(10):1269–1275.
Singer M., Deutschman C.S., Seymour C.W., Shankar-Hari M., Annane D., Bauer M. The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) JAMA. 2016;315(8):801.
Hirten RP, Danieletto M, Tomalin L, et al. Use of Physiological Data From a Wearable Device to Identify SARS-CoV-2 Infection and Symptoms and Predict COVID-19 Diagnosis: Observational Study. J Med Internet Res. 2021 Feb 22;23(2):e26107. doi: 10.2196/26107. PMID: 33529156; PMCID: PMC7901594.
Mishra T, Wang M, Metwally AA, et al. Pre-symptomatic detection of COVID-19 from smartwatch data. Nat Biomed Eng. 2020 Dec;4(12):1208–1220.
Natarajan A, Su HW, Heneghan C. Assessment of physiological signs associated with COVID-19 measured using wearable devices. NPJ Digit Med. 2020 Nov 30;3(1):156.
Lonini L, Shawen N, Botonis O et al. Rapid Screening of Physiological Changes Associated With COVID-19 Using Soft-Wearables and Structured Activities: A Pilot Study. IEEE J Transl Eng Health Med. 2021 Feb 11;9:4900311.
Griffin MP, Lake DE, Moorman JR. Heart rate characteristics and laboratory tests in neonatal sepsis. Pediatrics. 2005;115:937e941.
Griffin MP, Moorman JR. Toward the early diagnosis of neonatal sepsis and sepsis-like illness using novel heart rate analysis. Pediatrics. 2001 Jan;107(1):97–104.
Griffin MP, O'Shea TM, Bissonette EA, Harrell Jr FE, Lake DE, Moorman JR. Abnormal heart rate characteristics preceding neonatal sepsis and sepsis-like illness. Pediatr Res. 2003;53:920 e926.
Originals, H.C. Solutions. ADAMM Helps You Understand and Monitor Your Asthma More Easily; 2017. Available from: http://healthcareoriginals.com/solutions/#adamm-rsm.
E. Naydenova, A. Tsanas, C. Casals-Pascual and M. De Vos, "Smart diagnostic algorithms for automated detection of childhood pneumonia in resource-constrained settings," 2015 IEEE Global Humanitarian Technology Conference (GHTC), 2015, pp. 377–384.
Lee KK, Matos S, Ward K, Rafferty GF, Moxham J, Evans DH, Birring SS. Sound: a non-invasive measure of cough intensity. BMJ Open Respir Res. 2017 May 12;4(1):e000178.
Abeyratne UR, Swarnkar V, Triasih R, Setyati A. Cough sound analysis - a new tool for diagnosing pneumonia. Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:5216-9. doi: 10.1109/EMBC.2013.6610724. PMID: 24110911.
Enseki M, Nukaga M, Tadaki H, et al. Cough sound analysis can rapidly diagnose childhood pneumonia. Ann Biomed Eng. 2013 Nov;41(11):2448–62.
Swarnkar V, Abeyratne U, Tan J, et al. Stratifying asthma severity in children using cough sound analytic technology. J Asthma. 2021 Feb;58(2):160–169.
Laguarta J, Hueto F, Subirana B. COVID-19 Artificial Intelligence Diagnosis Using Only Cough Recordings. IEEE Open J Eng Med Biol. 2020 Sep 29;1:275–281.
Windmon A, Minakshi M, Bharti P, Chellappan S, Johansson M, Jenkins BA, Athilingam PR. TussisWatch: A Smart-Phone System to Identify Cough Episodes as Early Symptoms of Chronic Obstructive Pulmonary Disease and Congestive Heart Failure. IEEE J Biomed Health Inform. 2019 Jul;23(4):1566–1573.
Richardson, S. et al. Presenting characteristics, comorbidities and outcomes among 5,700 patients hospitalized with COVID-19 in the New York City area. JAMA 323, 2052–2059 (2020).
Mitratza M, Goodale BM, Shagadatova A, et al. The performance of wearable sensors in the detection of SARS-CoV-2 infection: a systematic review. Lancet Digit Health. 2022 May;4(5):e370-e383.
Quer G, Gouda P, Galarnyk M, Topol EJ, Steinhubl SR. Inter- and intraindividual variability in daily resting heart rate and its associations with age, sex, sleep, BMI, and time of year: Retrospective, longitudinal cohort study of 92,457 adults. PLoS One. 2020 Feb 5;15(2):e0227709.
Jaiswal SJ, Quer G, Galarnyk M, Steinhubl SR, Topol EJ, Owens RL. Association of Sleep Duration and Variability With Body Mass Index: Sleep Measurements in a Large US Population of Wearable Sensor Users. JAMA Intern Med. 2020 Dec 1;180(12):1694–1696. doi: 10.1001/jamainternmed.2020.2834. PMID: 32926073; PMCID: PMC7490746.
Almirall J, Serra-Prat M, Bolíbar I, Balasso V. Risk Factors for Community-Acquired Pneumonia in Adults: A Systematic Review of Observational Studies. Respiration. 2017;94(3):299–311. doi: 10.1159/000479089. Epub 2017 Jul 25. PMID: 28738364.
Mandell LA, Niederman MS. Aspiration Pneumonia. N Engl J Med. 2019 Feb 14;380(7):651–663.
Quer G, Radin JM, Gadaleta M, et al. Wearable sensor data and self-reported symptoms for COVID-19 detection. Nat Med. 2021 Jan;27(1):73–77.
Cleary JL, Fang Y, Sen S, Wu Z. A Caveat to Using Wearable Sensor Data for COVID-19 Detection: The Role of Behavioral Change after Receipt of Test Results. medRxiv [Preprint]. 2021 Apr 22:2021.04.17.21255513.
S. J. Alsunaidi, A. M. Almuhaideb, N. M. Ibrahim, et al. ‘‘Applications of big data analytics to control COVID-19 pandemic,’’ Sensors, vol. 21, no. 7, p. 2282, Mar. 2021.
F. Alhaidari, A. Almuhaideb, S. Alsunaidi, et al. ‘‘E-triage systems for COVID-19 outbreak: Review and recommendations,’’ Sensors, vol. 21, no. 8, p. 2845, Apr. 2021.
Nemcova A, Jordanova I, Varecka M, et al. Monitoring of heart rate, blood oxygen saturation, and blood pressure using a smartphone. Biomed Signal Process Control 2020; 59: 101928.
Alqudaihi KS, Aslam N, Khan IU et al. Cough Sound Detection and Diagnosis Using Artificial Intelligence Techniques: Challenges and Opportunities. IEEE Access. 2021 Jul 15;9:102327–102344.

Supplement 1 Pulmonary Infection Symptomatic Questionnaire

Patient ID:_________
Symptoms
	□Yes □No
Cough	□Yes □No
Chill	□Yes □No
Tachypnea	□Yes □No
Sore Throat	□Yes □No
Headache	□Yes □No
Inappetence	□Yes □No
Muscle Soreness	□Yes □No
Nausea and Vomiting	□Yes □No
Diarrhea and Stomach ache	□Yes □No
Runny Nose, Sneezing, or Stuffed Nose	□Yes □No
Fatigue	□Yes □No
Sputum	□Yes □No
Affecting Daily Life	□Yes □No
Other Symptoms	□Yes______ □No

(Not answered)

Download PDF

Version 1

posted

You are reading this latest preprint version

Respiratory Health Study: Pulmonary Infection Screening Using Wearable Sensor Data

Status:

Version 1

Abstract

Figures

Background

Methods

Results

Discussion

Primary Outcome

Limitations

Future Perspectives

Conclusion

Declarations

References

Supplement

Additional Declarations

Status:

Version 1