Thrombocytopenia is a medical condition where blood platelet count drops very low. This drop in platelet count can be attributed to many causes including medication, sepsis, viral infections, and autoimmunity. Clinically, the presence of thrombocytopenia might be very dangerous and is associated with poor outcomes of patients due to excessive bleeding if not addressed quickly enough. Hence, early detection and evaluation of thrombocytopenia is essential for rapid and appropriate intervention for these patients. Since artificial intelligence is able to combine and evaluate many linear and nonlinear variables simultaneously, it has shown great potential in its application in the early diagnosis, assessing the prognosis and predicting the distribution of patients with thrombocytopenia.
1. Introduction
Thrombocytopenia is a medical condition characterized by low platelet counts. There are many causes thrombocytopenia which can be broadly classified into decreased production, increased sequestration, and increased platelet destruction [
1]. The pathogenesis of thrombocytopenia is very complex and can be attributed to a multitude of causes. The decreased production of platelets can be related to bone marrow suppression commonly seen in conditions such as leukemia, patients taking chemotherapy, and in sepsis. Increased sequestration of platelets in the spleen is another major category of conditions that cause thrombocytopenia. Typically, this is seen in patients with splenomegaly, hypersplenism and in patients with portal hypertension. The increase in platelet destruction or utilization in peripheral blood is the final category in thrombocytopenia. Typically, this occurs in conditions where platelets are quickly used up or destroyed by autoantibodies [
2]. It is important to note that conditions that cause thrombocytopenia do not exclusively affect one pathological pathway and may involve multiple mechanisms simultaneously such as increased decreased production and sequestration. The diagnosis and treatment of thrombocytopenia require a thorough understanding of the underlying causes and the patient’s medical history. Thrombocytopenia is usually termed based on its causes. For example, when thrombocytopenia is caused by drugs it is termed drug induced immune thrombocytopenia (DITP). Similarly, when caused by sepsis it is termed sepsis associated thrombocytopenia (SAT) [
3].
Artificial intelligence (AI) is the simulation of human intelligence by computer programs. These programs are based on a set of algorithms that allow machines to mimic human intelligence through learning and problem solving. Although AI has previously been used in healthcare to automate hospital systems, recently, it has also been utilized in the diagnosis, early detection, and monitoring of diseases [
4,
5]. In recent years, there have been several successful applications of AI in various medical conditions, such as the diagnosis of LA fibrillation and evaluation of prognosis in COVID-19 [
6,
7]. This has been made possible because of machine learning (ML), which is a type of AI that utilizes datasets to learn and recognize patterns and create predictions based on them [
8]. What makes these algorithms unique is the fact that they can analyze linear and nonlinear variables simultaneously. This allows them to recognize patterns in a very complex manner that can be used to make extremely accurate predictions [
4,
9]. With the advent of artificial intelligence (AI), healthcare providers can leverage the power of machine learning algorithms and predictive analytics to improve the accuracy and efficiency of thrombocytopenia diagnosis and treatment.
2. Applications of Artificial Intelligence in Thrombocytopenia
2.1. Sepsis Associated Thrombocytopenia
Sepsis is defined as a life-threatening condition characterized by organ dysfunction due to a dysregulated immune response to an infectious agent [
20]. It is referred to as “septic shock” when circulatory and cellular metabolic abnormalities become present leading to a considerable increase in morbimortality [
21]. Almost 50% of patients with sepsis in the intensive care unit (ICU) develop thrombocytopenia, termed as SAT [
22,
23]. The mechanisms behind SAT are believed to be complex but are mainly associated with bone marrow suppression accompanied by endothelial dysfunction. This combination results in reduced production of new platelets and increased utilization of platelets due to disseminated intravascular coagulation and systemic inflammation. Clinically, the development of thrombocytopenia in sepsis patients is an indication of poor prognosis. Hence, the use of AI for early identification and risk prediction in these patients can be of great value.
2.1.1. Diagnosis
The early detection of SAT is extremely important in a clinical setting as research has shown that platelet transfusions protect these patients from possibly fatal bleeding [
27]. However, the issue with conventional monitoring of platelet count is that by the time SAT is identified in the patient the patient remains at risk of severe bleeding for a few days before receiving platelet transfusions due to the delay between diagnosis and transfusion [
21]. Hence, ML algorithms that track platelet count changes in patients can provide a major advantage for them, as it allows for early detection of patients at high risk for SAT.
A
recent
publication
by
Jiang
X
and
others
attempted
to
address
this
issue
by
utilizing
four
ML
algorithms
(Random
Forest
(RF),
Bayes
(Bayesian),
Neural
Network
(NNET), and
Gradient
Boosting
Machine
(GB))
to
assess
the
decrease
in
platelet
count,
as
well
as
other
variables
in
ICU
patients
suffering
from
sepsis
for
the
early
detection
of
patients
at
risk
of
thrombocytopenia
or
severe
thrombocytopenia.
External validation of the models for predicting thrombocytopenia showed that the NNET and GB models had the best predictions with a good AUC of 73% and 72%, respectively. There were no statistically significant differences between the two models at predicting thrombocytopenia in sepsis patients. Meanwhile, the RF and Bayes models had poorer predictive ability with an area under the ROC of 63% and 54%, respectively. Confusion matrix results for thrombocytopenia prediction showed that NNET had the highest precision and accuracy of 0.68 and 0.71, respectively. For the prediction of severe thrombocytopenia, the AUC for all ML algorithms was higher than that of thrombocytopenia prediction
[19].
2.1.2. Prognosis
As stated previously, thrombocytopenia is associated with poor prognosis in sepsis patients. Hence, it is important to properly assess the prognosis of patients with SAT to ensure proper care for these patients. Recent studies have shown that red cell distribution width (RDW) is a possible indicator for poor prognosis in various cancers and cardiovascular disease [
29,
30,
31]. Several studies have also shown that RDW has significant clinical utility as an independent predictor of poor prognosis in critically ill patients with sepsis and SAT. RDW is reliable in reflecting the levels of systemic inflammation in these patients [
32,
33,
34]. Since RDW is routinely measured clinically in a relatively inexpensive process, it could prove to be a useful ML marker for assessing prognosis in sepsis patients with SAT.
A recent publication by Ling J et al. has utilized eXtreme Gradient Boosting (XGBoost), a ML algorithm, to predict the 28-day mortality risk for sepsis patients based on 15 variables including RDW. The results of the paper showed that 28-day mortality in sepsis patients with thrombocytopenia was significantly higher than those without thrombocytopenia at the baseline (48.2% vs. 38.5%, respectively). SHAP interpretation of the XGBoost indicated that RDW was the second most important predictor of 28-day mortality in these patients following the SOFA scores. When comparing the subgroups of thrombocytopenia through AUC analysis, RDW was shown to be the most important predictor of 28-day mortality in thrombocytopenic patients with an area under the ROC of 0.646. An RDW of 16.05 displayed the best sensitivity and specificity for the prediction of mortality in these patients (70% and 57%, respectively) [27].
2.2. Drug-Induced Immune Thrombocytopenia
DITP is a common life-threatening complication seen in patients taking multiple drugs at the same time [
35]. This clinical syndrome is typically associated with severe bleeding that could ultimately result in death. There are many pathological mechanisms discussed in the literature to explain the causative mechanisms behind DITP [
35,
36,
37,
38]. However, the most widely accepted mechanisms are direct bone marrow suppression by drugs and the development of drug-dependent antibodies (DDAbs) that activate platelets, ultimately leading to their depletion [
38]. The main dilemma with DITP is that it is challenging to diagnose clinically, and it is even more problematic to identify the causative drug [
39]. Moreover, the current experimental invitro methods of DITP diagnosis through DDAbs are unreliable, expensive, time-consuming, and are only available in a few platelet-specialized laboratories [
40]. Currently, the most effective approach for the treatment of patients with DITP is the cessation of the causative drug [
41].
2.2.1. Diagnosis of DITP
Linezolid is a synthetic antimicrobial used in the treatment of infections. Several studies have shown that linezolid could lead to linezolid associated thrombocytopenia (LAT) a type of DITP [
42,
43,
44]. The identification of LAT in patients taking linezolid treatment for infections may be difficult and time-consuming. To address this, Takahashi and colleagues conducted a study to create a classification tree model that predicts LAT in patients taking linezolid treatment. A total of 74 patients receiving linezolid treatment were retrospectively included in the study. LAT was defined as a 25% decline in platelet count from baseline. The baseline platelet count; age; total linezolid concentration; platelet count changes at 24, 48, 72, 96, and 120 h; creatinine clearance; and body weight were used as predictors for LAT in these patients. Binary decision trees were used to utilizing different combinations of the predictor variables to create tree models for LAT prediction. These trees are ML algorithms that classify observations by creating a sequence of binary questions. Binary questions are formed by creating the best possible splits for the data and repeats till further branching no longer improves the classification of observations. Trees were then pruned to avoid overfitting of the model to the learning data. The tree model with the lowest misclassification rate was taken as the final model [
13].
Another drug that is commonly associated with DITP is heparin. Approximately 1–3% of all patients treated with heparin develop HIT, and similarly to all other types of induced thrombocytopenia, it is a life-threatening condition [
45]. A major issue seen in the normal diagnostic approach for DITPs is that misdiagnosis is common due to lack of diagnostic data utilized [
46,
47]. A study by Nilius and others utilized ML algorithms that integrate clinical and laboratory information to diagnose HIT more accurately than the traditional approach by the American Society of Hematology (ASH) [
15].
2.2.2. Predicting Drugs Causing DITP
Wang, B. et al. developed a several models to predict whether a drug could lead to DITP using seven different ML methods [
16]. A DITP dataset was collected from an online database, “platelets on the web”, which contained information on the compounds tested with DDAb [
48]. Compounds that had detectable DDAbs were classified as DITP toxicants (93) and those without DDAbs as non-toxicants (132). The dataset was then randomly divided in an 8:2 ratio into training and external validation sets, respectively. Support vector machine (SVM), k-nearest neighbor (k-NN), RF, naive bayes (NB), artificial neural network (ANN), adaptive boosting (AdaBoost), and XGBoost were used to produce binary classification models for DITP. Hyperparameters for each model was optimized by five-fold cross-validation, and the variance was reduced by 10× cross-validation. These models utilized six molecular fingerprints and three molecular descriptors to predict whether or not a drug can cause DITP [
16].
2.3. Hospital Acquired Thrombocytopenia
A common bleeding disorder following surgery is hospital acquired thrombocytopenia (HAT), This form of thrombocytopenia can be attributed to some of the previously discussed topics such as DIT or SAT. In a research paper conducted by Cheng and others, 7 ML models (GB, RF, logistic regression (LogR), XGBoost, multilayer perceptron, SVM, and k-NN) were created to predict patients at risk of HAT following surgery. Adult patients who were administered to the ICU following surgery were included in the study and divided in a 7:3 ratio into training and testing sets, respectively. Ten-fold validation was performed on the models generated. The
results
of
internal
validation
showed
that
the
RF
and
GB
models
outperformed
all
other
models
in
the
prediction
with
an
AUC
of
0.834
and
0.828,
respectively,
and
there
were
no
statistically
significant
differences
between
the
two
models.
Both
models
had
a
high
sensitivity
of
79.3%
and
73.6%,
respectively.
Specificity
for
the
models
were
79.1%
and
73.7%,
respectively [
46].
2.4. Immune Thrombocytopenia
Immune thrombocytopenia (ITP) is an autoimmune bleeding disorder [
49]. It is clinically characterized by low platelet count and the presence of autoantibodies to platelets [
50]. Diagnosis is typically made through the exclusion of all other causes of thrombocytopenia. ITP is considered a self-limiting disease in children where prognosis is good, and remission occurs easily. In adults however, ITP is chronic with a higher mortality rate [
51,
52]. The pathogenesis of ITP is not well understood but involves the formation of IgG autoantibodies that target the glycoproteins IIb-IIIa on platelets. This results in the phagocytosis of these platelets hence leading to a drop in circulating platelet count and, ultimately, thrombocytopenia [
50].
2.4.1. Diagnosis
Kim, T. and others used a clinical database to create five ML models (RF, NB, LogR, SVM, and AdaBoost) to predict chronic immune thrombocytopenia in pediatric patients with ITP. A total of 969 pediatric patients with ITP were included in the study, of which, 332 had confirmed acute ITP and 253 with chronic ITP. Clinical (age, gender, race, ethnicity, presence of primary ITP) and laboratory variables (baseline platelet count, leukocyte count, lymphocyte count, eosinophil count, mean platelet volume, anti-nuclear antibody, immature platelet fraction, direct antiglobulin test, and immunoglobin levels) were used in the ML models to predict chronic ITP and 10-fold cross-validation was performed.
2.4.2. Prognosis
One of the main indicators for poor prognosis in patients with any form of thrombocytopenia is bleeding. A study by An, Z. Y. and others developed ML models to predict the risk of critical bleeds in patients with ITP. Data from eight centers in China were used to create this model utilizing nine predictor variables (Platelet count, age, onset of ITP, infection, type of ITP, bleeding of skin and mucosa, low platelet count, cardiovascular disease, and uncontrolled diabetes). Out of all the models, the RF model outperformed all others (AUC: 0.901 when externally validated) [
55].
3. Conclusions
ML algorithms can possibly provide a faster, reliable evaluation of patients with thrombocytopenia and, in some cases, may even outperform the current approaches for evaluating the diagnosis and prognosis of patients.
This entry is adapted from the peer-reviewed paper 10.3390/diagnostics13061060