algorithms

Article
A Fair and Safe Usage Drug Recommendation System in
Medical Emergencies by a Stacked ANN
Usharani Bhimavarapu 1 , Nalini Chintalapudi 2 and Gopi Battineni 3, *

1 School of Competitive Coding (SOCC), Koneru Lakshmaiah Education Foundation, Vaddeswaram,

Vijayawada 522502, India; [email protected]
2 Informatics Centre, School of Science and Technology, University of Camerino, 62032 Camerino, Italy;
[email protected]
3 Clinical Research Center, School of Medicinal Health Products Sciences, University of Camerino,
62032 Camerino, Italy
* Correspondence: [email protected]; Tel.: +39-33-3172-8206

Abstract: The importance of online recommender systems for drugs, medical professionals, and hos-
pitals is growing. Today, the majority of people use online consultations for drug recommendations
for all types of health issues. Emergencies such as pandemics, floods, or cyclones can be helped by the
medical recommender system. In the era of machine learning (ML), recommender systems produce
more accurate, quick, and reliable clinical predictions with minimal costs. As a result, these systems
maintain better performance, integrity, and privacy of patient data in the decision-making process
and provide precise information at any time. Therefore, we present drug recommender systems with
a stacked artificial neural network (ANN) model to improve the fairness and safety of treatment for
infectious diseases. To reduce side effects, drugs are recommended based on a patient’s previous
health profile, lifestyle, and habits. The proposed system produced results with 97.5% accuracy.
A system such as this could be useful in recommending safe medicines to patients, especially during
health emergencies.
Citation: Bhimavarapu, U.;
Chintalapudi, N.; Battineni, G. A Fair Keywords: deep learning; safe drugs; pandemics; recommender systems; a medical emergency
and Safe Usage Drug Recommendation
System in Medical Emergencies by a
Stacked ANN. Algorithms 2022, 15,
186. https://doi.org/10.3390/ 1. Introduction
a15060186
Online consultations require the patient to describe their symptoms to the doctor.
Academic Editor: Frank Werner A spike in virtual medical services has been reported in the wake of the novel coronavirus
disease (COVID-19) [1]. Diabetes, hypertension, and heart disease are all associated with
Received: 27 April 2022
Accepted: 25 May 2022
an increased risk of virus infections. The availability of health care professionals 24/7,
Published: 27 May 2022
no need for travel, security, privacy, and drug recommendations are all advantages of
virtual medical services. The recommender system allows for improvements in medical
Publisher’s Note: MDPI stays neutral services in disparate areas [2]. Often, finding a physician in remote areas can be tricky, so
with regard to jurisdictional claims in
recommender systems have been created to help.
published maps and institutional affil-
Health-related recommender systems can make an early diagnosis, predict disease
iations.
progression, and make appropriate recommendations according to the health status of
patients [3,4]. Machine learning (ML) greatly improves the quality of medical recommender
systems by providing suggestions that are based on patient needs and feedback [5,6].
Copyright: © 2022 by the authors.
By using sentiment analysis and feature engineering, the drug recommender system can
Licensee MDPI, Basel, Switzerland.
dispense medicine according to a specific condition. Emotions, such as attitudes and
This article is an open access article opinions, are separated and extracted from language through sentiment analysis [7].
distributed under the terms and By using the recommender system, information overload can be solved, and e-
conditions of the Creative Commons government and e-learning can be improved [8]. Depending on an individual’s health
Attribution (CC BY) license (https:// status, these recommender systems prescribe medications, diagnose diseases, and refer
creativecommons.org/licenses/by/ them to the relevant health care. An ML-driven recommendation system generates ap-
4.0/). propriate recommendations using parameters such as blood pressure, gender, cholesterol

Algorithms 2022, 15, 186. https://doi.org/10.3390/a15060186 https://www.mdpi.com/journal/algorithms

Algorithms 2022, 15, 186 2 of 11

levels, and blood sugar for diseases such as colds, fevers, and cardiac deaths [9]. The
healthcare system built on the Internet of Things (IoT) coupled with an oncology interface
has provided nutrition information to individuals [10].
Depending on the patient’s medical history, a decision support system can assist a doc-
tor in prescribing a drug. In contrast, the recommendation system suggests the same based
on an analysis of previous usage patterns [11]. Four types of recommender systems exist,
including content-driven filtering, collaborative filtering, knowledge-driven recommender
systems, and hybrid recommender systems [12,13]. Since the drug recommendation frame-
work includes medical terminology, such as infection names, side effects, and synthetic
names, only a limited number of papers are available.
In this work, we proposed the development of a drug recommender system (DRS) for
different diseases to maintain good patient health and longevity. We addressed the unfair-
ness in drug usage by DRS for severe chronic diseases by improving the recommendation
accuracy by the integration of ML knowledge. A further discussion was carried out on how
the proposed DRS integrates the person’s health profile and automation of meditation, and
drug dosages. The system performance was calculated based on different metrics such as
accuracy, sensitivity, and specificity. The performance was further compared with other
existing ML models to validate its efficiency.

2. Related Work
From the existing literature, different health recommender systems (HRS) are available.
Collaborative filtering utilizes past user behavior to examine similar profiles and determine
preferences to make clear recommendations. A hospital recommendation system was
proposed by Fedelucio et al. [14] based on the treatments, consulted physicians, hospitals,
and patient health indicators of a patient. An alternative hybrid recommender system
based on available information on family doctors and available patients was suggested [15].
Various HRS help to support medical treatment and prognosis [16]. Recommendations
made on content-based filtering are dependent on specific features only. Different features
selected using rough set feature reduction can predict diabetes [17]. Content-driven models
are used to evaluate radial doses and weights for elements in cancer treatments [18]. It is
reported that content-based models achieve a better performance than traditional models
in predicting the risk of heart attack [19].
A model called iCARE uses collaborative filtering and hybrid learning to predict
disease risk based on a patient’s previous illnesses [20]. The risks of delivery for pregnant
women can be predicted using a collaborative filtering algorithm that includes Mahalanobis
distance and fuzzy membership [21]. Ontologies and methods of problem-solving are
fundamental components of knowledge-based systems [22]. Based on the knowledge
of users and products, knowledge-based filtering selects products that are suitable for
users [23]. Meanwhile, hybrid systems combine different filtering approaches [24].
Demographic filtering offers recommendations based on demographic data such as
age, gender, nationality, and residency [25]. In medical emergencies such as the COVID-19
pandemic, older people have a higher risk of complications and contracting serious illnesses
if they are untreated. Through information filtering, the HRS can handle such emergencies
by collecting patient messages and recommending treatment [26]. With the help of the
patient’s demographic information, these messages for smoking cessation users used hybrid
filtering to assess similarity.
A semantic web is a fast-evolving technology that utilizes a content-based recommen-
dation system with machine-readable annotations [27]. The social-based filtering algorithm
considers information about an individual’s neighborhood, along with similar tastes [28].
To prescribe the most appropriate treatment to patients, semantic clustering assesses the
similarities between records, taking into account the patient’s demographics, location, and
medical complications [29].
The DRS offers medicine based on patient reviews using sentiment analysis and
feature engineering. The risk level classification identifies a patient’s immune system and
Algorithms 2022, 15, 186 3 of 11

recommends medicines if the patient has a low immune system [30]. Doulaverakis et al. [31]
proposed GalenOWL, a semantic-driven online framework with the help of a specialist to
manage drug recommendations based on the past profile of the patient. By considering
worldwide standards such as ICD-10 and UNII, this framework converts clinical data and
drug interactions to ontological terms. Cloud-assisted drug recommendation (CADRE)
also considers the patient’s side effects and shifts to the cloud to advance the quality of
the patient’s experience [32]. No particular DRS system was developed for the COVID-19
emergency. Therefore, we aimed to develop a DRS modeling framework by incorporating a
stacked artificial neural network (ANN) for the fair and safe usage of drugs in pandemics.

3. Methods and Materials

3.1. Dataset
We prepared the drug selection dataset for the COVID-19 treatment from different
sources including drug banks, news reports, and the existing literature [33–37]. Primarily,
potential drugs recommended for COVID-19 by the World Health Organization (WHO)
including Remdesivir, Umifenovir, acetaminophen, and Favipiravir were considered. Later,
the data from studies [34–37] helped us to create interactions between the drugs and the
collected clinical data. Other demographic patient information including gender, age,
height, weight, exercise habits, country, food habits, COVID-19 infected data, and the
co-morbidities were collected and are presented in Table 1. The incomplete or missing
data columns were excluded from a given dataset. Patient symptoms based on individual
questionnaires and lab reports were collected and drug categorization was completed
for the drug using the stacked ANN. The recommendation of antibacterial drugs was
completed by mapping the patient’s health history.

Table 1. Features of the lifestyle and health status of a person.

Feature Values
Gender Male, Female
Age child, young, adult, old (1–65)
Height In cm
Weight In kg
Comorbidities Diabetes, hypertension, etc.
COVID-19 infection Yes or no
Exercise habits Yes or no
Test reports Diagnosis reports
Country Country
Food Veg or nonveg
Habits Tea, smoking, alcohol, etc.

3.1.1. Data Pre-Processing

The symmetric uncertainty feature selection measure was applied to find the associa-
tion between different features in the feature space. Under the candidate feature (fi ) we
evaluated the information shared between the selected feature (fs ) and fi . The relevance of
the class of the independent features was measured by:
I(f ,f )
Symmetric uncertainty = 2 × E(f )+i Es (f ) ; here, I is the mutual information and E is the
i s
entropy of the features.
The entropy of fi is calculated by Entropy(fi ) = −(p(0)× log(p(0)) + p(1)× log(p(1)))
P(i,s)
I(fi , fs ) = ∑i∈I ∑s∈S P(i, s) log P(i)P(s) ; Here i ∈ I, s ∈ S are the possible values of I and
S, respectively; P(i) and P(s) signify the distribution of I and S, and P(i,s) signifies the
joint distribution.
Algorithms 2022, 15, 186 4 of 11

3.1.2. Symptom Extraction and Severity Rating

We divided the survey data into parts of speech to extract the symptoms, and the
extracted words were mapped to the disease dictionary with the symptoms and drugs. The
dictionary of medical terms was adopted from the Systematized Nomenclature of Medicine
and Clinical Terms (SNOWMED-CT) [38,39]. The mapping of the corresponding symptom
entities was completed using the infection severity. The infection severity was estimated
under the guidance of the pharmacist.
0 0 0
To standardize the feature Fp0 = (fp1 , fp2 , . . . , fpn ), we used the min–max scaling to
0 0
fpq −min(F ) 0
normalize the features using Fpq = ; where fpq is the qth rating specific to the
max(F0 )−min(F0 )
qth infection symptom in Fp0 , max F0 , min F0 are the maximum and the minimum ratings



 n
in F0 , F0 = Fp0 .
p=1

3.1.3. Drug Target

To create the drug labels, we used the categorized drug information and described
them based on the patient attributes. To measure the frequency (FREQ) of the occurrence
of the drug dp based on the symptom feature sp for all the cases:
qdp ,sp
FREQdp ,sp = qdp ; here FREQdp ,sp is the frequency of the drug (dp ) to the symptom
feature (sp ); qdp ,sp is the number of cases containing the dp and sp ; and qdp is the number
of cases containing the drug dp .
The drug dp can be represented as dp = {FREQd1 ,s1 , FREQd2 ,s2 , . . . , FREQdp ,sp }. The k-
means clusters were applied in drug categorization [40–42]. We assembled the information
about diseases and drug interactions for a better representation by:
Gdrd |R1 | ∑PeRt qP ; here Rt represents the association of drug (t) to drug set (b).
t

 The drug prediction was performed based on the drug correlation presented by


σ TGd ∑d Tdq xd ⊗ xq ; here σ is the activation function, ⊗ represents the element-wise
product, Tdq represents the correlation between drug d and drug q.
 The drugtarget aggregation
g
 g
operation associates a drug with a specific disease by
g
σ TGd ∑d Tdq xkd ⊗ xkq ; here xkd represents drug d after the g aggregation operation.
To aggregate the drug target information by aggregating the k layers by
(TGd ∑d Tds (xd ⊗ ht )); here t represents the target of the disease symptom in drug symp-
tom, ht represents the initialized symptom t.
The Artificial Neural Network (ANN) model was incorporated to perform the drug
selection based on the patient’s symptoms. When a new patient (pnew ) appears, the model
collects patient symptomatic data for a similarity check of the existing patient records. Then,
the training phase is performed and the symptom drug classifier is classified according to
the patients’ symptoms. Medications are displayed based on side effects and co-morbidities,
and a drug is chosen based on the drug attributes. This is analyzed by:
∑ni=1 Ai,new ∗Ai,old
q q
2
; here Ai,new are the features for the new cases and Ai,old
(∑1=1 Ai,new )2
n
( ∑ni=1 Ai,old)
represent the old cases.

3.2. Recommendation Algorithm

To suggest drugs for the specific disease, the DRS recommends antibacterial drugs
based on the individual’s past health status and present risk level. The matching of the
drug with the active individual features is completed using the following equation:
(fx −fx )(qfy −fy )
∑ x∈I q 2 2
; here fx is the feature set of the individual and x, fx is the
∑ x ( fx − fx ) ∑y (fy −fx )
mean over the set of features of I.
If the diseased individual has allergies, high blood pressure, and poor health, adverse
side effects of the drug may lead to death or morbidity [43]. The probability of the drug
side effect is calculated by:
Algorithms 2022, 15, 186 5 of 11

sx ∩ sy
Dx sx ∪sy
∑m
x=1,x6=q sx ∩sy ; here Sx and Sy are the side effects of the drug Dx , prediction score
∑m
x=1 sx ∪sy

= ϑk + (1 − ϑk )Σ √ϑk × √ϑk 2 , and ϑk is the average risk of all the diseased individuals
∑ v2k ∑ ϑk
with a risk factor of k.
The fair drug recommendation system takes into account health conditions, prefer-
ences, race, and gender. Based on the weighted binary singular value decomposition,
a stacked ANN is proposed. Figure 1 illustrates the framework for the proposed drug
recommendation system. A normal health condition or a worsened state is indicated by
the input parameter values. For the recommendation algorithm, the current state of a
parameter is crucial. Each parameter value can belong to a different class according to
the proposed technique. Every user has a unique health profile, which is compared to a
user who had a similar health condition in the past. Based on the user’s immune system
Algorithms 2022, 15, x FOR PEER REVIEW 5 of 11
and preferences, the stacked ANN model identifies the appropriate set of medications.
Our recommendations were based on a comparison of the individuals’ health profiles and
individual preferences with thoseAlgorithm
3.2. Recommendation of similar individuals. In Algorithm 1, all the individuals
with the same features are grouped into
To suggest drugs for theaspecific
recommendation cluster.
disease, the DRS recommends antibacterial drugs
based on the individual’s past health status and present risk level. The matching of the
drug
Algorithm 1. Drug with the active individual
recommendation algorithmfeatures is completed using the following equation:
̅ ̅
; here fx is the feature set of the individual and x, f̅x is the
(fx −fx )(fy −fy )
Input: Patient data ∑ 2 2
√∑ (fx −f̅x ) √∑ (fy −f̅x )
Output: Recommended drug
x∈I x y

mean over the set of features of I.

1. Categorize the users according to the filtered features, and cluster all the individuals that
If the diseased individual has allergies, high blood pressure, and poor health, adverse
have the same features.
side effects of the drug may lead to death or morbidity [43]. The probability of the drug
2. Selection ofside
the effect
similar cluster individuals
is calculated by: to the active individual
3. Calculate the drug features
m
s(i.e.,
x ∩sy
dosages, tolerance, smell, gas generation) of the active
Dx
sx Usy
individual by considering
∑ the
m health
sx ∩sy
; herestatus
Sx andand
Sy the userside
are the preferences.
effects of the drug Dx, prediction
∑ sx Usy
x=1,x≠q
n 
p (tu )−Pp (tu ) x=1
fp Σ ϑ(tu )∗d(u∗ ,p).i(tu )
S(d(tu )) ̅ k )Σ ϑkf ×areϑkthe
score=ϑ̅k + (1 −; ϑ
where , and ϑ̅k important
most is the average riskfeatures,
drug of all the diseased
np and individuals
Pp are the
m ( tu ) p
√∑v2
k √∑ϑ2
k
measurements ofwith the next
a riskand the
factor of past
k. health status, tu are the allergies, m(tu ) is the instances
count, ϑ(tu ) is the selected infectious
The fair features of the
drug recommendation individual
system tu , daccount
takes into (u∗ , p)health
is the conditions,
feature direction
prefer-
change, the rangeences,
of therace,
values
and is −1,0,1,
gender. i(tu )onis the
Based theweighted
magnitude of the
binary specified
singular valuefeature and
decomposition, a
S(d(tu )) is the duration.
stacked ANN is proposed. Figure 1 illustrates the framework for the proposed drug rec-
ommendation system. A normal health condition or a worsened state is indicated by the
4. Generate recommendations by calculating the individual’s health status with ∑u∈U ∑p∈P At,u,p
input parameter values. For the recommendation algorithm, the current state of a param-
5. Store the list of isthe
eter recommended
crucial. drugs
Each parameter upon
value canthe acceptance
belong of theclass
to a different user.according
If the individuals
to the pro-
reject the list of drugs
posed and dosages,
technique. Every userprovide themhealth
has a unique withprofile,
the alternative list of drugs
which is compared and who
to a user
dosages whichhad ahas beenhealth
similar followed by similar
condition individuals
in the past. Based onwho have been
the user’s immune assessed
systemusing the
and pref-
erences, the stacked
drug recommendation ANN model identifies the appropriate set of medications. Our rec-
algorithm.
6. Generate the ommendations were basedlists
list of recommended on aofcomparison
drugs andofdosages
the individuals’
based on health profiles and indi-
the individual’s
vidual
health status, preferences
lifestyle, with those preferences.
and individual of similar individuals. In Algorithm 1, all the individuals
with the same features are grouped into a recommendation cluster.

Figure 1. Block diagram for the proposed recommender system.

Figure 1. Block diagram for the proposed recommender system.
 4.1. Fairness Drug Recommendation for SARS-CoV2 I
Regression
Algorithms 2022, 15, 186
Calculating high prediction values involves 6 of 11
th
and choosing the highest prediction values. The co
errors
3.3. and
Software and the
Hardware threshold should be calculated. W
Specifications
The experiments were conducted on a PC with an Intel i9, 7890XE processor with
possible
18 physical and 36predictors
logical cores, 128 GB toof memory,
improve the 10fairness
and Windows Enterprise as ofthe dru
operating system. Anaconda IDE was used to write the Python code.
characteristics of the patient and the severity of th
4. Results
deviation
4.1. was applied
Fairness Drug Recommendation for SARS-CoV-2to each
Infectious diagnostic
Diseases feature
Using ML and Regression
Calculating high prediction values involves three steps including obtaining, filtering,
rachoric
and analysis
choosing the highest predictionwas used
values. The to between
correlation estimate the correla
the recommendation
errors and the threshold should be calculated. We used a statistical test to identify the
tures.
possible ThetoConway
predictors Maxwell
improve the fairness Poisson by
of drug recommendations regression
considering w
the characteristics of the patient and the severity of the disease. A threshold of one
acteristics
standard deviation wasandappliedthe
to each clinical
diagnostic featureevidence.
based on symmetric The Hausm
uncertainty.
Tetrachoric analysis was used to estimate the correlation between the binary covariant
change
features. in the
The Conway effectiveness
Maxwell Poisson regression was prediction
employed to identifyscore
the drug for th
characteristics and the clinical evidence. The Hausman test was also applied to assess the
Figure
change in the 2.
effectiveness prediction score for the individual and the drug, as shown
in Figure 2.

Figure 2. Prediction score.

4.2. Fairness of Drug Side-Effects Predictions Using Deep Learning and Regression
Figure 2. Prediction score.
Drug features were extracted to predict drug side effects associated with drug names
and clinical characteristics. A bilingual evaluation understudy metric was used to identify
the associated drug side effects. The following drugs are tabulated along with their side
effects in Table 2.
The selection of an adequate threshold is crucial to fine-tune the medical recommen-
dation process. It is recommended that the parameter range is defined as (0,1), where
0 indicates complete fairness and 1 indicates no fairness. An assessment of the average
error for the recommendations is necessary for a better scale of accuracy. We chose 0.4 as
the threshold value for the optimal selection, and 0.5 as the default parameter value. Table 3
summarizes the proposed drug recommender system with different hidden layers.
Algorithms 2022, 15, 186 7 of 11

Table 2. Predicted drugs for specific diseases with the side effects.

Drug Id Drug Name Side Effects Disease

Headache, nausea, loss of appetite, diarrhea,
DB00608 chloroquine Susceptible infections, SARS-CoV-2
stomach pain, rash, itching
Weakness, diarrhea, heartburn, weight loss, Human immune deficiency
DB01601 Lopinavir
headache, staying asleep, muscle pain virus, SARS-CoV-2
Drowsiness, diarrhea, gas, heartburn, headache,
DB00503 Ritonavir Human immune deficiency virus
numbness, burning, muscle and joint pain
DB12598 Nafamostat Lung swelling SARS-CoV-2 pneumonia
Abnormal liver, rash, nausea, diarrhea, increased
Kidney injury,
DB13729 Camostat potassium levels in the blood, itching, jaundice, low
SARS-CoV-2
blood platelets, and gas
DB00927 Famotidine Difficulty breathing, feeling sad, racing heartbeat Ulcers
DB13609 Umifenovir Allergic reactions Influenza and respiratory virus
DB00507 Nitazoxanide Stomach pain, headache, upset stomach, vomiting. Infections, anaerobic bacteria, viruses
Fever, itching, joint pain, rapid heartbeat, headache,
DB00602 Ivermectin swelling of eyes, diarrhea, dizziness, loss of appetite, SARS-CoV-2
and sleepiness
DB06273 Tocilizumab Respiratory infections, rashes, dizziness, sore throat SARS-CoV-2
DB11767 sarilumab Sore throat, cold scores, itching Rheumatoid-rheumatoid arthritis
DB00112 Bevacizumab Body aches, cracks in skin, difficulty breathing Cancer, SARS-CoV-2
Headache, dry mouth, feeling nervous, and Obsessive-compulsive
DB00176 Fluvoxamine
trouble sleeping disorder, SARS-CoV-2

Table 3. Performance of the stacked ANN with different hidden layers for the drug recommenda-
tion system.

Hidden Layers MAPE RMSE

1 0.0284 0.0018
2 0.0256 0.0014
3 0.0251 0.0010
4 0.0324 0.0017
5 0.0328 0.0019
6 0.0330 0.0020

The stacked ANN was implemented for a drug recommendation system with varying
hidden layers, and the error rate was compared as the number of hidden layers was
increased. A minimum error rate was observed when three hidden layers were used. To
evaluate the proposed models, the Relu activation function and Adam optimizer with
150 epochs and 32 batch sizes were used. Table 4 presents a comparison of the performance
estimates for the different models. The performance metrics were applied to evaluate the
drug recommendation performance. We observed that the proposed model performed
better than other traditional ML algorithms in terms of accuracy, precision, sensitivity,
and specificity.
Algorithms 2022, 15, 186 8 of 11

Table 4. Comparison of the performance metrics of machine learning-based recommender systems.

Recommender Model Accuracy Precision Sensitivity Specificity

Content-Based 0.847 0.842 0.862 0.897
Hybrid restricted Boltzmann machine 0.946 0.932 0.926 0.927
Random forest 0.841 0.840 0.841 0.920
K nearest neighbors 0.840 0.823 0.824 0.915
Support vector machine 0.719 0.714 0.719 0.860
Logistic regression 0.534 0.522 0.534 0.767
Decision Tree 0.840 0.840 0.835 0.920
DeerDr [35] 0.956 0.945 0.924 0.919
MLP [36] 0.946 0.945 0.917 0.916
Proposed 0.985 0.96 0.939 0.929

5. Discussion
For example, a DRS for migraine patients can help doctors write the appropriate and
accurate drugs for the patients based on their severity and importance [44]. The proposed
DRS consists of individuals who are 80% similar to the present diseased individual. An
additional system for diabetic patients using collaborative filtering can recognize patients
that closely match the active patient by considering features such as insulin, glucose,
body mass index, and blood pressure [45]. By using information about a patient’s profile,
combined with ontologies and rule-based decision making, these systems can recommend
anti-diabetes medicines with dose restrictions [46].
A patient with COVID-19 and susceptible virus-related fatigue was treated with
chloroquine, as reported in [47]. Lopinavir significantly decreased the incidence of ARDS
in patients with SARS-CoV-2 infection [48]. Nafamostat has been reported as a treatment
for pancreatitis and abnormal coagulation that occur frequently in COVID-19 patients [49].
In the early phases of the COVID-19 treatment and for the treatment of influenza, camostat
is used [50]. Gastric ulcers are treated with farotine, which has few side effects and
an adequate efficacy and reduces iNOS activity [51]. With its immune system boosting
effects, Nitazoxanide improves the respiratory distress associated with SARS-CoV-2 [52].
Combined with other COVID-19 treatments, ivermectin lowers mortality rates and hospital
stays for moderate COVID-19 patients [53].
Researchers used resilient distributed dataset programming to implement the density
peak-based clustering algorithm in their study [54]. A system for identifying sickness and
treatment association rules was proposed to identify disease diagnosis recommendations.
Unfortunately, the outbreak of coronavirus has limited the availability of legitimate clinical
resources, such as doctors, nurses, and equipment. Due to the distress of the medical
profession, a lot of people are dying. Shen et al. [55] outlined a system for performing
infectious disease diagnoses and clinical decisions. In the proposed system, antibiotic usage
is recommended using the naive Bayes classifier, and the ontological relations and rules are
accurately stored in Neo4j.
Fairness is the major bias arising from recommender systems. Certain characteristics,
such as race, gender, age, qualification, or property, are not represented equally in the
dataset. In the case of unbalanced data, it is possible to highlight overrepresented groups in
the rankings while reducing visibility for underrepresented groups. According to previous
studies, the feedback loop causes the high usage medicines to become more popular
and the low usage medicines to become less popular. Using the Type 2 fuzzy ontology
and the wearable sensors for diabetes treatments, another study has reported that drugs
and diet plans are available to patients [56]. Based on the findings of the authors, the
proposed system is effective in extracting diabetic patients’ risk factors and recommending
drug therapy.
Algorithms 2022, 15, 186 9 of 11

In this paper, the accuracy of the proposed system framework gradually increased
to 98.5%, which indicates that the ANN is the accepted model for drug recommender
systems. After pre-processing, the patient feature spaces and the drug-drug interaction
are obtained from the drug-target association. Health care data provide drug information
for infectious diseases to the medical recommender system. This system compares the
patient’s choices based on their similarity and has a superior level of accuracy to other
state-of-the-art technologies. Since the proposed methodology builds both the interactions
between a disease and the drug and the interactions between a drug and a drug, as well
as between a drug and target, the hybrid restricted Boltzmann machine outperformed the
logistic regression by approximately 3.9%.

6. Conclusions
This work involved deep learning techniques to make unbiased and fair drug recom-
mendations. The loss function is used with the input data to improve fairness and accuracy.
When a patient with comorbidities comes for a recommendation, we obtain the patient’s
lab test results. A diagnosis is made by the DRS based on the features of the patient, and
we rely on this diagnosis to determine the drug category in the system. The architecture
uses statistical analysis to improve accuracy by adjusting the threshold value, which also
balances fairness.

Author Contributions: Conceptualization, U.B. and G.B.; methodology, U.B.; software, G.B.; valida-
tion, G.B. and U.B.; formal analysis, U.B. and N.C.; investigation, U.B.; resources, G.B.; data curation,
U.B.; writing—original draft preparation, U.B.; writing—review and editing, G.B.; visualization, U.B.;
supervision, G.B.; project administration, G.B.; funding acquisition, G.B. and N.C. All authors have
read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: Not applicable.
Conflicts of Interest: No author has any potential conflict of interest during the submission and
publication of the manuscript.

References
1. Battineni, G.; Sagaro, G.G.; Chintalapudi, N.; Di Canio, M.; Amenta, F. Assessment of Awareness and Knowledge on Novel
Coronavirus (COVID-19) Pandemic among Seafarers. Healthcare 2021, 9, 120. [CrossRef] [PubMed]
2. Goh, J.M.; Gao, G.; Agarwal, R. The creation of social value: Can an online health community reduce rural–urban health
disparities? MIS Q. 2016, 40, 247–263. [CrossRef]
3. Cook, S.F.; Bies, R.R. Disease Progression Modeling: Key Concepts and Recent Developments. Curr. Pharmacol. Rep. 2016, 2,
221–230. [CrossRef] [PubMed]
4. Koren, Y. Factorization Meets the Neighborhood: A Multifaceted Collaborative Filtering Model. In Proceedings of the 14th
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, NV, USA, 24–27 August 2008;
pp. 426–434.
5. Ye, Q.; Hsieh, C.Y.; Yang, Z.; Kang, Y.; Chen, J.; Cao, D.; He, S.; Hou, T. A unified drug-target interaction prediction framework
based on knowledge graph and recommendation system. Nat. Commun. 2021, 12, 6775. [CrossRef]
6. Fox, S.; Duggan, M. Health Online 2013; Pew Research Internet Project Report: Washington, DC, USA, 2013.
7. Chintalapudi, N.; Angeloni, U.; Battineni, G.; di Canio, M.; Marotta, C.; Rezza, G.; Sagaro, G.G.; Silenzi, A.; Amenta, F. LASSO
Regression Modeling on Prediction of Medical Terms among Seafarers’ Health Documents Using Tidy Text Mining. Bioengineering
2022, 9, 124. [CrossRef]
8. Lu, J.; Wu, D.; Mao, M.; Wang, W.; Zhang, G. Recommender system application developments: A survey. Decis. Support Syst.
2015, 74, 12–32. [CrossRef]
9. Huang, F.; Wang, S.; Chan, C.-C. Predicting disease by using data mining based on healthcare information system. In Proceedings
of the 2012 IEEE International Conference on granular computing, Washington, DC, USA, 11–13 August 2012; pp. 191–194.
10. Subramaniyaswamy, V.; Manogaran, G.; Logesh, R.; Vijayakumar, V.; Chilamkurti, N.; Malathi, D.; Senthilselvan, N. An ontology
driven personalized food recommendation in IoT-based healthcare system. J. Supercomput. 2019, 75, 3184–3216. [CrossRef]
11. Liang, T.P. Recommender systems for decision support. Expert Syst. Appl. 2008, 45, 385–386.
Algorithms 2022, 15, 186 10 of 11

12. Adomavicius, G.; Tuzhilin, A. Toward the Next Generation of Recommender Systems: A Survey of the State of the Art and
Possible Extensions. IEEE Trans. Knowl. Data Eng. 2005, 17, 734–749. [CrossRef]
13. Esfandiari, N.; Babavalian, R.; Moghadam, E.; Tabar, V. Knowledge discovery in medicine: Current issue and future trend.
Expert Syst. Appl. 2014, 41, 4434–4463. [CrossRef]
14. Narducci, F.; Musto, C.; Polignano, M.; de Gemmis, M.; Lops, P.; Semeraro, G. A Recommender System for Connecting Patients to
the Right Doctors in the Healthnet Social Network. In Proceedings of the 24th International Conference on World Wide Web,
Florence, Italy, 18–22 May 2015; pp. 81–82.
15. Han, Q.; Ji, M.; de Troya, I.M.d.R.; Gaur, M.; Zejnilovic, L. A Hybrid Recommender System for Patient-Doctor matchmaking in
Primary Care. In Proceedings of the 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA),
Turin, Italy, 1–4 October 2018; pp. 481–490.
16. Hassan, S.; Syed, Z. From Netflix to heart attacks: Collaborative filtering in medical datasets. In Proceedings of the HI’10:
ACM International Health Informatics Symposium, IHI’10: ACM International Health Informatics Symposium, Arlington, VA,
USA, 11–12 November 2010; pp. 128–134.
17. Teodorovic, D.; Selmic, M.; Mijatovic, L. Combining case-based reasoning with Bee Colony Optimization for dose planning in
well differentiated thyroid cancer treatment. Expert Syst. Appl. 2013, 40, 2147–2155. [CrossRef]
18. Savova, G.K.; Masanz, J.J.; Ogren, P.V.; Zheng, J.; Sohn, S.; Kipper, K.C.; Chute, C.G. Mayo clinical text analysis and knowledge
extraction system(cTAKES): Architecture component evaluation and applications. J. Am. Med. Inform. Assoc. 2010, 17, 507–513.
[CrossRef] [PubMed]
19. Davis, D.A.; Chawla, N.V.; Christakis, A.; Barabasi, A.L. Time to CARE: A collaborative engine for practical disease prediction.
Data Min. Knowl. Discov. 2010, 20, 388–415. [CrossRef]
20. Komkhao, M.; Lu, J.; Zhang, L. Determine Pattern Similarity in a Medical Recommender System. In International Conference on
Data and Knowledge Engineering; Springer: Berlin/Heidelberg, Germany, 2012; pp. 103–114.
21. Lu, X.; Huang, Z.; Duan, H. Supporting adaptive clinical treatment processes through recommendations. Comput. Methods
Programs Biomed. 2012, 107, 413–424. [CrossRef]
22. Caorsar, D.; Sleeman, D.H. Developing Knowledge Based System Using the Semantic web. In Proceedings of the International
BCS Conference, London, UK, 22–24 September 2008; pp. 29–40.
23. Burke, R. Knowledge recommender system. Encycl. Libr. Inf. Syst. 2000, 69 (Suppl. 32), 175–186.
24. Wiesner, M.; Pfeifer, D. Health recommender systems: Concepts requirements technical basics and challenges. Int. J. Environ. Res.
Public Health 2014, 11, 2580–2607. [CrossRef] [PubMed]
25. Bodadilla, J.; Ortega, F.; Hernando, A.; Gutierrez, A. Recommender system survey. Knowl. Based Syst. 2013, 46, 109–132. [CrossRef]
26. Masaba, B.B.; Moturi, J.K.; Taiswa, J.; Mmusi-Phetoe, R.M. Devolution of healthcare system in Kenya: Progress and challenges.
Public Health 2020, 189, 135–140. [CrossRef]
27. Berners, L.; Hendler, J.; Lassila, O. The semantic web. Sci. Am. 2001, 284, 28–37. [CrossRef]
28. Shardanad, U.; Maes, P. Social information filtering: Algorithms for automating word of mouth. Experts Syst. Appl. 1995,
95, 210–217.
29. Leilei, S.; Chuanren, L.; Chonghui, G.; Hui, X.; Yanming, X. Data-Driven Automatic Treatment Regimen Development and
Recommendation. In Proceedings of the International Conference on Knowledge Discovery and Data Mining(SIGKDD2016),
San Francisco, CA, USA, 13–17 August 2016; pp. 1865–1874.
30. Shimada, K.; Takada, H.; Mitsuyama, S.; Matsuo, H.; Otake, H.; Kunishima, H.; Kanemitsu, K.; Kaku, M. Drug recommendation
system for patients with infectious diseases. AMIA Annu. Symp. Proc. 2005, 2005, 1112.
31. Doulaverakis, C.; Nikolaidis, G.; Kleontas, A.; Kompatsiaris, I. GalenOWL: Ontology based drug recommendations discovery.
J. Biomed. Semat. 2012, 3, 14. [CrossRef] [PubMed]
32. Zhang, Y.Z.; Dafang, H.; Mohammad, A.; Atif, P.; Limei, P. CADRE: Cloud assisted drug recommendation service for online
pharmacies. Mob. Netw. Appl. 2014, 20, 348–355. [CrossRef]
33. Zhou, Y.; Hou, Y.; Shen, Y.; Huang, W.; Martin, F.; Cheng, F. Network based drug repurposing for novel coronavirus2019-
ncov/SARS-CoV-2. Nat. Cell Discov. 2020, 6, 14. [CrossRef]
34. Li, J.; Zheng, B.; Chen, B.; Butte, A.J.; Swamidass, S.J.; Lu, Z. A survey of current trends in computational drug repositioning.
Brief. Bioinform. 2016, 17, 2–12. [CrossRef]
35. Zeng, X.; Zhu, S.; Liu, Y.; Zhou, R.; Nussinov, C.F. DeerDR: A network based deep learning approach to in silico drug
repositionoing. Bioinformatics 2019, 35, 5191–5198. [CrossRef]
36. Aliper, A.; Plis, S.; Artemov, A.; Ulloa, P.; Mamoshina, A.; Zhavoronkov, A. Deep learning applications for predicting pharmaco-
logical properties of drugs and drug repurposing using transcriptomic data. Mol. Pharmcy 2016, 13, 2524–2530. [CrossRef]
37. Haifeng, L.; Hongfei, L.; Chen, S.; Liang, Y.; Yuan, L.; Bo, X.; Zhihao, Y.; Jian, W.; Yuanyuan, S. A network representation approach
for COVID-19 drug recommendation. Methods 2022, 198, 3–10.
38. SNOMED CT Standard Ontology Based on the Ontology for General Medical Science. Available online: https://bioportal.
bioontology.org/ontologies/SCTO (accessed on 16 May 2022).
39. Available online: https://go.drugbank.com/drugs (accessed on 8 January 2022).
40. Wang, X.; Sontag, D.; Wang, F. Unsupervised Learning of Disease Progression Models. In Proceedings of the 20th ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, 24–27 August 2014; pp. 85–94.
Algorithms 2022, 15, 186 11 of 11

41. Kumar, N.K.; Vigneswari, D. A Drug Recommendation System for Multi-Disease in Health Care using Machine Learning.
In Advances in Communication and Computational Technology; Springer: Berlin/Heidelberg, Germany, 2021; pp. 1–12.
42. Stark, B.; Knahl, C.; Aydin, M.; Samarah, M.; Elish, K.O. Better choice: A migraine drug recommendation system based on Neo4J.
In Proceedings of the 2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA), Beijing,
China, 8–11 September 2017; pp. 382–386.
43. Qian, Z.; Guangquan, Z.; Jie, L.; Wu, D. A framework of hybrid recommender system for personalized clinical prescription.
In Proceedings of the 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), Taipei, Taiwan,
24–27 November 2015; pp. 1–7.
44. Schäfer, H.; Hors-Fraile, S.; Karumur, R.P.; Valdez, A.C.; Said, A.; Torkamaan, H.; Ulmer, T.; Trattner, C. Towards health (aware)
recommender systems. In Proceedings of the DH’17: International Conference on Digital Health, London, UK, 2–5 July 2017;
pp. 157–161.
45. Bankhele, S.; Mhaske, A.; Bhat, S.; Shinde, S.V. A diabetic healthcare recommendation system. Int. J. Comput. Appl. 2017, 167,
14–18. [CrossRef]
46. Mahmoud, N.; Elbeh, H. Irs-t2d: Individualize recommendation system for type2 diabetes medication based on ontology and
swrl. In Proceedings of the 10th International Conference on Informatics and Systems, Giza, Egypt, 9–11 May 2016; pp. 203–209.
47. Toutet, F.; de Lamnallerie, X. Of chloroquine and COVID-19. Antivir. Res. 2020, 177, 104762.
48. Meini, S.; Pagotto, A.; Longo, B.; Vendramin, I.; Pecori, D.; Tascini, C. Role of Lopinavir/Ritonavir in the Treatment of COVID-19:
A Review of Current Evidence, Guideline Recommendations and Perceptives. J. Clin. Med. 2020, 9, 2050. [CrossRef] [PubMed]
49. Takahashi, W.; Yoneda, T.; Koba, H.; Ueda, T.; Tsuji, N.; Ogawa, H.; Asakura, H. Potential mechanisms of nafamostat therapy
for severe COVID-19 pneumonia with disseminated intravascular coagulation. Int. J. Infect. Dis. 2021, 102, 529–531. [CrossRef]
[PubMed]
50. Breining, P.; Frolund, A.L.; Hojen, J.F.; Gunst, J.D.; Staerke, N.B.; Saedder, E.; Thomas, M.C.; Little, P.; Nielsen, L.P.;
Sogaard, O.S.; et al. Camostat mesylate against SARS-CoV-2 and COVID-19 Rationale, dosing and safety. Basic Clin.
Pharmacol. Toxicol. 2021, 128, 204–212. [CrossRef] [PubMed]
51. Sehitoglu, M.H.; Oztopuz, O.; Karaboga, I.; Ovali, M.A.; Uzun, M. Human Acid has a protective effect on gastric ulcer by
alleviating inflammation in rats. Cytol. Genet. 2022, 56, 84–97. [CrossRef]
52. Amit, S.; Lokhande, P.; Devarajan, V. A review on possible mechanistic insights of Nitazoxanide for repurposing in COVID-19.
Eur. J. Pharmacol. 2021, 891, 173748.
53. Sherief, A.E.; Noor, R.A.; Badawi, R.; Eslam, M.K.; Soliman, S.E.S.; Mohamed, S.A.E.G.; Elbahnasawy, M.; Moustafa, E.F.; Hassany,
S.M.; Medhat, M.A.; et al. Clinical study evaluating the efficacy of ivermectin in COVID-19 treatment: A randomized controlled
study. J. Med. Virol. 2021, 93, 5833–5838.
54. Chen, J.; Li, K.; Rong, H.; Bilal, K.; Yang, N.; Li, K. A disease diagnosis and treatment recommendation system based on big data
mining and cloud computing. Inf. Sci. 2018, 435, 124–149. [CrossRef]
55. Shen, Y.; Yuan, K.; Chen, D.; Colloc, J.; Yang, M.; Li, Y.; Lei, K. An ontology-driven clinical decision support system (IDDAP) for
infectious disease diagnosis and antibiotic prescription. Artif. Intell. Med. 2018, 86, 20–32. [CrossRef]
56. Ali, F.; Islam, S.M.R.; Kwak, D.; Khan, P.; Ullah, N.; Yoo, S.-J.; Kwak, K.S. Type-2 fuzzy ontology-aided recommender systems for
IoT–based healthcare. Comput. Commun. 2018, 119, 138–155. [CrossRef]