Modern Machine-Learning Predictive Models for Diagnosing Infectious Diseases.

Controlling infectious diseases is a major health priority because they can spread and infect humans, thus evolving into epidemics or pandemics. Therefore, early detection of infectious diseases is a significant need, and many researchers have developed models to diagnose them in the early stages. This paper reviewed research articles for recent machine-learning (ML) algorithms applied to infectious disease diagnosis. We searched the Web of Science, ScienceDirect, PubMed, Springer, and IEEE databases from 2015 to 2022, identified the pros and cons of the reviewed ML models, and discussed the possible recommendations to advance the studies in this field. We found that most of the articles used small datasets, and few of them used real-time data. Our results demonstrated that a suitable ML technique depends on the nature of the dataset and the desired goal. Moreover, heterogeneous data could ensure the model's generalization, while big data, many features, and a hybrid model will increase the resulting performance. Furthermore, using other techniques such as deep learning and NLP to extract vast features from unstructured data is a powerful approach to enhancing the performance of ML diagnostic models.

Non-communicable diseases among Palestinian refugees from Syria: a cross-sectional study on prevalence, case management, access to and utilisation of UNRWA Health Services.

BACKGROUND: As of Feb 14, 2014, UNRWA had registered almost 53 000 Palestinian refugees from Syria (PRS) who had fled to Lebanon as the result of the conflict in Syria. Half of the PRS had gone to one of the 12 Palestinian camps, which are overcrowded and of poor infrastructure. Consequently, there is concern for the wellbeing of PRS; in particular, their health status and access to medical care. Little attention has been given to non-communicable diseases (NCDs) in the acute phases of emergencies. Therefore, an assessment of the prevalence of NCDs among PRS, as well as the patterns of use of available health care services by PRS, is warranted. METHODS: A cross-sectional study was conducted in April, 2018, with 1100 PRS residing inside and outside refugee camps across all governorates of Lebanon. A listing of all PRS families was the sampling frame. A random sample of families was selected and contacted, and then one adult randomly selected from each family was approached for data collection. Pregnant women and participants who were too ill to participate were excluded. After obtaining informed verbal consent, we did face-to-face interviews to collect data on household details (such as type of settlement, source of income) and sociodemographic information, major NCDs (for the household representative), lifestyle behaviours, and health-care use. We invited all participants to UNRWA clinics for physical and biochemical measurements. The study protocol was approved by the Institutional Review Board of the American University of Beirut. FINDINGS: We surveyed 959 PRS (59% male [465], 82% married [785], mean age 43 years [SD 12]). A quarter of those interviewed had at least one NCD; the most prevalent were hypertension (23%; 221 of 959), rheumatic diseases (17%; 166), cardiovascular diseases (CVDs, 13%; 126), diabetes (13%; 124), and chronic respiratory diseases (CRDs) (10%; 100). All these NCDs were more prevalent among PRS inside camps than in those residing outside camps, except for diabetes. Most participants who had been diagnosed with NCDs were adhering to their prescribed medications (90-98%). However, of those reporting CVDs, only 56% (71 of 126) had attended at least one follow-up appointment, and of those reporting rheumatic diseases, only 33% (55 of 166) had attended at least one follow-up appointment. About half of participants reported that they checked their blood pressure (55%; 528 of 959) or blood glucose (45%; 430). 111 of 221 (50%) participants with hypertension monitored their blood pressure, and 78 of 124 (63%) participants with diabetes monitored their blood glucose. 133 participants attended UNRWA clinics for measurements; 40% (54) had obesity (>30 kg/cm2), 10% (13) had elevated blood pressure, 12% (16) had stage 1 hypertension, and 8% (10) had stage 2 hypertension. Most participants had normal glucose (67%; 89 of 133), cholesterol (65%; 87), triglyceride (58%; 77), and glycosylated haemoglobin levels (64; 85). A substantial proportion of participants who were tested had undiagnosed diabetes (14%; 33 of 108 reporting no diabetes), undiagnosed hypertension (23%; 19 of 81), uncontrolled diabetes (79% of participants with diabetes; 19 of 24), or uncontrolled hypertension (64% of participants with hypertension; 29 of 45). INTERPRETATION: Further study is needed to understand why the prevalence of NCDs among PRS residing in Palestinian camps is higher than among those living outside, and to understand whether and why access to medicines is a problem, particularly outside camps. The burden of NCDs among PRS is high and their access to services is not optimal; therefore UNRWA should pay special attention to NCD services in this population. UNRWA should invest in efforts to increase awareness of free blood pressure and blood glucose monitoring services in its clinics, and could actively offer free testing in public areas inside camps. Doctors at UNRWA clinics should recommend that patients monitor their disease more frequently and educate them on how to do so. A limitation of the study was the low percentage of participants who attended UNRWA clinics for physical and biochemical measurements. FUNDING: UNRWA.